Upload 12 files
Browse files- README.md +9 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- all_results.json +7 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +34 -0
- train_results.json +7 -0
- trainer_log.jsonl +308 -0
- trainer_state.json +1870 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.4.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "cardio-llama-2-7b-miniguanaco-v16",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32.0,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88114b3589ed4980176efc056871f1448e44338b12d46edfaa85260b819f29f3
|
| 3 |
+
size 16822989
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.862230001638333,
|
| 4 |
+
"train_runtime": 23418.3393,
|
| 5 |
+
"train_samples_per_second": 2.1,
|
| 6 |
+
"train_steps_per_second": 0.131
|
| 7 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"legacy": false,
|
| 20 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
+
"pad_token": null,
|
| 22 |
+
"padding_side": "right",
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"use_default_system_prompt": true
|
| 34 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.862230001638333,
|
| 4 |
+
"train_runtime": 23418.3393,
|
| 5 |
+
"train_samples_per_second": 2.1,
|
| 6 |
+
"train_steps_per_second": 0.131
|
| 7 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,308 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 3072, "loss": 0.9611, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9998692735249987e-05, "epoch": 0.01, "percentage": 0.33, "elapsed_time": "0:01:20", "remaining_time": "6:51:18"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 3072, "loss": 0.94, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9994771077715244e-05, "epoch": 0.02, "percentage": 0.65, "elapsed_time": "0:02:35", "remaining_time": "6:34:42"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 3072, "loss": 0.9521, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.998823543752733e-05, "epoch": 0.03, "percentage": 0.98, "elapsed_time": "0:03:49", "remaining_time": "6:28:10"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 3072, "loss": 0.9413, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9979086498191216e-05, "epoch": 0.04, "percentage": 1.3, "elapsed_time": "0:05:06", "remaining_time": "6:27:01"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 3072, "loss": 0.8717, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9967325216513785e-05, "epoch": 0.05, "percentage": 1.63, "elapsed_time": "0:06:27", "remaining_time": "6:30:40"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 3072, "loss": 0.9099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.995295282250373e-05, "epoch": 0.06, "percentage": 1.95, "elapsed_time": "0:07:44", "remaining_time": "6:28:37"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 3072, "loss": 0.9671, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.993597081924299e-05, "epoch": 0.07, "percentage": 2.28, "elapsed_time": "0:08:56", "remaining_time": "6:23:35"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 3072, "loss": 0.9971, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.991638098272951e-05, "epoch": 0.08, "percentage": 2.6, "elapsed_time": "0:10:10", "remaining_time": "6:20:20"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 3072, "loss": 0.9215, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.98941853616915e-05, "epoch": 0.09, "percentage": 2.93, "elapsed_time": "0:11:28", "remaining_time": "6:20:21"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 3072, "loss": 0.9008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.98693862773732e-05, "epoch": 0.1, "percentage": 3.26, "elapsed_time": "0:12:43", "remaining_time": "6:18:08"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 3072, "loss": 0.8907, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.98419863232921e-05, "epoch": 0.11, "percentage": 3.58, "elapsed_time": "0:14:00", "remaining_time": "6:17:05"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 3072, "loss": 0.8838, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.981198836496775e-05, "epoch": 0.12, "percentage": 3.91, "elapsed_time": "0:15:13", "remaining_time": "6:14:38"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 3072, "loss": 0.9156, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9779395539622024e-05, "epoch": 0.13, "percentage": 4.23, "elapsed_time": "0:16:32", "remaining_time": "6:14:15"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 3072, "loss": 0.8241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9744211255851046e-05, "epoch": 0.14, "percentage": 4.56, "elapsed_time": "0:17:51", "remaining_time": "6:13:51"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 3072, "loss": 0.8777, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9706439193268736e-05, "epoch": 0.15, "percentage": 4.88, "elapsed_time": "0:19:07", "remaining_time": "6:12:31"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 3072, "loss": 0.8757, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.966608330212198e-05, "epoch": 0.16, "percentage": 5.21, "elapsed_time": "0:20:20", "remaining_time": "6:10:13"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 3072, "loss": 0.8574, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.962314780287748e-05, "epoch": 0.17, "percentage": 5.53, "elapsed_time": "0:21:35", "remaining_time": "6:08:39"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 3072, "loss": 0.8419, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.957763718578041e-05, "epoch": 0.18, "percentage": 5.86, "elapsed_time": "0:22:50", "remaining_time": "6:07:07"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 3072, "loss": 0.8368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.952955621038482e-05, "epoch": 0.19, "percentage": 6.18, "elapsed_time": "0:24:07", "remaining_time": "6:05:51"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 3072, "loss": 0.9646, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9478909905055845e-05, "epoch": 0.2, "percentage": 6.51, "elapsed_time": "0:25:23", "remaining_time": "6:04:36"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 3072, "loss": 0.9666, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.942570356644386e-05, "epoch": 0.2, "percentage": 6.84, "elapsed_time": "0:26:40", "remaining_time": "6:03:26"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 3072, "loss": 0.9451, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.936994275893054e-05, "epoch": 0.21, "percentage": 7.16, "elapsed_time": "0:27:55", "remaining_time": "6:02:02"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 3072, "loss": 0.8937, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.931163331404694e-05, "epoch": 0.22, "percentage": 7.49, "elapsed_time": "0:29:12", "remaining_time": "6:00:51"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 3072, "loss": 0.9066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9250781329863606e-05, "epoch": 0.23, "percentage": 7.81, "elapsed_time": "0:30:30", "remaining_time": "6:00:04"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 3072, "loss": 0.8378, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9187393170352844e-05, "epoch": 0.24, "percentage": 8.14, "elapsed_time": "0:31:48", "remaining_time": "5:59:02"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 3072, "loss": 0.8696, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9121475464723175e-05, "epoch": 0.25, "percentage": 8.46, "elapsed_time": "0:33:07", "remaining_time": "5:58:14"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 3072, "loss": 0.8534, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9053035106726045e-05, "epoch": 0.26, "percentage": 8.79, "elapsed_time": "0:34:23", "remaining_time": "5:56:52"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 3072, "loss": 0.8417, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.898207925393484e-05, "epoch": 0.27, "percentage": 9.11, "elapsed_time": "0:35:38", "remaining_time": "5:55:28"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 3072, "loss": 0.8718, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.890861532699639e-05, "epoch": 0.28, "percentage": 9.44, "elapsed_time": "0:36:54", "remaining_time": "5:54:05"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 3072, "loss": 0.9024, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8832651008854845e-05, "epoch": 0.29, "percentage": 9.77, "elapsed_time": "0:38:13", "remaining_time": "5:53:14"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 3072, "loss": 0.8846, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8754194243948245e-05, "epoch": 0.3, "percentage": 10.09, "elapsed_time": "0:39:28", "remaining_time": "5:51:43"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 3072, "loss": 0.8569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.867325323737765e-05, "epoch": 0.31, "percentage": 10.42, "elapsed_time": "0:40:44", "remaining_time": "5:50:19"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 3072, "loss": 0.863, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.858983645404901e-05, "epoch": 0.32, "percentage": 10.74, "elapsed_time": "0:42:00", "remaining_time": "5:49:03"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 3072, "loss": 0.7955, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8503952617787983e-05, "epoch": 0.33, "percentage": 11.07, "elapsed_time": "0:43:14", "remaining_time": "5:47:25"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 3072, "loss": 0.913, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.84156107104275e-05, "epoch": 0.34, "percentage": 11.39, "elapsed_time": "0:44:32", "remaining_time": "5:46:24"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 3072, "loss": 0.8538, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8324819970868473e-05, "epoch": 0.35, "percentage": 11.72, "elapsed_time": "0:45:49", "remaining_time": "5:45:15"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 3072, "loss": 0.9323, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8231589894113584e-05, "epoch": 0.36, "percentage": 12.04, "elapsed_time": "0:47:07", "remaining_time": "5:44:07"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 3072, "loss": 0.8345, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.813593023027427e-05, "epoch": 0.37, "percentage": 12.37, "elapsed_time": "0:48:24", "remaining_time": "5:42:52"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 3072, "loss": 0.8482, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.803785098355105e-05, "epoch": 0.38, "percentage": 12.7, "elapsed_time": "0:49:43", "remaining_time": "5:41:54"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 3072, "loss": 0.9007, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.793736241118728e-05, "epoch": 0.39, "percentage": 13.02, "elapsed_time": "0:51:01", "remaining_time": "5:40:50"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 3072, "loss": 0.8718, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.783447502239645e-05, "epoch": 0.4, "percentage": 13.35, "elapsed_time": "0:52:14", "remaining_time": "5:39:11"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 3072, "loss": 0.8733, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7729199577263065e-05, "epoch": 0.41, "percentage": 13.67, "elapsed_time": "0:53:33", "remaining_time": "5:38:10"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 3072, "loss": 0.7678, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7621547085617406e-05, "epoch": 0.42, "percentage": 14.0, "elapsed_time": "0:54:49", "remaining_time": "5:36:53"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 3072, "loss": 0.8189, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.751152880588409e-05, "epoch": 0.43, "percentage": 14.32, "elapsed_time": "0:56:05", "remaining_time": "5:35:32"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 3072, "loss": 0.9303, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.739915624390463e-05, "epoch": 0.44, "percentage": 14.65, "elapsed_time": "0:57:21", "remaining_time": "5:34:13"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 3072, "loss": 0.8666, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.728444115173415e-05, "epoch": 0.45, "percentage": 14.97, "elapsed_time": "0:58:39", "remaining_time": "5:33:03"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 3072, "loss": 0.8999, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.716739552641237e-05, "epoch": 0.46, "percentage": 15.3, "elapsed_time": "0:59:57", "remaining_time": "5:31:55"}
|
| 48 |
+
{"current_steps": 480, "total_steps": 3072, "loss": 0.8813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7048031608708876e-05, "epoch": 0.47, "percentage": 15.62, "elapsed_time": "1:01:15", "remaining_time": "5:30:48"}
|
| 49 |
+
{"current_steps": 490, "total_steps": 3072, "loss": 0.9063, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.692636188184305e-05, "epoch": 0.48, "percentage": 15.95, "elapsed_time": "1:02:27", "remaining_time": "5:29:07"}
|
| 50 |
+
{"current_steps": 500, "total_steps": 3072, "loss": 0.8109, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.680239907017849e-05, "epoch": 0.49, "percentage": 16.28, "elapsed_time": "1:03:41", "remaining_time": "5:27:38"}
|
| 51 |
+
{"current_steps": 510, "total_steps": 3072, "loss": 0.825, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.667615613789232e-05, "epoch": 0.5, "percentage": 16.6, "elapsed_time": "1:04:59", "remaining_time": "5:26:30"}
|
| 52 |
+
{"current_steps": 520, "total_steps": 3072, "loss": 0.9117, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.654764628761936e-05, "epoch": 0.51, "percentage": 16.93, "elapsed_time": "1:06:13", "remaining_time": "5:25:01"}
|
| 53 |
+
{"current_steps": 530, "total_steps": 3072, "loss": 0.8901, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6416882959071395e-05, "epoch": 0.52, "percentage": 17.25, "elapsed_time": "1:07:33", "remaining_time": "5:24:00"}
|
| 54 |
+
{"current_steps": 540, "total_steps": 3072, "loss": 0.8362, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.628387982763163e-05, "epoch": 0.53, "percentage": 17.58, "elapsed_time": "1:08:46", "remaining_time": "5:22:28"}
|
| 55 |
+
{"current_steps": 550, "total_steps": 3072, "loss": 0.9148, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.614865080292449e-05, "epoch": 0.54, "percentage": 17.9, "elapsed_time": "1:10:03", "remaining_time": "5:21:13"}
|
| 56 |
+
{"current_steps": 560, "total_steps": 3072, "loss": 0.9449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.601121002736095e-05, "epoch": 0.55, "percentage": 18.23, "elapsed_time": "1:11:18", "remaining_time": "5:19:52"}
|
| 57 |
+
{"current_steps": 570, "total_steps": 3072, "loss": 0.7937, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.58715718746595e-05, "epoch": 0.56, "percentage": 18.55, "elapsed_time": "1:12:34", "remaining_time": "5:18:34"}
|
| 58 |
+
{"current_steps": 580, "total_steps": 3072, "loss": 0.835, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5729750948342926e-05, "epoch": 0.57, "percentage": 18.88, "elapsed_time": "1:13:53", "remaining_time": "5:17:27"}
|
| 59 |
+
{"current_steps": 590, "total_steps": 3072, "loss": 0.9117, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.558576208021105e-05, "epoch": 0.58, "percentage": 19.21, "elapsed_time": "1:15:08", "remaining_time": "5:16:06"}
|
| 60 |
+
{"current_steps": 600, "total_steps": 3072, "loss": 0.7855, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5439620328789593e-05, "epoch": 0.59, "percentage": 19.53, "elapsed_time": "1:16:25", "remaining_time": "5:14:50"}
|
| 61 |
+
{"current_steps": 610, "total_steps": 3072, "loss": 0.8816, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.529134097775539e-05, "epoch": 0.6, "percentage": 19.86, "elapsed_time": "1:17:40", "remaining_time": "5:13:28"}
|
| 62 |
+
{"current_steps": 620, "total_steps": 3072, "loss": 0.8344, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.514093953433792e-05, "epoch": 0.61, "percentage": 20.18, "elapsed_time": "1:19:00", "remaining_time": "5:12:25"}
|
| 63 |
+
{"current_steps": 630, "total_steps": 3072, "loss": 0.8936, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.498843172769763e-05, "epoch": 0.61, "percentage": 20.51, "elapsed_time": "1:20:18", "remaining_time": "5:11:18"}
|
| 64 |
+
{"current_steps": 640, "total_steps": 3072, "loss": 0.9126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4833833507280884e-05, "epoch": 0.62, "percentage": 20.83, "elapsed_time": "1:21:35", "remaining_time": "5:10:02"}
|
| 65 |
+
{"current_steps": 650, "total_steps": 3072, "loss": 0.8691, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4677161041152005e-05, "epoch": 0.63, "percentage": 21.16, "elapsed_time": "1:22:50", "remaining_time": "5:08:39"}
|
| 66 |
+
{"current_steps": 660, "total_steps": 3072, "loss": 0.8383, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.451843071430236e-05, "epoch": 0.64, "percentage": 21.48, "elapsed_time": "1:24:02", "remaining_time": "5:07:09"}
|
| 67 |
+
{"current_steps": 670, "total_steps": 3072, "loss": 0.9212, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.435765912693686e-05, "epoch": 0.65, "percentage": 21.81, "elapsed_time": "1:25:22", "remaining_time": "5:06:04"}
|
| 68 |
+
{"current_steps": 680, "total_steps": 3072, "loss": 0.8768, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.419486309273781e-05, "epoch": 0.66, "percentage": 22.14, "elapsed_time": "1:26:40", "remaining_time": "5:04:53"}
|
| 69 |
+
{"current_steps": 690, "total_steps": 3072, "loss": 0.9103, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.403005963710655e-05, "epoch": 0.67, "percentage": 22.46, "elapsed_time": "1:27:55", "remaining_time": "5:03:32"}
|
| 70 |
+
{"current_steps": 700, "total_steps": 3072, "loss": 0.8308, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.386326599538295e-05, "epoch": 0.68, "percentage": 22.79, "elapsed_time": "1:29:15", "remaining_time": "5:02:27"}
|
| 71 |
+
{"current_steps": 710, "total_steps": 3072, "loss": 0.9243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.369449961104289e-05, "epoch": 0.69, "percentage": 23.11, "elapsed_time": "1:30:36", "remaining_time": "5:01:27"}
|
| 72 |
+
{"current_steps": 720, "total_steps": 3072, "loss": 0.8994, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.352377813387398e-05, "epoch": 0.7, "percentage": 23.44, "elapsed_time": "1:31:50", "remaining_time": "5:00:00"}
|
| 73 |
+
{"current_steps": 730, "total_steps": 3072, "loss": 0.9656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.335111941812975e-05, "epoch": 0.71, "percentage": 23.76, "elapsed_time": "1:33:05", "remaining_time": "4:58:39"}
|
| 74 |
+
{"current_steps": 740, "total_steps": 3072, "loss": 0.901, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3176541520662426e-05, "epoch": 0.72, "percentage": 24.09, "elapsed_time": "1:34:25", "remaining_time": "4:57:33"}
|
| 75 |
+
{"current_steps": 750, "total_steps": 3072, "loss": 0.924, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3000062699034544e-05, "epoch": 0.73, "percentage": 24.41, "elapsed_time": "1:35:43", "remaining_time": "4:56:20"}
|
| 76 |
+
{"current_steps": 760, "total_steps": 3072, "loss": 0.8821, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.28217014096095e-05, "epoch": 0.74, "percentage": 24.74, "elapsed_time": "1:36:57", "remaining_time": "4:54:57"}
|
| 77 |
+
{"current_steps": 770, "total_steps": 3072, "loss": 0.8631, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.264147630562141e-05, "epoch": 0.75, "percentage": 25.07, "elapsed_time": "1:38:14", "remaining_time": "4:53:40"}
|
| 78 |
+
{"current_steps": 780, "total_steps": 3072, "loss": 0.9012, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.245940623522433e-05, "epoch": 0.76, "percentage": 25.39, "elapsed_time": "1:39:37", "remaining_time": "4:52:43"}
|
| 79 |
+
{"current_steps": 790, "total_steps": 3072, "loss": 0.9543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.227551023952104e-05, "epoch": 0.77, "percentage": 25.72, "elapsed_time": "1:40:56", "remaining_time": "4:51:36"}
|
| 80 |
+
{"current_steps": 800, "total_steps": 3072, "loss": 0.8243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.208980755057178e-05, "epoch": 0.78, "percentage": 26.04, "elapsed_time": "1:42:10", "remaining_time": "4:50:10"}
|
| 81 |
+
{"current_steps": 810, "total_steps": 3072, "loss": 0.8568, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.19023175893829e-05, "epoch": 0.79, "percentage": 26.37, "elapsed_time": "1:43:21", "remaining_time": "4:48:38"}
|
| 82 |
+
{"current_steps": 820, "total_steps": 3072, "loss": 0.9434, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.171305996387577e-05, "epoch": 0.8, "percentage": 26.69, "elapsed_time": "1:44:34", "remaining_time": "4:47:12"}
|
| 83 |
+
{"current_steps": 830, "total_steps": 3072, "loss": 0.8362, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1522054466836186e-05, "epoch": 0.81, "percentage": 27.02, "elapsed_time": "1:45:48", "remaining_time": "4:45:47"}
|
| 84 |
+
{"current_steps": 840, "total_steps": 3072, "loss": 0.8904, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1329321073844415e-05, "epoch": 0.82, "percentage": 27.34, "elapsed_time": "1:47:07", "remaining_time": "4:44:38"}
|
| 85 |
+
{"current_steps": 850, "total_steps": 3072, "loss": 0.9025, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1134879941186135e-05, "epoch": 0.83, "percentage": 27.67, "elapsed_time": "1:48:24", "remaining_time": "4:43:22"}
|
| 86 |
+
{"current_steps": 860, "total_steps": 3072, "loss": 0.872, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.093875140374443e-05, "epoch": 0.84, "percentage": 27.99, "elapsed_time": "1:49:40", "remaining_time": "4:42:04"}
|
| 87 |
+
{"current_steps": 870, "total_steps": 3072, "loss": 0.8268, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.074095597287318e-05, "epoch": 0.85, "percentage": 28.32, "elapsed_time": "1:50:58", "remaining_time": "4:40:52"}
|
| 88 |
+
{"current_steps": 880, "total_steps": 3072, "loss": 0.8755, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.054151433425194e-05, "epoch": 0.86, "percentage": 28.65, "elapsed_time": "1:52:15", "remaining_time": "4:39:36"}
|
| 89 |
+
{"current_steps": 890, "total_steps": 3072, "loss": 0.8389, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.034044734572262e-05, "epoch": 0.87, "percentage": 28.97, "elapsed_time": "1:53:30", "remaining_time": "4:38:17"}
|
| 90 |
+
{"current_steps": 900, "total_steps": 3072, "loss": 0.8528, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.013777603510814e-05, "epoch": 0.88, "percentage": 29.3, "elapsed_time": "1:54:45", "remaining_time": "4:36:57"}
|
| 91 |
+
{"current_steps": 910, "total_steps": 3072, "loss": 0.8036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.993352159801332e-05, "epoch": 0.89, "percentage": 29.62, "elapsed_time": "1:56:00", "remaining_time": "4:35:36"}
|
| 92 |
+
{"current_steps": 920, "total_steps": 3072, "loss": 0.8854, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9727705395608205e-05, "epoch": 0.9, "percentage": 29.95, "elapsed_time": "1:57:15", "remaining_time": "4:34:17"}
|
| 93 |
+
{"current_steps": 930, "total_steps": 3072, "loss": 0.8261, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9520348952394115e-05, "epoch": 0.91, "percentage": 30.27, "elapsed_time": "1:58:33", "remaining_time": "4:33:03"}
|
| 94 |
+
{"current_steps": 940, "total_steps": 3072, "loss": 0.842, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.931147395395256e-05, "epoch": 0.92, "percentage": 30.6, "elapsed_time": "1:59:53", "remaining_time": "4:31:54"}
|
| 95 |
+
{"current_steps": 950, "total_steps": 3072, "loss": 0.8749, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9101102244677335e-05, "epoch": 0.93, "percentage": 30.92, "elapsed_time": "2:01:12", "remaining_time": "4:30:45"}
|
| 96 |
+
{"current_steps": 960, "total_steps": 3072, "loss": 0.8799, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.888925582549006e-05, "epoch": 0.94, "percentage": 31.25, "elapsed_time": "2:02:33", "remaining_time": "4:29:38"}
|
| 97 |
+
{"current_steps": 970, "total_steps": 3072, "loss": 0.8573, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.867595685153922e-05, "epoch": 0.95, "percentage": 31.58, "elapsed_time": "2:03:51", "remaining_time": "4:28:23"}
|
| 98 |
+
{"current_steps": 980, "total_steps": 3072, "loss": 0.8694, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.846122762988319e-05, "epoch": 0.96, "percentage": 31.9, "elapsed_time": "2:05:08", "remaining_time": "4:27:09"}
|
| 99 |
+
{"current_steps": 990, "total_steps": 3072, "loss": 0.927, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.824509061715738e-05, "epoch": 0.97, "percentage": 32.23, "elapsed_time": "2:06:26", "remaining_time": "4:25:55"}
|
| 100 |
+
{"current_steps": 1000, "total_steps": 3072, "loss": 0.8816, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.802756841722559e-05, "epoch": 0.98, "percentage": 32.55, "elapsed_time": "2:07:41", "remaining_time": "4:24:34"}
|
| 101 |
+
{"current_steps": 1010, "total_steps": 3072, "loss": 0.9129, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.780868377881619e-05, "epoch": 0.99, "percentage": 32.88, "elapsed_time": "2:08:58", "remaining_time": "4:23:18"}
|
| 102 |
+
{"current_steps": 1020, "total_steps": 3072, "loss": 0.8362, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.758845959314294e-05, "epoch": 1.0, "percentage": 33.2, "elapsed_time": "2:10:13", "remaining_time": "4:21:59"}
|
| 103 |
+
{"current_steps": 1030, "total_steps": 3072, "loss": 0.8907, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7366918891511046e-05, "epoch": 1.01, "percentage": 33.53, "elapsed_time": "2:11:30", "remaining_time": "4:20:42"}
|
| 104 |
+
{"current_steps": 1040, "total_steps": 3072, "loss": 0.9378, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7144084842908505e-05, "epoch": 1.02, "percentage": 33.85, "elapsed_time": "2:12:45", "remaining_time": "4:19:22"}
|
| 105 |
+
{"current_steps": 1050, "total_steps": 3072, "loss": 0.9064, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.691998075158306e-05, "epoch": 1.02, "percentage": 34.18, "elapsed_time": "2:14:01", "remaining_time": "4:18:05"}
|
| 106 |
+
{"current_steps": 1060, "total_steps": 3072, "loss": 0.9101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.669463005460502e-05, "epoch": 1.03, "percentage": 34.51, "elapsed_time": "2:15:21", "remaining_time": "4:16:55"}
|
| 107 |
+
{"current_steps": 1070, "total_steps": 3072, "loss": 0.8307, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.646805631941619e-05, "epoch": 1.04, "percentage": 34.83, "elapsed_time": "2:16:41", "remaining_time": "4:15:46"}
|
| 108 |
+
{"current_steps": 1080, "total_steps": 3072, "loss": 0.8958, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.624028324136517e-05, "epoch": 1.05, "percentage": 35.16, "elapsed_time": "2:17:57", "remaining_time": "4:14:26"}
|
| 109 |
+
{"current_steps": 1090, "total_steps": 3072, "loss": 0.8681, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6011334641229215e-05, "epoch": 1.06, "percentage": 35.48, "elapsed_time": "2:19:13", "remaining_time": "4:13:09"}
|
| 110 |
+
{"current_steps": 1100, "total_steps": 3072, "loss": 0.8711, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.578123446272309e-05, "epoch": 1.07, "percentage": 35.81, "elapsed_time": "2:20:30", "remaining_time": "4:11:53"}
|
| 111 |
+
{"current_steps": 1110, "total_steps": 3072, "loss": 0.8607, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5550006769994996e-05, "epoch": 1.08, "percentage": 36.13, "elapsed_time": "2:21:43", "remaining_time": "4:10:29"}
|
| 112 |
+
{"current_steps": 1120, "total_steps": 3072, "loss": 0.9532, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5317675745109866e-05, "epoch": 1.09, "percentage": 36.46, "elapsed_time": "2:22:58", "remaining_time": "4:09:11"}
|
| 113 |
+
{"current_steps": 1130, "total_steps": 3072, "loss": 0.848, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.508426568552045e-05, "epoch": 1.1, "percentage": 36.78, "elapsed_time": "2:24:15", "remaining_time": "4:07:54"}
|
| 114 |
+
{"current_steps": 1140, "total_steps": 3072, "loss": 0.8097, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.484980100152621e-05, "epoch": 1.11, "percentage": 37.11, "elapsed_time": "2:25:32", "remaining_time": "4:06:39"}
|
| 115 |
+
{"current_steps": 1150, "total_steps": 3072, "loss": 0.8612, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.461430621372044e-05, "epoch": 1.12, "percentage": 37.43, "elapsed_time": "2:26:42", "remaining_time": "4:05:11"}
|
| 116 |
+
{"current_steps": 1160, "total_steps": 3072, "loss": 0.8281, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.437780595042595e-05, "epoch": 1.13, "percentage": 37.76, "elapsed_time": "2:27:58", "remaining_time": "4:03:54"}
|
| 117 |
+
{"current_steps": 1170, "total_steps": 3072, "loss": 0.8297, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.414032494511935e-05, "epoch": 1.14, "percentage": 38.09, "elapsed_time": "2:29:14", "remaining_time": "4:02:36"}
|
| 118 |
+
{"current_steps": 1180, "total_steps": 3072, "loss": 0.8607, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.390188803384439e-05, "epoch": 1.15, "percentage": 38.41, "elapsed_time": "2:30:29", "remaining_time": "4:01:17"}
|
| 119 |
+
{"current_steps": 1190, "total_steps": 3072, "loss": 0.8986, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3662520152614615e-05, "epoch": 1.16, "percentage": 38.74, "elapsed_time": "2:31:39", "remaining_time": "3:59:50"}
|
| 120 |
+
{"current_steps": 1200, "total_steps": 3072, "loss": 0.8884, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.34222463348055e-05, "epoch": 1.17, "percentage": 39.06, "elapsed_time": "2:32:49", "remaining_time": "3:58:25"}
|
| 121 |
+
{"current_steps": 1210, "total_steps": 3072, "loss": 0.8901, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3181091708536435e-05, "epoch": 1.18, "percentage": 39.39, "elapsed_time": "2:34:05", "remaining_time": "3:57:06"}
|
| 122 |
+
{"current_steps": 1220, "total_steps": 3072, "loss": 0.8583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.293908149404279e-05, "epoch": 1.19, "percentage": 39.71, "elapsed_time": "2:35:23", "remaining_time": "3:55:53"}
|
| 123 |
+
{"current_steps": 1230, "total_steps": 3072, "loss": 0.7928, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2696241001038374e-05, "epoch": 1.2, "percentage": 40.04, "elapsed_time": "2:36:40", "remaining_time": "3:54:37"}
|
| 124 |
+
{"current_steps": 1240, "total_steps": 3072, "loss": 0.8508, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.245259562606851e-05, "epoch": 1.21, "percentage": 40.36, "elapsed_time": "2:37:58", "remaining_time": "3:53:23"}
|
| 125 |
+
{"current_steps": 1250, "total_steps": 3072, "loss": 0.8245, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.220817084985398e-05, "epoch": 1.22, "percentage": 40.69, "elapsed_time": "2:39:13", "remaining_time": "3:52:05"}
|
| 126 |
+
{"current_steps": 1260, "total_steps": 3072, "loss": 0.8746, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.196299223462633e-05, "epoch": 1.23, "percentage": 41.02, "elapsed_time": "2:40:34", "remaining_time": "3:50:55"}
|
| 127 |
+
{"current_steps": 1270, "total_steps": 3072, "loss": 0.8666, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.171708542145445e-05, "epoch": 1.24, "percentage": 41.34, "elapsed_time": "2:41:52", "remaining_time": "3:49:41"}
|
| 128 |
+
{"current_steps": 1280, "total_steps": 3072, "loss": 0.8807, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.147047612756302e-05, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "2:43:09", "remaining_time": "3:48:25"}
|
| 129 |
+
{"current_steps": 1290, "total_steps": 3072, "loss": 0.8557, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1223190143643014e-05, "epoch": 1.26, "percentage": 41.99, "elapsed_time": "2:44:26", "remaining_time": "3:47:09"}
|
| 130 |
+
{"current_steps": 1300, "total_steps": 3072, "loss": 0.842, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.09752533311544e-05, "epoch": 1.27, "percentage": 42.32, "elapsed_time": "2:45:45", "remaining_time": "3:45:56"}
|
| 131 |
+
{"current_steps": 1310, "total_steps": 3072, "loss": 0.8701, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0726691619621617e-05, "epoch": 1.28, "percentage": 42.64, "elapsed_time": "2:47:03", "remaining_time": "3:44:42"}
|
| 132 |
+
{"current_steps": 1320, "total_steps": 3072, "loss": 0.8755, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0477531003921745e-05, "epoch": 1.29, "percentage": 42.97, "elapsed_time": "2:48:23", "remaining_time": "3:43:30"}
|
| 133 |
+
{"current_steps": 1330, "total_steps": 3072, "loss": 0.9009, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0227797541566e-05, "epoch": 1.3, "percentage": 43.29, "elapsed_time": "2:49:39", "remaining_time": "3:42:12"}
|
| 134 |
+
{"current_steps": 1340, "total_steps": 3072, "loss": 0.8578, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9977517349974544e-05, "epoch": 1.31, "percentage": 43.62, "elapsed_time": "2:50:53", "remaining_time": "3:40:52"}
|
| 135 |
+
{"current_steps": 1350, "total_steps": 3072, "loss": 0.8067, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9726716603745157e-05, "epoch": 1.32, "percentage": 43.95, "elapsed_time": "2:52:10", "remaining_time": "3:39:36"}
|
| 136 |
+
{"current_steps": 1360, "total_steps": 3072, "loss": 0.8139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9475421531915827e-05, "epoch": 1.33, "percentage": 44.27, "elapsed_time": "2:53:25", "remaining_time": "3:38:18"}
|
| 137 |
+
{"current_steps": 1370, "total_steps": 3072, "loss": 0.8382, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.922365841522167e-05, "epoch": 1.34, "percentage": 44.6, "elapsed_time": "2:54:44", "remaining_time": "3:37:04"}
|
| 138 |
+
{"current_steps": 1380, "total_steps": 3072, "loss": 0.9073, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8971453583346536e-05, "epoch": 1.35, "percentage": 44.92, "elapsed_time": "2:55:56", "remaining_time": "3:35:43"}
|
| 139 |
+
{"current_steps": 1390, "total_steps": 3072, "loss": 0.8783, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.871883341216934e-05, "epoch": 1.36, "percentage": 45.25, "elapsed_time": "2:57:14", "remaining_time": "3:34:28"}
|
| 140 |
+
{"current_steps": 1400, "total_steps": 3072, "loss": 0.8555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.846582432100567e-05, "epoch": 1.37, "percentage": 45.57, "elapsed_time": "2:58:27", "remaining_time": "3:33:07"}
|
| 141 |
+
{"current_steps": 1410, "total_steps": 3072, "loss": 0.8236, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8212452769844834e-05, "epoch": 1.38, "percentage": 45.9, "elapsed_time": "2:59:37", "remaining_time": "3:31:43"}
|
| 142 |
+
{"current_steps": 1420, "total_steps": 3072, "loss": 0.8816, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.795874525658263e-05, "epoch": 1.39, "percentage": 46.22, "elapsed_time": "3:00:57", "remaining_time": "3:30:31"}
|
| 143 |
+
{"current_steps": 1430, "total_steps": 3072, "loss": 0.8199, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7704728314250168e-05, "epoch": 1.4, "percentage": 46.55, "elapsed_time": "3:02:11", "remaining_time": "3:29:11"}
|
| 144 |
+
{"current_steps": 1440, "total_steps": 3072, "loss": 0.8271, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7450428508239024e-05, "epoch": 1.41, "percentage": 46.88, "elapsed_time": "3:03:22", "remaining_time": "3:27:50"}
|
| 145 |
+
{"current_steps": 1450, "total_steps": 3072, "loss": 0.8444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7195872433522974e-05, "epoch": 1.42, "percentage": 47.2, "elapsed_time": "3:04:37", "remaining_time": "3:26:31"}
|
| 146 |
+
{"current_steps": 1460, "total_steps": 3072, "loss": 0.8232, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.694108671187669e-05, "epoch": 1.43, "percentage": 47.53, "elapsed_time": "3:05:53", "remaining_time": "3:25:15"}
|
| 147 |
+
{"current_steps": 1470, "total_steps": 3072, "loss": 0.7959, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.66860979890916e-05, "epoch": 1.43, "percentage": 47.85, "elapsed_time": "3:07:11", "remaining_time": "3:23:59"}
|
| 148 |
+
{"current_steps": 1480, "total_steps": 3072, "loss": 0.8368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6430932932189224e-05, "epoch": 1.44, "percentage": 48.18, "elapsed_time": "3:08:26", "remaining_time": "3:22:41"}
|
| 149 |
+
{"current_steps": 1490, "total_steps": 3072, "loss": 0.8336, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.617561822663228e-05, "epoch": 1.45, "percentage": 48.5, "elapsed_time": "3:09:41", "remaining_time": "3:21:24"}
|
| 150 |
+
{"current_steps": 1500, "total_steps": 3072, "loss": 0.8431, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5920180573533976e-05, "epoch": 1.46, "percentage": 48.83, "elapsed_time": "3:10:58", "remaining_time": "3:20:08"}
|
| 151 |
+
{"current_steps": 1510, "total_steps": 3072, "loss": 0.8309, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.566464668686547e-05, "epoch": 1.47, "percentage": 49.15, "elapsed_time": "3:12:19", "remaining_time": "3:18:57"}
|
| 152 |
+
{"current_steps": 1520, "total_steps": 3072, "loss": 0.9332, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5409043290662173e-05, "epoch": 1.48, "percentage": 49.48, "elapsed_time": "3:13:36", "remaining_time": "3:17:41"}
|
| 153 |
+
{"current_steps": 1530, "total_steps": 3072, "loss": 0.8416, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5153397116228865e-05, "epoch": 1.49, "percentage": 49.8, "elapsed_time": "3:14:54", "remaining_time": "3:16:26"}
|
| 154 |
+
{"current_steps": 1540, "total_steps": 3072, "loss": 0.8978, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.489773489934413e-05, "epoch": 1.5, "percentage": 50.13, "elapsed_time": "3:16:11", "remaining_time": "3:15:10"}
|
| 155 |
+
{"current_steps": 1550, "total_steps": 3072, "loss": 0.8724, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4642083377464305e-05, "epoch": 1.51, "percentage": 50.46, "elapsed_time": "3:17:27", "remaining_time": "3:13:53"}
|
| 156 |
+
{"current_steps": 1560, "total_steps": 3072, "loss": 0.9087, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4386469286927196e-05, "epoch": 1.52, "percentage": 50.78, "elapsed_time": "3:18:45", "remaining_time": "3:12:38"}
|
| 157 |
+
{"current_steps": 1570, "total_steps": 3072, "loss": 0.8749, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.413091936015603e-05, "epoch": 1.53, "percentage": 51.11, "elapsed_time": "3:20:06", "remaining_time": "3:11:26"}
|
| 158 |
+
{"current_steps": 1580, "total_steps": 3072, "loss": 0.8781, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3875460322863697e-05, "epoch": 1.54, "percentage": 51.43, "elapsed_time": "3:21:20", "remaining_time": "3:10:07"}
|
| 159 |
+
{"current_steps": 1590, "total_steps": 3072, "loss": 0.8544, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3620118891257754e-05, "epoch": 1.55, "percentage": 51.76, "elapsed_time": "3:22:37", "remaining_time": "3:08:52"}
|
| 160 |
+
{"current_steps": 1600, "total_steps": 3072, "loss": 0.8244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3364921769246423e-05, "epoch": 1.56, "percentage": 52.08, "elapsed_time": "3:23:53", "remaining_time": "3:07:35"}
|
| 161 |
+
{"current_steps": 1610, "total_steps": 3072, "loss": 0.8656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3109895645645867e-05, "epoch": 1.57, "percentage": 52.41, "elapsed_time": "3:25:08", "remaining_time": "3:06:16"}
|
| 162 |
+
{"current_steps": 1620, "total_steps": 3072, "loss": 0.888, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2855067191389006e-05, "epoch": 1.58, "percentage": 52.73, "elapsed_time": "3:26:20", "remaining_time": "3:04:56"}
|
| 163 |
+
{"current_steps": 1630, "total_steps": 3072, "loss": 0.8219, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2600463056736293e-05, "epoch": 1.59, "percentage": 53.06, "elapsed_time": "3:27:37", "remaining_time": "3:03:40"}
|
| 164 |
+
{"current_steps": 1640, "total_steps": 3072, "loss": 0.8732, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2346109868488567e-05, "epoch": 1.6, "percentage": 53.39, "elapsed_time": "3:28:54", "remaining_time": "3:02:24"}
|
| 165 |
+
{"current_steps": 1650, "total_steps": 3072, "loss": 0.8984, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2092034227202383e-05, "epoch": 1.61, "percentage": 53.71, "elapsed_time": "3:30:12", "remaining_time": "3:01:09"}
|
| 166 |
+
{"current_steps": 1660, "total_steps": 3072, "loss": 0.8474, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.183826270440812e-05, "epoch": 1.62, "percentage": 54.04, "elapsed_time": "3:31:32", "remaining_time": "2:59:56"}
|
| 167 |
+
{"current_steps": 1670, "total_steps": 3072, "loss": 0.8423, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.158482183983109e-05, "epoch": 1.63, "percentage": 54.36, "elapsed_time": "3:32:52", "remaining_time": "2:58:42"}
|
| 168 |
+
{"current_steps": 1680, "total_steps": 3072, "loss": 0.8716, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1331738138615958e-05, "epoch": 1.64, "percentage": 54.69, "elapsed_time": "3:34:05", "remaining_time": "2:57:23"}
|
| 169 |
+
{"current_steps": 1690, "total_steps": 3072, "loss": 0.8783, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1079038068554842e-05, "epoch": 1.65, "percentage": 55.01, "elapsed_time": "3:35:25", "remaining_time": "2:56:09"}
|
| 170 |
+
{"current_steps": 1700, "total_steps": 3072, "loss": 0.7759, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.082674805731926e-05, "epoch": 1.66, "percentage": 55.34, "elapsed_time": "3:36:42", "remaining_time": "2:54:53"}
|
| 171 |
+
{"current_steps": 1710, "total_steps": 3072, "loss": 0.8975, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0574894489696285e-05, "epoch": 1.67, "percentage": 55.66, "elapsed_time": "3:37:59", "remaining_time": "2:53:37"}
|
| 172 |
+
{"current_steps": 1720, "total_steps": 3072, "loss": 0.8425, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.03235037048292e-05, "epoch": 1.68, "percentage": 55.99, "elapsed_time": "3:39:15", "remaining_time": "2:52:20"}
|
| 173 |
+
{"current_steps": 1730, "total_steps": 3072, "loss": 0.824, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0072601993462946e-05, "epoch": 1.69, "percentage": 56.32, "elapsed_time": "3:40:33", "remaining_time": "2:51:05"}
|
| 174 |
+
{"current_steps": 1740, "total_steps": 3072, "loss": 0.7989, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.982221559519454e-05, "epoch": 1.7, "percentage": 56.64, "elapsed_time": "3:41:48", "remaining_time": "2:49:47"}
|
| 175 |
+
{"current_steps": 1750, "total_steps": 3072, "loss": 0.8145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.957237069572898e-05, "epoch": 1.71, "percentage": 56.97, "elapsed_time": "3:43:04", "remaining_time": "2:48:31"}
|
| 176 |
+
{"current_steps": 1760, "total_steps": 3072, "loss": 0.8581, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.932309342414067e-05, "epoch": 1.72, "percentage": 57.29, "elapsed_time": "3:44:23", "remaining_time": "2:47:16"}
|
| 177 |
+
{"current_steps": 1770, "total_steps": 3072, "loss": 0.8886, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.907440985014082e-05, "epoch": 1.73, "percentage": 57.62, "elapsed_time": "3:45:38", "remaining_time": "2:45:58"}
|
| 178 |
+
{"current_steps": 1780, "total_steps": 3072, "loss": 0.8048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8826345981351044e-05, "epoch": 1.74, "percentage": 57.94, "elapsed_time": "3:46:56", "remaining_time": "2:44:43"}
|
| 179 |
+
{"current_steps": 1790, "total_steps": 3072, "loss": 0.8534, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8578927760583463e-05, "epoch": 1.75, "percentage": 58.27, "elapsed_time": "3:48:09", "remaining_time": "2:43:24"}
|
| 180 |
+
{"current_steps": 1800, "total_steps": 3072, "loss": 0.8392, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8332181063127545e-05, "epoch": 1.76, "percentage": 58.59, "elapsed_time": "3:49:22", "remaining_time": "2:42:05"}
|
| 181 |
+
{"current_steps": 1810, "total_steps": 3072, "loss": 0.8926, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8086131694044077e-05, "epoch": 1.77, "percentage": 58.92, "elapsed_time": "3:50:38", "remaining_time": "2:40:48"}
|
| 182 |
+
{"current_steps": 1820, "total_steps": 3072, "loss": 0.923, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.784080538546642e-05, "epoch": 1.78, "percentage": 59.24, "elapsed_time": "3:51:50", "remaining_time": "2:39:29"}
|
| 183 |
+
{"current_steps": 1830, "total_steps": 3072, "loss": 0.8209, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7596227793909402e-05, "epoch": 1.79, "percentage": 59.57, "elapsed_time": "3:53:05", "remaining_time": "2:38:11"}
|
| 184 |
+
{"current_steps": 1840, "total_steps": 3072, "loss": 0.813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7352424497586163e-05, "epoch": 1.8, "percentage": 59.9, "elapsed_time": "3:54:19", "remaining_time": "2:36:54"}
|
| 185 |
+
{"current_steps": 1850, "total_steps": 3072, "loss": 0.8375, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7109420993733115e-05, "epoch": 1.81, "percentage": 60.22, "elapsed_time": "3:55:34", "remaining_time": "2:35:36"}
|
| 186 |
+
{"current_steps": 1860, "total_steps": 3072, "loss": 0.8477, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.686724269594343e-05, "epoch": 1.82, "percentage": 60.55, "elapsed_time": "3:56:49", "remaining_time": "2:34:19"}
|
| 187 |
+
{"current_steps": 1870, "total_steps": 3072, "loss": 0.8263, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6625914931509262e-05, "epoch": 1.83, "percentage": 60.87, "elapsed_time": "3:58:04", "remaining_time": "2:33:01"}
|
| 188 |
+
{"current_steps": 1880, "total_steps": 3072, "loss": 0.8816, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6385462938772992e-05, "epoch": 1.84, "percentage": 61.2, "elapsed_time": "3:59:19", "remaining_time": "2:31:44"}
|
| 189 |
+
{"current_steps": 1890, "total_steps": 3072, "loss": 0.8677, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.614591186448774e-05, "epoch": 1.84, "percentage": 61.52, "elapsed_time": "4:00:36", "remaining_time": "2:30:28"}
|
| 190 |
+
{"current_steps": 1900, "total_steps": 3072, "loss": 0.9021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5907286761187535e-05, "epoch": 1.85, "percentage": 61.85, "elapsed_time": "4:01:45", "remaining_time": "2:29:07"}
|
| 191 |
+
{"current_steps": 1910, "total_steps": 3072, "loss": 0.8449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5669612584567265e-05, "epoch": 1.86, "percentage": 62.17, "elapsed_time": "4:03:00", "remaining_time": "2:27:50"}
|
| 192 |
+
{"current_steps": 1920, "total_steps": 3072, "loss": 0.8328, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5432914190872757e-05, "epoch": 1.87, "percentage": 62.5, "elapsed_time": "4:04:17", "remaining_time": "2:26:34"}
|
| 193 |
+
{"current_steps": 1930, "total_steps": 3072, "loss": 0.8591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5197216334301339e-05, "epoch": 1.88, "percentage": 62.83, "elapsed_time": "4:05:31", "remaining_time": "2:25:16"}
|
| 194 |
+
{"current_steps": 1940, "total_steps": 3072, "loss": 0.9411, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4962543664412986e-05, "epoch": 1.89, "percentage": 63.15, "elapsed_time": "4:06:42", "remaining_time": "2:23:57"}
|
| 195 |
+
{"current_steps": 1950, "total_steps": 3072, "loss": 0.9106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4728920723552407e-05, "epoch": 1.9, "percentage": 63.48, "elapsed_time": "4:07:55", "remaining_time": "2:22:39"}
|
| 196 |
+
{"current_steps": 1960, "total_steps": 3072, "loss": 0.8332, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4496371944282441e-05, "epoch": 1.91, "percentage": 63.8, "elapsed_time": "4:09:10", "remaining_time": "2:21:22"}
|
| 197 |
+
{"current_steps": 1970, "total_steps": 3072, "loss": 0.783, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4264921646828838e-05, "epoch": 1.92, "percentage": 64.13, "elapsed_time": "4:10:27", "remaining_time": "2:20:06"}
|
| 198 |
+
{"current_steps": 1980, "total_steps": 3072, "loss": 0.8703, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4034594036536817e-05, "epoch": 1.93, "percentage": 64.45, "elapsed_time": "4:11:44", "remaining_time": "2:18:50"}
|
| 199 |
+
{"current_steps": 1990, "total_steps": 3072, "loss": 0.8918, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3805413201339632e-05, "epoch": 1.94, "percentage": 64.78, "elapsed_time": "4:13:02", "remaining_time": "2:17:35"}
|
| 200 |
+
{"current_steps": 2000, "total_steps": 3072, "loss": 0.8795, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3577403109239484e-05, "epoch": 1.95, "percentage": 65.1, "elapsed_time": "4:14:20", "remaining_time": "2:16:19"}
|
| 201 |
+
{"current_steps": 2010, "total_steps": 3072, "loss": 0.8222, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3350587605800852e-05, "epoch": 1.96, "percentage": 65.43, "elapsed_time": "4:15:27", "remaining_time": "2:14:58"}
|
| 202 |
+
{"current_steps": 2020, "total_steps": 3072, "loss": 0.8187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3124990411656706e-05, "epoch": 1.97, "percentage": 65.76, "elapsed_time": "4:16:44", "remaining_time": "2:13:42"}
|
| 203 |
+
{"current_steps": 2030, "total_steps": 3072, "loss": 0.8343, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2900635120027859e-05, "epoch": 1.98, "percentage": 66.08, "elapsed_time": "4:18:01", "remaining_time": "2:12:26"}
|
| 204 |
+
{"current_steps": 2040, "total_steps": 3072, "loss": 0.9145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2677545194255402e-05, "epoch": 1.99, "percentage": 66.41, "elapsed_time": "4:19:18", "remaining_time": "2:11:10"}
|
| 205 |
+
{"current_steps": 2050, "total_steps": 3072, "loss": 0.913, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2455743965347047e-05, "epoch": 2.0, "percentage": 66.73, "elapsed_time": "4:20:35", "remaining_time": "2:09:54"}
|
| 206 |
+
{"current_steps": 2060, "total_steps": 3072, "loss": 0.9304, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.223525462953703e-05, "epoch": 2.01, "percentage": 67.06, "elapsed_time": "4:21:50", "remaining_time": "2:08:37"}
|
| 207 |
+
{"current_steps": 2070, "total_steps": 3072, "loss": 0.82, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.201610024586026e-05, "epoch": 2.02, "percentage": 67.38, "elapsed_time": "4:23:08", "remaining_time": "2:07:22"}
|
| 208 |
+
{"current_steps": 2080, "total_steps": 3072, "loss": 0.8232, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1798303733740802e-05, "epoch": 2.03, "percentage": 67.71, "elapsed_time": "4:24:24", "remaining_time": "2:06:06"}
|
| 209 |
+
{"current_steps": 2090, "total_steps": 3072, "loss": 0.8997, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1581887870594884e-05, "epoch": 2.04, "percentage": 68.03, "elapsed_time": "4:25:39", "remaining_time": "2:04:49"}
|
| 210 |
+
{"current_steps": 2100, "total_steps": 3072, "loss": 0.9386, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1366875289448845e-05, "epoch": 2.05, "percentage": 68.36, "elapsed_time": "4:26:54", "remaining_time": "2:03:32"}
|
| 211 |
+
{"current_steps": 2110, "total_steps": 3072, "loss": 0.8515, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1153288476572126e-05, "epoch": 2.06, "percentage": 68.68, "elapsed_time": "4:28:09", "remaining_time": "2:02:15"}
|
| 212 |
+
{"current_steps": 2120, "total_steps": 3072, "loss": 0.8724, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0941149769125674e-05, "epoch": 2.07, "percentage": 69.01, "elapsed_time": "4:29:24", "remaining_time": "2:00:58"}
|
| 213 |
+
{"current_steps": 2130, "total_steps": 3072, "loss": 0.8616, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0730481352825823e-05, "epoch": 2.08, "percentage": 69.34, "elapsed_time": "4:30:34", "remaining_time": "1:59:39"}
|
| 214 |
+
{"current_steps": 2140, "total_steps": 3072, "loss": 0.82, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0521305259624129e-05, "epoch": 2.09, "percentage": 69.66, "elapsed_time": "4:31:47", "remaining_time": "1:58:22"}
|
| 215 |
+
{"current_steps": 2150, "total_steps": 3072, "loss": 0.866, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0313643365403274e-05, "epoch": 2.1, "percentage": 69.99, "elapsed_time": "4:33:02", "remaining_time": "1:57:05"}
|
| 216 |
+
{"current_steps": 2160, "total_steps": 3072, "loss": 0.7712, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0107517387689166e-05, "epoch": 2.11, "percentage": 70.31, "elapsed_time": "4:34:20", "remaining_time": "1:55:49"}
|
| 217 |
+
{"current_steps": 2170, "total_steps": 3072, "loss": 0.8451, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.90294888337981e-06, "epoch": 2.12, "percentage": 70.64, "elapsed_time": "4:35:39", "remaining_time": "1:54:35"}
|
| 218 |
+
{"current_steps": 2180, "total_steps": 3072, "loss": 0.7923, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.699959246490762e-06, "epoch": 2.13, "percentage": 70.96, "elapsed_time": "4:36:58", "remaining_time": "1:53:19"}
|
| 219 |
+
{"current_steps": 2190, "total_steps": 3072, "loss": 0.8547, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.498569705917771e-06, "epoch": 2.14, "percentage": 71.29, "elapsed_time": "4:38:18", "remaining_time": "1:52:04"}
|
| 220 |
+
{"current_steps": 2200, "total_steps": 3072, "loss": 0.8624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.298801323216647e-06, "epoch": 2.15, "percentage": 71.61, "elapsed_time": "4:39:34", "remaining_time": "1:50:48"}
|
| 221 |
+
{"current_steps": 2210, "total_steps": 3072, "loss": 0.8079, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.100674990400571e-06, "epoch": 2.16, "percentage": 71.94, "elapsed_time": "4:40:49", "remaining_time": "1:49:32"}
|
| 222 |
+
{"current_steps": 2220, "total_steps": 3072, "loss": 0.8211, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.904211427755218e-06, "epoch": 2.17, "percentage": 72.27, "elapsed_time": "4:42:06", "remaining_time": "1:48:16"}
|
| 223 |
+
{"current_steps": 2230, "total_steps": 3072, "loss": 0.9058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.70943118167179e-06, "epoch": 2.18, "percentage": 72.59, "elapsed_time": "4:43:24", "remaining_time": "1:47:00"}
|
| 224 |
+
{"current_steps": 2240, "total_steps": 3072, "loss": 0.7715, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.51635462249828e-06, "epoch": 2.19, "percentage": 72.92, "elapsed_time": "4:44:40", "remaining_time": "1:45:44"}
|
| 225 |
+
{"current_steps": 2250, "total_steps": 3072, "loss": 0.8093, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.325001942409066e-06, "epoch": 2.2, "percentage": 73.24, "elapsed_time": "4:45:58", "remaining_time": "1:44:28"}
|
| 226 |
+
{"current_steps": 2260, "total_steps": 3072, "loss": 0.8812, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.13539315329322e-06, "epoch": 2.21, "percentage": 73.57, "elapsed_time": "4:47:12", "remaining_time": "1:43:11"}
|
| 227 |
+
{"current_steps": 2270, "total_steps": 3072, "loss": 0.8675, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.947548084661674e-06, "epoch": 2.22, "percentage": 73.89, "elapsed_time": "4:48:31", "remaining_time": "1:41:56"}
|
| 228 |
+
{"current_steps": 2280, "total_steps": 3072, "loss": 0.7757, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.761486381573327e-06, "epoch": 2.23, "percentage": 74.22, "elapsed_time": "4:49:46", "remaining_time": "1:40:39"}
|
| 229 |
+
{"current_steps": 2290, "total_steps": 3072, "loss": 0.9026, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.577227502580667e-06, "epoch": 2.24, "percentage": 74.54, "elapsed_time": "4:51:01", "remaining_time": "1:39:22"}
|
| 230 |
+
{"current_steps": 2300, "total_steps": 3072, "loss": 0.8779, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.394790717694677e-06, "epoch": 2.24, "percentage": 74.87, "elapsed_time": "4:52:15", "remaining_time": "1:38:05"}
|
| 231 |
+
{"current_steps": 2310, "total_steps": 3072, "loss": 0.8702, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.214195106369587e-06, "epoch": 2.25, "percentage": 75.2, "elapsed_time": "4:53:28", "remaining_time": "1:36:48"}
|
| 232 |
+
{"current_steps": 2320, "total_steps": 3072, "loss": 0.8602, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.035459555507548e-06, "epoch": 2.26, "percentage": 75.52, "elapsed_time": "4:54:44", "remaining_time": "1:35:32"}
|
| 233 |
+
{"current_steps": 2330, "total_steps": 3072, "loss": 0.8647, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.858602757483371e-06, "epoch": 2.27, "percentage": 75.85, "elapsed_time": "4:56:00", "remaining_time": "1:34:15"}
|
| 234 |
+
{"current_steps": 2340, "total_steps": 3072, "loss": 0.8216, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.683643208189683e-06, "epoch": 2.28, "percentage": 76.17, "elapsed_time": "4:57:15", "remaining_time": "1:32:59"}
|
| 235 |
+
{"current_steps": 2350, "total_steps": 3072, "loss": 0.8674, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.510599205102594e-06, "epoch": 2.29, "percentage": 76.5, "elapsed_time": "4:58:29", "remaining_time": "1:31:42"}
|
| 236 |
+
{"current_steps": 2360, "total_steps": 3072, "loss": 0.8232, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.339488845368155e-06, "epoch": 2.3, "percentage": 76.82, "elapsed_time": "4:59:48", "remaining_time": "1:30:27"}
|
| 237 |
+
{"current_steps": 2370, "total_steps": 3072, "loss": 0.8058, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.17033002390969e-06, "epoch": 2.31, "percentage": 77.15, "elapsed_time": "5:01:05", "remaining_time": "1:29:11"}
|
| 238 |
+
{"current_steps": 2380, "total_steps": 3072, "loss": 0.8183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.003140431556345e-06, "epoch": 2.32, "percentage": 77.47, "elapsed_time": "5:02:21", "remaining_time": "1:27:54"}
|
| 239 |
+
{"current_steps": 2390, "total_steps": 3072, "loss": 0.8745, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.837937553192999e-06, "epoch": 2.33, "percentage": 77.8, "elapsed_time": "5:03:39", "remaining_time": "1:26:38"}
|
| 240 |
+
{"current_steps": 2400, "total_steps": 3072, "loss": 0.7398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.674738665931575e-06, "epoch": 2.34, "percentage": 78.12, "elapsed_time": "5:04:59", "remaining_time": "1:25:23"}
|
| 241 |
+
{"current_steps": 2410, "total_steps": 3072, "loss": 0.8321, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.513560837304304e-06, "epoch": 2.35, "percentage": 78.45, "elapsed_time": "5:06:15", "remaining_time": "1:24:07"}
|
| 242 |
+
{"current_steps": 2420, "total_steps": 3072, "loss": 0.8657, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.354420923478687e-06, "epoch": 2.36, "percentage": 78.78, "elapsed_time": "5:07:33", "remaining_time": "1:22:51"}
|
| 243 |
+
{"current_steps": 2430, "total_steps": 3072, "loss": 0.8899, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.197335567494696e-06, "epoch": 2.37, "percentage": 79.1, "elapsed_time": "5:08:44", "remaining_time": "1:21:34"}
|
| 244 |
+
{"current_steps": 2440, "total_steps": 3072, "loss": 0.8185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.042321197524213e-06, "epoch": 2.38, "percentage": 79.43, "elapsed_time": "5:10:02", "remaining_time": "1:20:18"}
|
| 245 |
+
{"current_steps": 2450, "total_steps": 3072, "loss": 0.9032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.889394025152979e-06, "epoch": 2.39, "percentage": 79.75, "elapsed_time": "5:11:16", "remaining_time": "1:19:01"}
|
| 246 |
+
{"current_steps": 2460, "total_steps": 3072, "loss": 0.8692, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.738570043685134e-06, "epoch": 2.4, "percentage": 80.08, "elapsed_time": "5:12:28", "remaining_time": "1:17:44"}
|
| 247 |
+
{"current_steps": 2470, "total_steps": 3072, "loss": 0.8571, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.589865026470619e-06, "epoch": 2.41, "percentage": 80.4, "elapsed_time": "5:13:49", "remaining_time": "1:16:29"}
|
| 248 |
+
{"current_steps": 2480, "total_steps": 3072, "loss": 0.8563, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4432945252556284e-06, "epoch": 2.42, "percentage": 80.73, "elapsed_time": "5:15:08", "remaining_time": "1:15:13"}
|
| 249 |
+
{"current_steps": 2490, "total_steps": 3072, "loss": 0.8423, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.298873868556108e-06, "epoch": 2.43, "percentage": 81.05, "elapsed_time": "5:16:27", "remaining_time": "1:13:57"}
|
| 250 |
+
{"current_steps": 2500, "total_steps": 3072, "loss": 0.8008, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.156618160054771e-06, "epoch": 2.44, "percentage": 81.38, "elapsed_time": "5:17:43", "remaining_time": "1:12:41"}
|
| 251 |
+
{"current_steps": 2510, "total_steps": 3072, "loss": 0.9192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.016542277021465e-06, "epoch": 2.45, "percentage": 81.71, "elapsed_time": "5:18:58", "remaining_time": "1:11:25"}
|
| 252 |
+
{"current_steps": 2520, "total_steps": 3072, "loss": 0.9414, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.878660868757323e-06, "epoch": 2.46, "percentage": 82.03, "elapsed_time": "5:20:11", "remaining_time": "1:10:08"}
|
| 253 |
+
{"current_steps": 2530, "total_steps": 3072, "loss": 0.8645, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.742988355062735e-06, "epoch": 2.47, "percentage": 82.36, "elapsed_time": "5:21:27", "remaining_time": "1:08:51"}
|
| 254 |
+
{"current_steps": 2540, "total_steps": 3072, "loss": 0.7851, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.609538924729269e-06, "epoch": 2.48, "percentage": 82.68, "elapsed_time": "5:22:44", "remaining_time": "1:07:35"}
|
| 255 |
+
{"current_steps": 2550, "total_steps": 3072, "loss": 0.8207, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.478326534055823e-06, "epoch": 2.49, "percentage": 83.01, "elapsed_time": "5:24:00", "remaining_time": "1:06:19"}
|
| 256 |
+
{"current_steps": 2560, "total_steps": 3072, "loss": 0.8443, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3493649053890326e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "5:25:15", "remaining_time": "1:05:03"}
|
| 257 |
+
{"current_steps": 2570, "total_steps": 3072, "loss": 0.841, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2226675256882167e-06, "epoch": 2.51, "percentage": 83.66, "elapsed_time": "5:26:32", "remaining_time": "1:03:47"}
|
| 258 |
+
{"current_steps": 2580, "total_steps": 3072, "loss": 0.8591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.098247645114838e-06, "epoch": 2.52, "percentage": 83.98, "elapsed_time": "5:27:50", "remaining_time": "1:02:31"}
|
| 259 |
+
{"current_steps": 2590, "total_steps": 3072, "loss": 0.8146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9761182756468165e-06, "epoch": 2.53, "percentage": 84.31, "elapsed_time": "5:29:07", "remaining_time": "1:01:15"}
|
| 260 |
+
{"current_steps": 2600, "total_steps": 3072, "loss": 0.8441, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.856292189717741e-06, "epoch": 2.54, "percentage": 84.64, "elapsed_time": "5:30:26", "remaining_time": "0:59:59"}
|
| 261 |
+
{"current_steps": 2610, "total_steps": 3072, "loss": 0.878, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7387819188810534e-06, "epoch": 2.55, "percentage": 84.96, "elapsed_time": "5:31:38", "remaining_time": "0:58:42"}
|
| 262 |
+
{"current_steps": 2620, "total_steps": 3072, "loss": 0.8543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.623599752499553e-06, "epoch": 2.56, "percentage": 85.29, "elapsed_time": "5:32:53", "remaining_time": "0:57:25"}
|
| 263 |
+
{"current_steps": 2630, "total_steps": 3072, "loss": 0.8435, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.510757736460112e-06, "epoch": 2.57, "percentage": 85.61, "elapsed_time": "5:34:09", "remaining_time": "0:56:09"}
|
| 264 |
+
{"current_steps": 2640, "total_steps": 3072, "loss": 0.8424, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4002676719139166e-06, "epoch": 2.58, "percentage": 85.94, "elapsed_time": "5:35:23", "remaining_time": "0:54:52"}
|
| 265 |
+
{"current_steps": 2650, "total_steps": 3072, "loss": 0.8488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2921411140423037e-06, "epoch": 2.59, "percentage": 86.26, "elapsed_time": "5:36:40", "remaining_time": "0:53:36"}
|
| 266 |
+
{"current_steps": 2660, "total_steps": 3072, "loss": 0.8021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1863893708482795e-06, "epoch": 2.6, "percentage": 86.59, "elapsed_time": "5:37:53", "remaining_time": "0:52:20"}
|
| 267 |
+
{"current_steps": 2670, "total_steps": 3072, "loss": 0.8198, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0830235019739352e-06, "epoch": 2.61, "percentage": 86.91, "elapsed_time": "5:39:12", "remaining_time": "0:51:04"}
|
| 268 |
+
{"current_steps": 2680, "total_steps": 3072, "loss": 0.7836, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9820543175438077e-06, "epoch": 2.62, "percentage": 87.24, "elapsed_time": "5:40:33", "remaining_time": "0:49:48"}
|
| 269 |
+
{"current_steps": 2690, "total_steps": 3072, "loss": 0.7949, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8834923770343544e-06, "epoch": 2.63, "percentage": 87.57, "elapsed_time": "5:41:51", "remaining_time": "0:48:32"}
|
| 270 |
+
{"current_steps": 2700, "total_steps": 3072, "loss": 0.8243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.787347988169613e-06, "epoch": 2.64, "percentage": 87.89, "elapsed_time": "5:43:09", "remaining_time": "0:47:16"}
|
| 271 |
+
{"current_steps": 2710, "total_steps": 3072, "loss": 0.8798, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6936312058432158e-06, "epoch": 2.65, "percentage": 88.22, "elapsed_time": "5:44:29", "remaining_time": "0:46:01"}
|
| 272 |
+
{"current_steps": 2720, "total_steps": 3072, "loss": 0.9497, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6023518310668618e-06, "epoch": 2.65, "percentage": 88.54, "elapsed_time": "5:45:47", "remaining_time": "0:44:44"}
|
| 273 |
+
{"current_steps": 2730, "total_steps": 3072, "loss": 0.8978, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5135194099452521e-06, "epoch": 2.66, "percentage": 88.87, "elapsed_time": "5:46:59", "remaining_time": "0:43:28"}
|
| 274 |
+
{"current_steps": 2740, "total_steps": 3072, "loss": 0.8524, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4271432326778273e-06, "epoch": 2.67, "percentage": 89.19, "elapsed_time": "5:48:13", "remaining_time": "0:42:11"}
|
| 275 |
+
{"current_steps": 2750, "total_steps": 3072, "loss": 0.7888, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3432323325871216e-06, "epoch": 2.68, "percentage": 89.52, "elapsed_time": "5:49:28", "remaining_time": "0:40:55"}
|
| 276 |
+
{"current_steps": 2760, "total_steps": 3072, "loss": 0.8624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2617954851740832e-06, "epoch": 2.69, "percentage": 89.84, "elapsed_time": "5:50:43", "remaining_time": "0:39:38"}
|
| 277 |
+
{"current_steps": 2770, "total_steps": 3072, "loss": 0.8722, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1828412072003108e-06, "epoch": 2.7, "percentage": 90.17, "elapsed_time": "5:51:58", "remaining_time": "0:38:22"}
|
| 278 |
+
{"current_steps": 2780, "total_steps": 3072, "loss": 0.8501, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1063777557973638e-06, "epoch": 2.71, "percentage": 90.49, "elapsed_time": "5:53:18", "remaining_time": "0:37:06"}
|
| 279 |
+
{"current_steps": 2790, "total_steps": 3072, "loss": 0.8302, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0324131276032127e-06, "epoch": 2.72, "percentage": 90.82, "elapsed_time": "5:54:35", "remaining_time": "0:35:50"}
|
| 280 |
+
{"current_steps": 2800, "total_steps": 3072, "loss": 0.8424, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.609550579259496e-07, "epoch": 2.73, "percentage": 91.15, "elapsed_time": "5:55:52", "remaining_time": "0:34:34"}
|
| 281 |
+
{"current_steps": 2810, "total_steps": 3072, "loss": 0.8208, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.920110199348325e-07, "epoch": 2.74, "percentage": 91.47, "elapsed_time": "5:57:06", "remaining_time": "0:33:17"}
|
| 282 |
+
{"current_steps": 2820, "total_steps": 3072, "loss": 0.8773, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.255882238786983e-07, "epoch": 2.75, "percentage": 91.8, "elapsed_time": "5:58:24", "remaining_time": "0:32:01"}
|
| 283 |
+
{"current_steps": 2830, "total_steps": 3072, "loss": 0.7867, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.616936163319404e-07, "epoch": 2.76, "percentage": 92.12, "elapsed_time": "5:59:39", "remaining_time": "0:30:45"}
|
| 284 |
+
{"current_steps": 2840, "total_steps": 3072, "loss": 0.847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.003338794680153e-07, "epoch": 2.77, "percentage": 92.45, "elapsed_time": "6:00:57", "remaining_time": "0:29:29"}
|
| 285 |
+
{"current_steps": 2850, "total_steps": 3072, "loss": 0.8479, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.415154303606036e-07, "epoch": 2.78, "percentage": 92.77, "elapsed_time": "6:02:13", "remaining_time": "0:28:12"}
|
| 286 |
+
{"current_steps": 2860, "total_steps": 3072, "loss": 0.8197, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.852444203125223e-07, "epoch": 2.79, "percentage": 93.1, "elapsed_time": "6:03:28", "remaining_time": "0:26:56"}
|
| 287 |
+
{"current_steps": 2870, "total_steps": 3072, "loss": 0.8719, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.315267342124008e-07, "epoch": 2.8, "percentage": 93.42, "elapsed_time": "6:04:43", "remaining_time": "0:25:40"}
|
| 288 |
+
{"current_steps": 2880, "total_steps": 3072, "loss": 0.922, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.803679899192392e-07, "epoch": 2.81, "percentage": 93.75, "elapsed_time": "6:05:58", "remaining_time": "0:24:23"}
|
| 289 |
+
{"current_steps": 2890, "total_steps": 3072, "loss": 0.8622, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3177353767488163e-07, "epoch": 2.82, "percentage": 94.08, "elapsed_time": "6:07:13", "remaining_time": "0:23:07"}
|
| 290 |
+
{"current_steps": 2900, "total_steps": 3072, "loss": 0.8361, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8574845954448823e-07, "epoch": 2.83, "percentage": 94.4, "elapsed_time": "6:08:31", "remaining_time": "0:21:51"}
|
| 291 |
+
{"current_steps": 2910, "total_steps": 3072, "loss": 0.9201, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4229756888503604e-07, "epoch": 2.84, "percentage": 94.73, "elapsed_time": "6:09:41", "remaining_time": "0:20:34"}
|
| 292 |
+
{"current_steps": 2920, "total_steps": 3072, "loss": 0.834, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.014254098419406e-07, "epoch": 2.85, "percentage": 95.05, "elapsed_time": "6:10:55", "remaining_time": "0:19:18"}
|
| 293 |
+
{"current_steps": 2930, "total_steps": 3072, "loss": 0.8569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6313625687383046e-07, "epoch": 2.86, "percentage": 95.38, "elapsed_time": "6:12:10", "remaining_time": "0:18:02"}
|
| 294 |
+
{"current_steps": 2940, "total_steps": 3072, "loss": 0.8411, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2743411430549976e-07, "epoch": 2.87, "percentage": 95.7, "elapsed_time": "6:13:30", "remaining_time": "0:16:46"}
|
| 295 |
+
{"current_steps": 2950, "total_steps": 3072, "loss": 0.8648, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.943227159091482e-07, "epoch": 2.88, "percentage": 96.03, "elapsed_time": "6:14:45", "remaining_time": "0:15:29"}
|
| 296 |
+
{"current_steps": 2960, "total_steps": 3072, "loss": 0.8477, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6380552451389086e-07, "epoch": 2.89, "percentage": 96.35, "elapsed_time": "6:16:02", "remaining_time": "0:14:13"}
|
| 297 |
+
{"current_steps": 2970, "total_steps": 3072, "loss": 0.8449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3588573164361463e-07, "epoch": 2.9, "percentage": 96.68, "elapsed_time": "6:17:19", "remaining_time": "0:12:57"}
|
| 298 |
+
{"current_steps": 2980, "total_steps": 3072, "loss": 0.8185, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1056625718320334e-07, "epoch": 2.91, "percentage": 97.01, "elapsed_time": "6:18:37", "remaining_time": "0:11:41"}
|
| 299 |
+
{"current_steps": 2990, "total_steps": 3072, "loss": 0.8326, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.784974907317111e-08, "epoch": 2.92, "percentage": 97.33, "elapsed_time": "6:19:55", "remaining_time": "0:10:25"}
|
| 300 |
+
{"current_steps": 3000, "total_steps": 3072, "loss": 0.84, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.773858303274483e-08, "epoch": 2.93, "percentage": 97.66, "elapsed_time": "6:21:10", "remaining_time": "0:09:08"}
|
| 301 |
+
{"current_steps": 3010, "total_steps": 3072, "loss": 0.7393, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0234862311399065e-08, "epoch": 2.94, "percentage": 97.98, "elapsed_time": "6:22:24", "remaining_time": "0:07:52"}
|
| 302 |
+
{"current_steps": 3020, "total_steps": 3072, "loss": 0.8723, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5340417468898714e-08, "epoch": 2.95, "percentage": 98.31, "elapsed_time": "6:23:42", "remaining_time": "0:06:36"}
|
| 303 |
+
{"current_steps": 3030, "total_steps": 3072, "loss": 0.8481, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3056806183865965e-08, "epoch": 2.96, "percentage": 98.63, "elapsed_time": "6:25:00", "remaining_time": "0:05:20"}
|
| 304 |
+
{"current_steps": 3040, "total_steps": 3072, "loss": 0.8273, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3385313090857887e-08, "epoch": 2.97, "percentage": 98.96, "elapsed_time": "6:26:16", "remaining_time": "0:04:03"}
|
| 305 |
+
{"current_steps": 3050, "total_steps": 3072, "loss": 0.899, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.326949646040525e-09, "epoch": 2.98, "percentage": 99.28, "elapsed_time": "6:27:29", "remaining_time": "0:02:47"}
|
| 306 |
+
{"current_steps": 3060, "total_steps": 3072, "loss": 0.8056, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8824540213874255e-09, "epoch": 2.99, "percentage": 99.61, "elapsed_time": "6:28:46", "remaining_time": "0:01:31"}
|
| 307 |
+
{"current_steps": 3070, "total_steps": 3072, "loss": 0.8446, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.229102749415571e-11, "epoch": 3.0, "percentage": 99.93, "elapsed_time": "6:30:03", "remaining_time": "0:00:15"}
|
| 308 |
+
{"current_steps": 3072, "total_steps": 3072, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:30:18", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1870 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.998535871156662,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3072,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 4.9998692735249987e-05,
|
| 14 |
+
"loss": 0.9611,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 4.9994771077715244e-05,
|
| 20 |
+
"loss": 0.94,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 4.998823543752733e-05,
|
| 26 |
+
"loss": 0.9521,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.04,
|
| 31 |
+
"learning_rate": 4.9979086498191216e-05,
|
| 32 |
+
"loss": 0.9413,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.05,
|
| 37 |
+
"learning_rate": 4.9967325216513785e-05,
|
| 38 |
+
"loss": 0.8717,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.06,
|
| 43 |
+
"learning_rate": 4.995295282250373e-05,
|
| 44 |
+
"loss": 0.9099,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07,
|
| 49 |
+
"learning_rate": 4.993597081924299e-05,
|
| 50 |
+
"loss": 0.9671,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08,
|
| 55 |
+
"learning_rate": 4.991638098272951e-05,
|
| 56 |
+
"loss": 0.9971,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.09,
|
| 61 |
+
"learning_rate": 4.98941853616915e-05,
|
| 62 |
+
"loss": 0.9215,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.1,
|
| 67 |
+
"learning_rate": 4.98693862773732e-05,
|
| 68 |
+
"loss": 0.9008,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.11,
|
| 73 |
+
"learning_rate": 4.98419863232921e-05,
|
| 74 |
+
"loss": 0.8907,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.12,
|
| 79 |
+
"learning_rate": 4.981198836496775e-05,
|
| 80 |
+
"loss": 0.8838,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.13,
|
| 85 |
+
"learning_rate": 4.9779395539622024e-05,
|
| 86 |
+
"loss": 0.9156,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.14,
|
| 91 |
+
"learning_rate": 4.9744211255851046e-05,
|
| 92 |
+
"loss": 0.8241,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.15,
|
| 97 |
+
"learning_rate": 4.9706439193268736e-05,
|
| 98 |
+
"loss": 0.8777,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.16,
|
| 103 |
+
"learning_rate": 4.966608330212198e-05,
|
| 104 |
+
"loss": 0.8757,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.17,
|
| 109 |
+
"learning_rate": 4.962314780287748e-05,
|
| 110 |
+
"loss": 0.8574,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.18,
|
| 115 |
+
"learning_rate": 4.957763718578041e-05,
|
| 116 |
+
"loss": 0.8419,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.19,
|
| 121 |
+
"learning_rate": 4.952955621038482e-05,
|
| 122 |
+
"loss": 0.8368,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.2,
|
| 127 |
+
"learning_rate": 4.9478909905055845e-05,
|
| 128 |
+
"loss": 0.9646,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2,
|
| 133 |
+
"learning_rate": 4.942570356644386e-05,
|
| 134 |
+
"loss": 0.9666,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.21,
|
| 139 |
+
"learning_rate": 4.936994275893054e-05,
|
| 140 |
+
"loss": 0.9451,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.22,
|
| 145 |
+
"learning_rate": 4.931163331404694e-05,
|
| 146 |
+
"loss": 0.8937,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.23,
|
| 151 |
+
"learning_rate": 4.9250781329863606e-05,
|
| 152 |
+
"loss": 0.9066,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.24,
|
| 157 |
+
"learning_rate": 4.9187393170352844e-05,
|
| 158 |
+
"loss": 0.8378,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.25,
|
| 163 |
+
"learning_rate": 4.9121475464723175e-05,
|
| 164 |
+
"loss": 0.8696,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.26,
|
| 169 |
+
"learning_rate": 4.9053035106726045e-05,
|
| 170 |
+
"loss": 0.8534,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.27,
|
| 175 |
+
"learning_rate": 4.898207925393484e-05,
|
| 176 |
+
"loss": 0.8417,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.28,
|
| 181 |
+
"learning_rate": 4.890861532699639e-05,
|
| 182 |
+
"loss": 0.8718,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.29,
|
| 187 |
+
"learning_rate": 4.8832651008854845e-05,
|
| 188 |
+
"loss": 0.9024,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.3,
|
| 193 |
+
"learning_rate": 4.8754194243948245e-05,
|
| 194 |
+
"loss": 0.8846,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.31,
|
| 199 |
+
"learning_rate": 4.867325323737765e-05,
|
| 200 |
+
"loss": 0.8569,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.32,
|
| 205 |
+
"learning_rate": 4.858983645404901e-05,
|
| 206 |
+
"loss": 0.863,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.33,
|
| 211 |
+
"learning_rate": 4.8503952617787983e-05,
|
| 212 |
+
"loss": 0.7955,
|
| 213 |
+
"step": 340
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.34,
|
| 217 |
+
"learning_rate": 4.84156107104275e-05,
|
| 218 |
+
"loss": 0.913,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.35,
|
| 223 |
+
"learning_rate": 4.8324819970868473e-05,
|
| 224 |
+
"loss": 0.8538,
|
| 225 |
+
"step": 360
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.36,
|
| 229 |
+
"learning_rate": 4.8231589894113584e-05,
|
| 230 |
+
"loss": 0.9323,
|
| 231 |
+
"step": 370
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.37,
|
| 235 |
+
"learning_rate": 4.813593023027427e-05,
|
| 236 |
+
"loss": 0.8345,
|
| 237 |
+
"step": 380
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.38,
|
| 241 |
+
"learning_rate": 4.803785098355105e-05,
|
| 242 |
+
"loss": 0.8482,
|
| 243 |
+
"step": 390
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.39,
|
| 247 |
+
"learning_rate": 4.793736241118728e-05,
|
| 248 |
+
"loss": 0.9007,
|
| 249 |
+
"step": 400
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.4,
|
| 253 |
+
"learning_rate": 4.783447502239645e-05,
|
| 254 |
+
"loss": 0.8718,
|
| 255 |
+
"step": 410
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.41,
|
| 259 |
+
"learning_rate": 4.7729199577263065e-05,
|
| 260 |
+
"loss": 0.8733,
|
| 261 |
+
"step": 420
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.42,
|
| 265 |
+
"learning_rate": 4.7621547085617406e-05,
|
| 266 |
+
"loss": 0.7678,
|
| 267 |
+
"step": 430
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.43,
|
| 271 |
+
"learning_rate": 4.751152880588409e-05,
|
| 272 |
+
"loss": 0.8189,
|
| 273 |
+
"step": 440
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.44,
|
| 277 |
+
"learning_rate": 4.739915624390463e-05,
|
| 278 |
+
"loss": 0.9303,
|
| 279 |
+
"step": 450
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.45,
|
| 283 |
+
"learning_rate": 4.728444115173415e-05,
|
| 284 |
+
"loss": 0.8666,
|
| 285 |
+
"step": 460
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.46,
|
| 289 |
+
"learning_rate": 4.716739552641237e-05,
|
| 290 |
+
"loss": 0.8999,
|
| 291 |
+
"step": 470
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.47,
|
| 295 |
+
"learning_rate": 4.7048031608708876e-05,
|
| 296 |
+
"loss": 0.8813,
|
| 297 |
+
"step": 480
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.48,
|
| 301 |
+
"learning_rate": 4.692636188184305e-05,
|
| 302 |
+
"loss": 0.9063,
|
| 303 |
+
"step": 490
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.49,
|
| 307 |
+
"learning_rate": 4.680239907017849e-05,
|
| 308 |
+
"loss": 0.8109,
|
| 309 |
+
"step": 500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.5,
|
| 313 |
+
"learning_rate": 4.667615613789232e-05,
|
| 314 |
+
"loss": 0.825,
|
| 315 |
+
"step": 510
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.51,
|
| 319 |
+
"learning_rate": 4.654764628761936e-05,
|
| 320 |
+
"loss": 0.9117,
|
| 321 |
+
"step": 520
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.52,
|
| 325 |
+
"learning_rate": 4.6416882959071395e-05,
|
| 326 |
+
"loss": 0.8901,
|
| 327 |
+
"step": 530
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.53,
|
| 331 |
+
"learning_rate": 4.628387982763163e-05,
|
| 332 |
+
"loss": 0.8362,
|
| 333 |
+
"step": 540
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.54,
|
| 337 |
+
"learning_rate": 4.614865080292449e-05,
|
| 338 |
+
"loss": 0.9148,
|
| 339 |
+
"step": 550
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.55,
|
| 343 |
+
"learning_rate": 4.601121002736095e-05,
|
| 344 |
+
"loss": 0.9449,
|
| 345 |
+
"step": 560
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.56,
|
| 349 |
+
"learning_rate": 4.58715718746595e-05,
|
| 350 |
+
"loss": 0.7937,
|
| 351 |
+
"step": 570
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.57,
|
| 355 |
+
"learning_rate": 4.5729750948342926e-05,
|
| 356 |
+
"loss": 0.835,
|
| 357 |
+
"step": 580
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.58,
|
| 361 |
+
"learning_rate": 4.558576208021105e-05,
|
| 362 |
+
"loss": 0.9117,
|
| 363 |
+
"step": 590
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.59,
|
| 367 |
+
"learning_rate": 4.5439620328789593e-05,
|
| 368 |
+
"loss": 0.7855,
|
| 369 |
+
"step": 600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.6,
|
| 373 |
+
"learning_rate": 4.529134097775539e-05,
|
| 374 |
+
"loss": 0.8816,
|
| 375 |
+
"step": 610
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.61,
|
| 379 |
+
"learning_rate": 4.514093953433792e-05,
|
| 380 |
+
"loss": 0.8344,
|
| 381 |
+
"step": 620
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.61,
|
| 385 |
+
"learning_rate": 4.498843172769763e-05,
|
| 386 |
+
"loss": 0.8936,
|
| 387 |
+
"step": 630
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.62,
|
| 391 |
+
"learning_rate": 4.4833833507280884e-05,
|
| 392 |
+
"loss": 0.9126,
|
| 393 |
+
"step": 640
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.63,
|
| 397 |
+
"learning_rate": 4.4677161041152005e-05,
|
| 398 |
+
"loss": 0.8691,
|
| 399 |
+
"step": 650
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.64,
|
| 403 |
+
"learning_rate": 4.451843071430236e-05,
|
| 404 |
+
"loss": 0.8383,
|
| 405 |
+
"step": 660
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.65,
|
| 409 |
+
"learning_rate": 4.435765912693686e-05,
|
| 410 |
+
"loss": 0.9212,
|
| 411 |
+
"step": 670
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.66,
|
| 415 |
+
"learning_rate": 4.419486309273781e-05,
|
| 416 |
+
"loss": 0.8768,
|
| 417 |
+
"step": 680
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.67,
|
| 421 |
+
"learning_rate": 4.403005963710655e-05,
|
| 422 |
+
"loss": 0.9103,
|
| 423 |
+
"step": 690
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.68,
|
| 427 |
+
"learning_rate": 4.386326599538295e-05,
|
| 428 |
+
"loss": 0.8308,
|
| 429 |
+
"step": 700
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.69,
|
| 433 |
+
"learning_rate": 4.369449961104289e-05,
|
| 434 |
+
"loss": 0.9243,
|
| 435 |
+
"step": 710
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.7,
|
| 439 |
+
"learning_rate": 4.352377813387398e-05,
|
| 440 |
+
"loss": 0.8994,
|
| 441 |
+
"step": 720
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.71,
|
| 445 |
+
"learning_rate": 4.335111941812975e-05,
|
| 446 |
+
"loss": 0.9656,
|
| 447 |
+
"step": 730
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.72,
|
| 451 |
+
"learning_rate": 4.3176541520662426e-05,
|
| 452 |
+
"loss": 0.901,
|
| 453 |
+
"step": 740
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.73,
|
| 457 |
+
"learning_rate": 4.3000062699034544e-05,
|
| 458 |
+
"loss": 0.924,
|
| 459 |
+
"step": 750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.74,
|
| 463 |
+
"learning_rate": 4.28217014096095e-05,
|
| 464 |
+
"loss": 0.8821,
|
| 465 |
+
"step": 760
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.75,
|
| 469 |
+
"learning_rate": 4.264147630562141e-05,
|
| 470 |
+
"loss": 0.8631,
|
| 471 |
+
"step": 770
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.76,
|
| 475 |
+
"learning_rate": 4.245940623522433e-05,
|
| 476 |
+
"loss": 0.9012,
|
| 477 |
+
"step": 780
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.77,
|
| 481 |
+
"learning_rate": 4.227551023952104e-05,
|
| 482 |
+
"loss": 0.9543,
|
| 483 |
+
"step": 790
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.78,
|
| 487 |
+
"learning_rate": 4.208980755057178e-05,
|
| 488 |
+
"loss": 0.8243,
|
| 489 |
+
"step": 800
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.79,
|
| 493 |
+
"learning_rate": 4.19023175893829e-05,
|
| 494 |
+
"loss": 0.8568,
|
| 495 |
+
"step": 810
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.8,
|
| 499 |
+
"learning_rate": 4.171305996387577e-05,
|
| 500 |
+
"loss": 0.9434,
|
| 501 |
+
"step": 820
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.81,
|
| 505 |
+
"learning_rate": 4.1522054466836186e-05,
|
| 506 |
+
"loss": 0.8362,
|
| 507 |
+
"step": 830
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.82,
|
| 511 |
+
"learning_rate": 4.1329321073844415e-05,
|
| 512 |
+
"loss": 0.8904,
|
| 513 |
+
"step": 840
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.83,
|
| 517 |
+
"learning_rate": 4.1134879941186135e-05,
|
| 518 |
+
"loss": 0.9025,
|
| 519 |
+
"step": 850
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.84,
|
| 523 |
+
"learning_rate": 4.093875140374443e-05,
|
| 524 |
+
"loss": 0.872,
|
| 525 |
+
"step": 860
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.85,
|
| 529 |
+
"learning_rate": 4.074095597287318e-05,
|
| 530 |
+
"loss": 0.8268,
|
| 531 |
+
"step": 870
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.86,
|
| 535 |
+
"learning_rate": 4.054151433425194e-05,
|
| 536 |
+
"loss": 0.8755,
|
| 537 |
+
"step": 880
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.87,
|
| 541 |
+
"learning_rate": 4.034044734572262e-05,
|
| 542 |
+
"loss": 0.8389,
|
| 543 |
+
"step": 890
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.88,
|
| 547 |
+
"learning_rate": 4.013777603510814e-05,
|
| 548 |
+
"loss": 0.8528,
|
| 549 |
+
"step": 900
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.89,
|
| 553 |
+
"learning_rate": 3.993352159801332e-05,
|
| 554 |
+
"loss": 0.8036,
|
| 555 |
+
"step": 910
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.9,
|
| 559 |
+
"learning_rate": 3.9727705395608205e-05,
|
| 560 |
+
"loss": 0.8854,
|
| 561 |
+
"step": 920
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.91,
|
| 565 |
+
"learning_rate": 3.9520348952394115e-05,
|
| 566 |
+
"loss": 0.8261,
|
| 567 |
+
"step": 930
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.92,
|
| 571 |
+
"learning_rate": 3.931147395395256e-05,
|
| 572 |
+
"loss": 0.842,
|
| 573 |
+
"step": 940
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.93,
|
| 577 |
+
"learning_rate": 3.9101102244677335e-05,
|
| 578 |
+
"loss": 0.8749,
|
| 579 |
+
"step": 950
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.94,
|
| 583 |
+
"learning_rate": 3.888925582549006e-05,
|
| 584 |
+
"loss": 0.8799,
|
| 585 |
+
"step": 960
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.95,
|
| 589 |
+
"learning_rate": 3.867595685153922e-05,
|
| 590 |
+
"loss": 0.8573,
|
| 591 |
+
"step": 970
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.96,
|
| 595 |
+
"learning_rate": 3.846122762988319e-05,
|
| 596 |
+
"loss": 0.8694,
|
| 597 |
+
"step": 980
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.97,
|
| 601 |
+
"learning_rate": 3.824509061715738e-05,
|
| 602 |
+
"loss": 0.927,
|
| 603 |
+
"step": 990
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.98,
|
| 607 |
+
"learning_rate": 3.802756841722559e-05,
|
| 608 |
+
"loss": 0.8816,
|
| 609 |
+
"step": 1000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.99,
|
| 613 |
+
"learning_rate": 3.780868377881619e-05,
|
| 614 |
+
"loss": 0.9129,
|
| 615 |
+
"step": 1010
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.0,
|
| 619 |
+
"learning_rate": 3.758845959314294e-05,
|
| 620 |
+
"loss": 0.8362,
|
| 621 |
+
"step": 1020
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.01,
|
| 625 |
+
"learning_rate": 3.7366918891511046e-05,
|
| 626 |
+
"loss": 0.8907,
|
| 627 |
+
"step": 1030
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.02,
|
| 631 |
+
"learning_rate": 3.7144084842908505e-05,
|
| 632 |
+
"loss": 0.9378,
|
| 633 |
+
"step": 1040
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.02,
|
| 637 |
+
"learning_rate": 3.691998075158306e-05,
|
| 638 |
+
"loss": 0.9064,
|
| 639 |
+
"step": 1050
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.03,
|
| 643 |
+
"learning_rate": 3.669463005460502e-05,
|
| 644 |
+
"loss": 0.9101,
|
| 645 |
+
"step": 1060
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.04,
|
| 649 |
+
"learning_rate": 3.646805631941619e-05,
|
| 650 |
+
"loss": 0.8307,
|
| 651 |
+
"step": 1070
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.05,
|
| 655 |
+
"learning_rate": 3.624028324136517e-05,
|
| 656 |
+
"loss": 0.8958,
|
| 657 |
+
"step": 1080
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.06,
|
| 661 |
+
"learning_rate": 3.6011334641229215e-05,
|
| 662 |
+
"loss": 0.8681,
|
| 663 |
+
"step": 1090
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 1.07,
|
| 667 |
+
"learning_rate": 3.578123446272309e-05,
|
| 668 |
+
"loss": 0.8711,
|
| 669 |
+
"step": 1100
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.08,
|
| 673 |
+
"learning_rate": 3.5550006769994996e-05,
|
| 674 |
+
"loss": 0.8607,
|
| 675 |
+
"step": 1110
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.09,
|
| 679 |
+
"learning_rate": 3.5317675745109866e-05,
|
| 680 |
+
"loss": 0.9532,
|
| 681 |
+
"step": 1120
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.1,
|
| 685 |
+
"learning_rate": 3.508426568552045e-05,
|
| 686 |
+
"loss": 0.848,
|
| 687 |
+
"step": 1130
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.11,
|
| 691 |
+
"learning_rate": 3.484980100152621e-05,
|
| 692 |
+
"loss": 0.8097,
|
| 693 |
+
"step": 1140
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.12,
|
| 697 |
+
"learning_rate": 3.461430621372044e-05,
|
| 698 |
+
"loss": 0.8612,
|
| 699 |
+
"step": 1150
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.13,
|
| 703 |
+
"learning_rate": 3.437780595042595e-05,
|
| 704 |
+
"loss": 0.8281,
|
| 705 |
+
"step": 1160
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.14,
|
| 709 |
+
"learning_rate": 3.414032494511935e-05,
|
| 710 |
+
"loss": 0.8297,
|
| 711 |
+
"step": 1170
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.15,
|
| 715 |
+
"learning_rate": 3.390188803384439e-05,
|
| 716 |
+
"loss": 0.8607,
|
| 717 |
+
"step": 1180
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.16,
|
| 721 |
+
"learning_rate": 3.3662520152614615e-05,
|
| 722 |
+
"loss": 0.8986,
|
| 723 |
+
"step": 1190
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.17,
|
| 727 |
+
"learning_rate": 3.34222463348055e-05,
|
| 728 |
+
"loss": 0.8884,
|
| 729 |
+
"step": 1200
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.18,
|
| 733 |
+
"learning_rate": 3.3181091708536435e-05,
|
| 734 |
+
"loss": 0.8901,
|
| 735 |
+
"step": 1210
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.19,
|
| 739 |
+
"learning_rate": 3.293908149404279e-05,
|
| 740 |
+
"loss": 0.8583,
|
| 741 |
+
"step": 1220
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.2,
|
| 745 |
+
"learning_rate": 3.2696241001038374e-05,
|
| 746 |
+
"loss": 0.7928,
|
| 747 |
+
"step": 1230
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.21,
|
| 751 |
+
"learning_rate": 3.245259562606851e-05,
|
| 752 |
+
"loss": 0.8508,
|
| 753 |
+
"step": 1240
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.22,
|
| 757 |
+
"learning_rate": 3.220817084985398e-05,
|
| 758 |
+
"loss": 0.8245,
|
| 759 |
+
"step": 1250
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.23,
|
| 763 |
+
"learning_rate": 3.196299223462633e-05,
|
| 764 |
+
"loss": 0.8746,
|
| 765 |
+
"step": 1260
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.24,
|
| 769 |
+
"learning_rate": 3.171708542145445e-05,
|
| 770 |
+
"loss": 0.8666,
|
| 771 |
+
"step": 1270
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.25,
|
| 775 |
+
"learning_rate": 3.147047612756302e-05,
|
| 776 |
+
"loss": 0.8807,
|
| 777 |
+
"step": 1280
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.26,
|
| 781 |
+
"learning_rate": 3.1223190143643014e-05,
|
| 782 |
+
"loss": 0.8557,
|
| 783 |
+
"step": 1290
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.27,
|
| 787 |
+
"learning_rate": 3.09752533311544e-05,
|
| 788 |
+
"loss": 0.842,
|
| 789 |
+
"step": 1300
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.28,
|
| 793 |
+
"learning_rate": 3.0726691619621617e-05,
|
| 794 |
+
"loss": 0.8701,
|
| 795 |
+
"step": 1310
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.29,
|
| 799 |
+
"learning_rate": 3.0477531003921745e-05,
|
| 800 |
+
"loss": 0.8755,
|
| 801 |
+
"step": 1320
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.3,
|
| 805 |
+
"learning_rate": 3.0227797541566e-05,
|
| 806 |
+
"loss": 0.9009,
|
| 807 |
+
"step": 1330
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.31,
|
| 811 |
+
"learning_rate": 2.9977517349974544e-05,
|
| 812 |
+
"loss": 0.8578,
|
| 813 |
+
"step": 1340
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.32,
|
| 817 |
+
"learning_rate": 2.9726716603745157e-05,
|
| 818 |
+
"loss": 0.8067,
|
| 819 |
+
"step": 1350
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.33,
|
| 823 |
+
"learning_rate": 2.9475421531915827e-05,
|
| 824 |
+
"loss": 0.8139,
|
| 825 |
+
"step": 1360
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.34,
|
| 829 |
+
"learning_rate": 2.922365841522167e-05,
|
| 830 |
+
"loss": 0.8382,
|
| 831 |
+
"step": 1370
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.35,
|
| 835 |
+
"learning_rate": 2.8971453583346536e-05,
|
| 836 |
+
"loss": 0.9073,
|
| 837 |
+
"step": 1380
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.36,
|
| 841 |
+
"learning_rate": 2.871883341216934e-05,
|
| 842 |
+
"loss": 0.8783,
|
| 843 |
+
"step": 1390
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.37,
|
| 847 |
+
"learning_rate": 2.846582432100567e-05,
|
| 848 |
+
"loss": 0.8555,
|
| 849 |
+
"step": 1400
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.38,
|
| 853 |
+
"learning_rate": 2.8212452769844834e-05,
|
| 854 |
+
"loss": 0.8236,
|
| 855 |
+
"step": 1410
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.39,
|
| 859 |
+
"learning_rate": 2.795874525658263e-05,
|
| 860 |
+
"loss": 0.8816,
|
| 861 |
+
"step": 1420
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.4,
|
| 865 |
+
"learning_rate": 2.7704728314250168e-05,
|
| 866 |
+
"loss": 0.8199,
|
| 867 |
+
"step": 1430
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.41,
|
| 871 |
+
"learning_rate": 2.7450428508239024e-05,
|
| 872 |
+
"loss": 0.8271,
|
| 873 |
+
"step": 1440
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.42,
|
| 877 |
+
"learning_rate": 2.7195872433522974e-05,
|
| 878 |
+
"loss": 0.8444,
|
| 879 |
+
"step": 1450
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.43,
|
| 883 |
+
"learning_rate": 2.694108671187669e-05,
|
| 884 |
+
"loss": 0.8232,
|
| 885 |
+
"step": 1460
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.43,
|
| 889 |
+
"learning_rate": 2.66860979890916e-05,
|
| 890 |
+
"loss": 0.7959,
|
| 891 |
+
"step": 1470
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.44,
|
| 895 |
+
"learning_rate": 2.6430932932189224e-05,
|
| 896 |
+
"loss": 0.8368,
|
| 897 |
+
"step": 1480
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.45,
|
| 901 |
+
"learning_rate": 2.617561822663228e-05,
|
| 902 |
+
"loss": 0.8336,
|
| 903 |
+
"step": 1490
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.46,
|
| 907 |
+
"learning_rate": 2.5920180573533976e-05,
|
| 908 |
+
"loss": 0.8431,
|
| 909 |
+
"step": 1500
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.47,
|
| 913 |
+
"learning_rate": 2.566464668686547e-05,
|
| 914 |
+
"loss": 0.8309,
|
| 915 |
+
"step": 1510
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.48,
|
| 919 |
+
"learning_rate": 2.5409043290662173e-05,
|
| 920 |
+
"loss": 0.9332,
|
| 921 |
+
"step": 1520
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.49,
|
| 925 |
+
"learning_rate": 2.5153397116228865e-05,
|
| 926 |
+
"loss": 0.8416,
|
| 927 |
+
"step": 1530
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.5,
|
| 931 |
+
"learning_rate": 2.489773489934413e-05,
|
| 932 |
+
"loss": 0.8978,
|
| 933 |
+
"step": 1540
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.51,
|
| 937 |
+
"learning_rate": 2.4642083377464305e-05,
|
| 938 |
+
"loss": 0.8724,
|
| 939 |
+
"step": 1550
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.52,
|
| 943 |
+
"learning_rate": 2.4386469286927196e-05,
|
| 944 |
+
"loss": 0.9087,
|
| 945 |
+
"step": 1560
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.53,
|
| 949 |
+
"learning_rate": 2.413091936015603e-05,
|
| 950 |
+
"loss": 0.8749,
|
| 951 |
+
"step": 1570
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 1.54,
|
| 955 |
+
"learning_rate": 2.3875460322863697e-05,
|
| 956 |
+
"loss": 0.8781,
|
| 957 |
+
"step": 1580
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 1.55,
|
| 961 |
+
"learning_rate": 2.3620118891257754e-05,
|
| 962 |
+
"loss": 0.8544,
|
| 963 |
+
"step": 1590
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 1.56,
|
| 967 |
+
"learning_rate": 2.3364921769246423e-05,
|
| 968 |
+
"loss": 0.8244,
|
| 969 |
+
"step": 1600
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.57,
|
| 973 |
+
"learning_rate": 2.3109895645645867e-05,
|
| 974 |
+
"loss": 0.8656,
|
| 975 |
+
"step": 1610
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 1.58,
|
| 979 |
+
"learning_rate": 2.2855067191389006e-05,
|
| 980 |
+
"loss": 0.888,
|
| 981 |
+
"step": 1620
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.59,
|
| 985 |
+
"learning_rate": 2.2600463056736293e-05,
|
| 986 |
+
"loss": 0.8219,
|
| 987 |
+
"step": 1630
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 1.6,
|
| 991 |
+
"learning_rate": 2.2346109868488567e-05,
|
| 992 |
+
"loss": 0.8732,
|
| 993 |
+
"step": 1640
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 1.61,
|
| 997 |
+
"learning_rate": 2.2092034227202383e-05,
|
| 998 |
+
"loss": 0.8984,
|
| 999 |
+
"step": 1650
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.62,
|
| 1003 |
+
"learning_rate": 2.183826270440812e-05,
|
| 1004 |
+
"loss": 0.8474,
|
| 1005 |
+
"step": 1660
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 1.63,
|
| 1009 |
+
"learning_rate": 2.158482183983109e-05,
|
| 1010 |
+
"loss": 0.8423,
|
| 1011 |
+
"step": 1670
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.64,
|
| 1015 |
+
"learning_rate": 2.1331738138615958e-05,
|
| 1016 |
+
"loss": 0.8716,
|
| 1017 |
+
"step": 1680
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 1.65,
|
| 1021 |
+
"learning_rate": 2.1079038068554842e-05,
|
| 1022 |
+
"loss": 0.8783,
|
| 1023 |
+
"step": 1690
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.66,
|
| 1027 |
+
"learning_rate": 2.082674805731926e-05,
|
| 1028 |
+
"loss": 0.7759,
|
| 1029 |
+
"step": 1700
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.67,
|
| 1033 |
+
"learning_rate": 2.0574894489696285e-05,
|
| 1034 |
+
"loss": 0.8975,
|
| 1035 |
+
"step": 1710
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.68,
|
| 1039 |
+
"learning_rate": 2.03235037048292e-05,
|
| 1040 |
+
"loss": 0.8425,
|
| 1041 |
+
"step": 1720
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.69,
|
| 1045 |
+
"learning_rate": 2.0072601993462946e-05,
|
| 1046 |
+
"loss": 0.824,
|
| 1047 |
+
"step": 1730
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 1.7,
|
| 1051 |
+
"learning_rate": 1.982221559519454e-05,
|
| 1052 |
+
"loss": 0.7989,
|
| 1053 |
+
"step": 1740
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.71,
|
| 1057 |
+
"learning_rate": 1.957237069572898e-05,
|
| 1058 |
+
"loss": 0.8145,
|
| 1059 |
+
"step": 1750
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.72,
|
| 1063 |
+
"learning_rate": 1.932309342414067e-05,
|
| 1064 |
+
"loss": 0.8581,
|
| 1065 |
+
"step": 1760
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.73,
|
| 1069 |
+
"learning_rate": 1.907440985014082e-05,
|
| 1070 |
+
"loss": 0.8886,
|
| 1071 |
+
"step": 1770
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.74,
|
| 1075 |
+
"learning_rate": 1.8826345981351044e-05,
|
| 1076 |
+
"loss": 0.8048,
|
| 1077 |
+
"step": 1780
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.75,
|
| 1081 |
+
"learning_rate": 1.8578927760583463e-05,
|
| 1082 |
+
"loss": 0.8534,
|
| 1083 |
+
"step": 1790
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.76,
|
| 1087 |
+
"learning_rate": 1.8332181063127545e-05,
|
| 1088 |
+
"loss": 0.8392,
|
| 1089 |
+
"step": 1800
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.77,
|
| 1093 |
+
"learning_rate": 1.8086131694044077e-05,
|
| 1094 |
+
"loss": 0.8926,
|
| 1095 |
+
"step": 1810
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.78,
|
| 1099 |
+
"learning_rate": 1.784080538546642e-05,
|
| 1100 |
+
"loss": 0.923,
|
| 1101 |
+
"step": 1820
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.79,
|
| 1105 |
+
"learning_rate": 1.7596227793909402e-05,
|
| 1106 |
+
"loss": 0.8209,
|
| 1107 |
+
"step": 1830
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.8,
|
| 1111 |
+
"learning_rate": 1.7352424497586163e-05,
|
| 1112 |
+
"loss": 0.813,
|
| 1113 |
+
"step": 1840
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 1.81,
|
| 1117 |
+
"learning_rate": 1.7109420993733115e-05,
|
| 1118 |
+
"loss": 0.8375,
|
| 1119 |
+
"step": 1850
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.82,
|
| 1123 |
+
"learning_rate": 1.686724269594343e-05,
|
| 1124 |
+
"loss": 0.8477,
|
| 1125 |
+
"step": 1860
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 1.83,
|
| 1129 |
+
"learning_rate": 1.6625914931509262e-05,
|
| 1130 |
+
"loss": 0.8263,
|
| 1131 |
+
"step": 1870
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 1.84,
|
| 1135 |
+
"learning_rate": 1.6385462938772992e-05,
|
| 1136 |
+
"loss": 0.8816,
|
| 1137 |
+
"step": 1880
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.84,
|
| 1141 |
+
"learning_rate": 1.614591186448774e-05,
|
| 1142 |
+
"loss": 0.8677,
|
| 1143 |
+
"step": 1890
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.85,
|
| 1147 |
+
"learning_rate": 1.5907286761187535e-05,
|
| 1148 |
+
"loss": 0.9021,
|
| 1149 |
+
"step": 1900
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.86,
|
| 1153 |
+
"learning_rate": 1.5669612584567265e-05,
|
| 1154 |
+
"loss": 0.8449,
|
| 1155 |
+
"step": 1910
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.87,
|
| 1159 |
+
"learning_rate": 1.5432914190872757e-05,
|
| 1160 |
+
"loss": 0.8328,
|
| 1161 |
+
"step": 1920
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.88,
|
| 1165 |
+
"learning_rate": 1.5197216334301339e-05,
|
| 1166 |
+
"loss": 0.8591,
|
| 1167 |
+
"step": 1930
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 1.89,
|
| 1171 |
+
"learning_rate": 1.4962543664412986e-05,
|
| 1172 |
+
"loss": 0.9411,
|
| 1173 |
+
"step": 1940
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 1.9,
|
| 1177 |
+
"learning_rate": 1.4728920723552407e-05,
|
| 1178 |
+
"loss": 0.9106,
|
| 1179 |
+
"step": 1950
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.91,
|
| 1183 |
+
"learning_rate": 1.4496371944282441e-05,
|
| 1184 |
+
"loss": 0.8332,
|
| 1185 |
+
"step": 1960
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.92,
|
| 1189 |
+
"learning_rate": 1.4264921646828838e-05,
|
| 1190 |
+
"loss": 0.783,
|
| 1191 |
+
"step": 1970
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.93,
|
| 1195 |
+
"learning_rate": 1.4034594036536817e-05,
|
| 1196 |
+
"loss": 0.8703,
|
| 1197 |
+
"step": 1980
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.94,
|
| 1201 |
+
"learning_rate": 1.3805413201339632e-05,
|
| 1202 |
+
"loss": 0.8918,
|
| 1203 |
+
"step": 1990
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.95,
|
| 1207 |
+
"learning_rate": 1.3577403109239484e-05,
|
| 1208 |
+
"loss": 0.8795,
|
| 1209 |
+
"step": 2000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 1.96,
|
| 1213 |
+
"learning_rate": 1.3350587605800852e-05,
|
| 1214 |
+
"loss": 0.8222,
|
| 1215 |
+
"step": 2010
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 1.97,
|
| 1219 |
+
"learning_rate": 1.3124990411656706e-05,
|
| 1220 |
+
"loss": 0.8187,
|
| 1221 |
+
"step": 2020
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.98,
|
| 1225 |
+
"learning_rate": 1.2900635120027859e-05,
|
| 1226 |
+
"loss": 0.8343,
|
| 1227 |
+
"step": 2030
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.99,
|
| 1231 |
+
"learning_rate": 1.2677545194255402e-05,
|
| 1232 |
+
"loss": 0.9145,
|
| 1233 |
+
"step": 2040
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 2.0,
|
| 1237 |
+
"learning_rate": 1.2455743965347047e-05,
|
| 1238 |
+
"loss": 0.913,
|
| 1239 |
+
"step": 2050
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 2.01,
|
| 1243 |
+
"learning_rate": 1.223525462953703e-05,
|
| 1244 |
+
"loss": 0.9304,
|
| 1245 |
+
"step": 2060
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.02,
|
| 1249 |
+
"learning_rate": 1.201610024586026e-05,
|
| 1250 |
+
"loss": 0.82,
|
| 1251 |
+
"step": 2070
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 2.03,
|
| 1255 |
+
"learning_rate": 1.1798303733740802e-05,
|
| 1256 |
+
"loss": 0.8232,
|
| 1257 |
+
"step": 2080
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.04,
|
| 1261 |
+
"learning_rate": 1.1581887870594884e-05,
|
| 1262 |
+
"loss": 0.8997,
|
| 1263 |
+
"step": 2090
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.05,
|
| 1267 |
+
"learning_rate": 1.1366875289448845e-05,
|
| 1268 |
+
"loss": 0.9386,
|
| 1269 |
+
"step": 2100
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 2.06,
|
| 1273 |
+
"learning_rate": 1.1153288476572126e-05,
|
| 1274 |
+
"loss": 0.8515,
|
| 1275 |
+
"step": 2110
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 2.07,
|
| 1279 |
+
"learning_rate": 1.0941149769125674e-05,
|
| 1280 |
+
"loss": 0.8724,
|
| 1281 |
+
"step": 2120
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 2.08,
|
| 1285 |
+
"learning_rate": 1.0730481352825823e-05,
|
| 1286 |
+
"loss": 0.8616,
|
| 1287 |
+
"step": 2130
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 2.09,
|
| 1291 |
+
"learning_rate": 1.0521305259624129e-05,
|
| 1292 |
+
"loss": 0.82,
|
| 1293 |
+
"step": 2140
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 2.1,
|
| 1297 |
+
"learning_rate": 1.0313643365403274e-05,
|
| 1298 |
+
"loss": 0.866,
|
| 1299 |
+
"step": 2150
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.11,
|
| 1303 |
+
"learning_rate": 1.0107517387689166e-05,
|
| 1304 |
+
"loss": 0.7712,
|
| 1305 |
+
"step": 2160
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.12,
|
| 1309 |
+
"learning_rate": 9.90294888337981e-06,
|
| 1310 |
+
"loss": 0.8451,
|
| 1311 |
+
"step": 2170
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 2.13,
|
| 1315 |
+
"learning_rate": 9.699959246490762e-06,
|
| 1316 |
+
"loss": 0.7923,
|
| 1317 |
+
"step": 2180
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 2.14,
|
| 1321 |
+
"learning_rate": 9.498569705917771e-06,
|
| 1322 |
+
"loss": 0.8547,
|
| 1323 |
+
"step": 2190
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 2.15,
|
| 1327 |
+
"learning_rate": 9.298801323216647e-06,
|
| 1328 |
+
"loss": 0.8624,
|
| 1329 |
+
"step": 2200
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.16,
|
| 1333 |
+
"learning_rate": 9.100674990400571e-06,
|
| 1334 |
+
"loss": 0.8079,
|
| 1335 |
+
"step": 2210
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 2.17,
|
| 1339 |
+
"learning_rate": 8.904211427755218e-06,
|
| 1340 |
+
"loss": 0.8211,
|
| 1341 |
+
"step": 2220
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.18,
|
| 1345 |
+
"learning_rate": 8.70943118167179e-06,
|
| 1346 |
+
"loss": 0.9058,
|
| 1347 |
+
"step": 2230
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.19,
|
| 1351 |
+
"learning_rate": 8.51635462249828e-06,
|
| 1352 |
+
"loss": 0.7715,
|
| 1353 |
+
"step": 2240
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 2.2,
|
| 1357 |
+
"learning_rate": 8.325001942409066e-06,
|
| 1358 |
+
"loss": 0.8093,
|
| 1359 |
+
"step": 2250
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 2.21,
|
| 1363 |
+
"learning_rate": 8.13539315329322e-06,
|
| 1364 |
+
"loss": 0.8812,
|
| 1365 |
+
"step": 2260
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 2.22,
|
| 1369 |
+
"learning_rate": 7.947548084661674e-06,
|
| 1370 |
+
"loss": 0.8675,
|
| 1371 |
+
"step": 2270
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 2.23,
|
| 1375 |
+
"learning_rate": 7.761486381573327e-06,
|
| 1376 |
+
"loss": 0.7757,
|
| 1377 |
+
"step": 2280
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 2.24,
|
| 1381 |
+
"learning_rate": 7.577227502580667e-06,
|
| 1382 |
+
"loss": 0.9026,
|
| 1383 |
+
"step": 2290
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 2.24,
|
| 1387 |
+
"learning_rate": 7.394790717694677e-06,
|
| 1388 |
+
"loss": 0.8779,
|
| 1389 |
+
"step": 2300
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.25,
|
| 1393 |
+
"learning_rate": 7.214195106369587e-06,
|
| 1394 |
+
"loss": 0.8702,
|
| 1395 |
+
"step": 2310
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 2.26,
|
| 1399 |
+
"learning_rate": 7.035459555507548e-06,
|
| 1400 |
+
"loss": 0.8602,
|
| 1401 |
+
"step": 2320
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 2.27,
|
| 1405 |
+
"learning_rate": 6.858602757483371e-06,
|
| 1406 |
+
"loss": 0.8647,
|
| 1407 |
+
"step": 2330
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 2.28,
|
| 1411 |
+
"learning_rate": 6.683643208189683e-06,
|
| 1412 |
+
"loss": 0.8216,
|
| 1413 |
+
"step": 2340
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.29,
|
| 1417 |
+
"learning_rate": 6.510599205102594e-06,
|
| 1418 |
+
"loss": 0.8674,
|
| 1419 |
+
"step": 2350
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 2.3,
|
| 1423 |
+
"learning_rate": 6.339488845368155e-06,
|
| 1424 |
+
"loss": 0.8232,
|
| 1425 |
+
"step": 2360
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.31,
|
| 1429 |
+
"learning_rate": 6.17033002390969e-06,
|
| 1430 |
+
"loss": 0.8058,
|
| 1431 |
+
"step": 2370
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.32,
|
| 1435 |
+
"learning_rate": 6.003140431556345e-06,
|
| 1436 |
+
"loss": 0.8183,
|
| 1437 |
+
"step": 2380
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 2.33,
|
| 1441 |
+
"learning_rate": 5.837937553192999e-06,
|
| 1442 |
+
"loss": 0.8745,
|
| 1443 |
+
"step": 2390
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 2.34,
|
| 1447 |
+
"learning_rate": 5.674738665931575e-06,
|
| 1448 |
+
"loss": 0.7398,
|
| 1449 |
+
"step": 2400
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.35,
|
| 1453 |
+
"learning_rate": 5.513560837304304e-06,
|
| 1454 |
+
"loss": 0.8321,
|
| 1455 |
+
"step": 2410
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 2.36,
|
| 1459 |
+
"learning_rate": 5.354420923478687e-06,
|
| 1460 |
+
"loss": 0.8657,
|
| 1461 |
+
"step": 2420
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 2.37,
|
| 1465 |
+
"learning_rate": 5.197335567494696e-06,
|
| 1466 |
+
"loss": 0.8899,
|
| 1467 |
+
"step": 2430
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 2.38,
|
| 1471 |
+
"learning_rate": 5.042321197524213e-06,
|
| 1472 |
+
"loss": 0.8185,
|
| 1473 |
+
"step": 2440
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.39,
|
| 1477 |
+
"learning_rate": 4.889394025152979e-06,
|
| 1478 |
+
"loss": 0.9032,
|
| 1479 |
+
"step": 2450
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.4,
|
| 1483 |
+
"learning_rate": 4.738570043685134e-06,
|
| 1484 |
+
"loss": 0.8692,
|
| 1485 |
+
"step": 2460
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 2.41,
|
| 1489 |
+
"learning_rate": 4.589865026470619e-06,
|
| 1490 |
+
"loss": 0.8571,
|
| 1491 |
+
"step": 2470
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 2.42,
|
| 1495 |
+
"learning_rate": 4.4432945252556284e-06,
|
| 1496 |
+
"loss": 0.8563,
|
| 1497 |
+
"step": 2480
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 2.43,
|
| 1501 |
+
"learning_rate": 4.298873868556108e-06,
|
| 1502 |
+
"loss": 0.8423,
|
| 1503 |
+
"step": 2490
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 2.44,
|
| 1507 |
+
"learning_rate": 4.156618160054771e-06,
|
| 1508 |
+
"loss": 0.8008,
|
| 1509 |
+
"step": 2500
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 2.45,
|
| 1513 |
+
"learning_rate": 4.016542277021465e-06,
|
| 1514 |
+
"loss": 0.9192,
|
| 1515 |
+
"step": 2510
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.46,
|
| 1519 |
+
"learning_rate": 3.878660868757323e-06,
|
| 1520 |
+
"loss": 0.9414,
|
| 1521 |
+
"step": 2520
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 2.47,
|
| 1525 |
+
"learning_rate": 3.742988355062735e-06,
|
| 1526 |
+
"loss": 0.8645,
|
| 1527 |
+
"step": 2530
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 2.48,
|
| 1531 |
+
"learning_rate": 3.609538924729269e-06,
|
| 1532 |
+
"loss": 0.7851,
|
| 1533 |
+
"step": 2540
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 2.49,
|
| 1537 |
+
"learning_rate": 3.478326534055823e-06,
|
| 1538 |
+
"loss": 0.8207,
|
| 1539 |
+
"step": 2550
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 2.5,
|
| 1543 |
+
"learning_rate": 3.3493649053890326e-06,
|
| 1544 |
+
"loss": 0.8443,
|
| 1545 |
+
"step": 2560
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 2.51,
|
| 1549 |
+
"learning_rate": 3.2226675256882167e-06,
|
| 1550 |
+
"loss": 0.841,
|
| 1551 |
+
"step": 2570
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 2.52,
|
| 1555 |
+
"learning_rate": 3.098247645114838e-06,
|
| 1556 |
+
"loss": 0.8591,
|
| 1557 |
+
"step": 2580
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.53,
|
| 1561 |
+
"learning_rate": 2.9761182756468165e-06,
|
| 1562 |
+
"loss": 0.8146,
|
| 1563 |
+
"step": 2590
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 2.54,
|
| 1567 |
+
"learning_rate": 2.856292189717741e-06,
|
| 1568 |
+
"loss": 0.8441,
|
| 1569 |
+
"step": 2600
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 2.55,
|
| 1573 |
+
"learning_rate": 2.7387819188810534e-06,
|
| 1574 |
+
"loss": 0.878,
|
| 1575 |
+
"step": 2610
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 2.56,
|
| 1579 |
+
"learning_rate": 2.623599752499553e-06,
|
| 1580 |
+
"loss": 0.8543,
|
| 1581 |
+
"step": 2620
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 2.57,
|
| 1585 |
+
"learning_rate": 2.510757736460112e-06,
|
| 1586 |
+
"loss": 0.8435,
|
| 1587 |
+
"step": 2630
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 2.58,
|
| 1591 |
+
"learning_rate": 2.4002676719139166e-06,
|
| 1592 |
+
"loss": 0.8424,
|
| 1593 |
+
"step": 2640
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.59,
|
| 1597 |
+
"learning_rate": 2.2921411140423037e-06,
|
| 1598 |
+
"loss": 0.8488,
|
| 1599 |
+
"step": 2650
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.6,
|
| 1603 |
+
"learning_rate": 2.1863893708482795e-06,
|
| 1604 |
+
"loss": 0.8021,
|
| 1605 |
+
"step": 2660
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 2.61,
|
| 1609 |
+
"learning_rate": 2.0830235019739352e-06,
|
| 1610 |
+
"loss": 0.8198,
|
| 1611 |
+
"step": 2670
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 2.62,
|
| 1615 |
+
"learning_rate": 1.9820543175438077e-06,
|
| 1616 |
+
"loss": 0.7836,
|
| 1617 |
+
"step": 2680
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 2.63,
|
| 1621 |
+
"learning_rate": 1.8834923770343544e-06,
|
| 1622 |
+
"loss": 0.7949,
|
| 1623 |
+
"step": 2690
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 2.64,
|
| 1627 |
+
"learning_rate": 1.787347988169613e-06,
|
| 1628 |
+
"loss": 0.8243,
|
| 1629 |
+
"step": 2700
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 2.65,
|
| 1633 |
+
"learning_rate": 1.6936312058432158e-06,
|
| 1634 |
+
"loss": 0.8798,
|
| 1635 |
+
"step": 2710
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.65,
|
| 1639 |
+
"learning_rate": 1.6023518310668618e-06,
|
| 1640 |
+
"loss": 0.9497,
|
| 1641 |
+
"step": 2720
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.66,
|
| 1645 |
+
"learning_rate": 1.5135194099452521e-06,
|
| 1646 |
+
"loss": 0.8978,
|
| 1647 |
+
"step": 2730
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 2.67,
|
| 1651 |
+
"learning_rate": 1.4271432326778273e-06,
|
| 1652 |
+
"loss": 0.8524,
|
| 1653 |
+
"step": 2740
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 2.68,
|
| 1657 |
+
"learning_rate": 1.3432323325871216e-06,
|
| 1658 |
+
"loss": 0.7888,
|
| 1659 |
+
"step": 2750
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 2.69,
|
| 1663 |
+
"learning_rate": 1.2617954851740832e-06,
|
| 1664 |
+
"loss": 0.8624,
|
| 1665 |
+
"step": 2760
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 2.7,
|
| 1669 |
+
"learning_rate": 1.1828412072003108e-06,
|
| 1670 |
+
"loss": 0.8722,
|
| 1671 |
+
"step": 2770
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 2.71,
|
| 1675 |
+
"learning_rate": 1.1063777557973638e-06,
|
| 1676 |
+
"loss": 0.8501,
|
| 1677 |
+
"step": 2780
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 2.72,
|
| 1681 |
+
"learning_rate": 1.0324131276032127e-06,
|
| 1682 |
+
"loss": 0.8302,
|
| 1683 |
+
"step": 2790
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.73,
|
| 1687 |
+
"learning_rate": 9.609550579259496e-07,
|
| 1688 |
+
"loss": 0.8424,
|
| 1689 |
+
"step": 2800
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.74,
|
| 1693 |
+
"learning_rate": 8.920110199348325e-07,
|
| 1694 |
+
"loss": 0.8208,
|
| 1695 |
+
"step": 2810
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 2.75,
|
| 1699 |
+
"learning_rate": 8.255882238786983e-07,
|
| 1700 |
+
"loss": 0.8773,
|
| 1701 |
+
"step": 2820
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 2.76,
|
| 1705 |
+
"learning_rate": 7.616936163319404e-07,
|
| 1706 |
+
"loss": 0.7867,
|
| 1707 |
+
"step": 2830
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 2.77,
|
| 1711 |
+
"learning_rate": 7.003338794680153e-07,
|
| 1712 |
+
"loss": 0.847,
|
| 1713 |
+
"step": 2840
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 2.78,
|
| 1717 |
+
"learning_rate": 6.415154303606036e-07,
|
| 1718 |
+
"loss": 0.8479,
|
| 1719 |
+
"step": 2850
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 2.79,
|
| 1723 |
+
"learning_rate": 5.852444203125223e-07,
|
| 1724 |
+
"loss": 0.8197,
|
| 1725 |
+
"step": 2860
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.8,
|
| 1729 |
+
"learning_rate": 5.315267342124008e-07,
|
| 1730 |
+
"loss": 0.8719,
|
| 1731 |
+
"step": 2870
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 2.81,
|
| 1735 |
+
"learning_rate": 4.803679899192392e-07,
|
| 1736 |
+
"loss": 0.922,
|
| 1737 |
+
"step": 2880
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 2.82,
|
| 1741 |
+
"learning_rate": 4.3177353767488163e-07,
|
| 1742 |
+
"loss": 0.8622,
|
| 1743 |
+
"step": 2890
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 2.83,
|
| 1747 |
+
"learning_rate": 3.8574845954448823e-07,
|
| 1748 |
+
"loss": 0.8361,
|
| 1749 |
+
"step": 2900
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 2.84,
|
| 1753 |
+
"learning_rate": 3.4229756888503604e-07,
|
| 1754 |
+
"loss": 0.9201,
|
| 1755 |
+
"step": 2910
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 2.85,
|
| 1759 |
+
"learning_rate": 3.014254098419406e-07,
|
| 1760 |
+
"loss": 0.834,
|
| 1761 |
+
"step": 2920
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 2.86,
|
| 1765 |
+
"learning_rate": 2.6313625687383046e-07,
|
| 1766 |
+
"loss": 0.8569,
|
| 1767 |
+
"step": 2930
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.87,
|
| 1771 |
+
"learning_rate": 2.2743411430549976e-07,
|
| 1772 |
+
"loss": 0.8411,
|
| 1773 |
+
"step": 2940
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 2.88,
|
| 1777 |
+
"learning_rate": 1.943227159091482e-07,
|
| 1778 |
+
"loss": 0.8648,
|
| 1779 |
+
"step": 2950
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 2.89,
|
| 1783 |
+
"learning_rate": 1.6380552451389086e-07,
|
| 1784 |
+
"loss": 0.8477,
|
| 1785 |
+
"step": 2960
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 2.9,
|
| 1789 |
+
"learning_rate": 1.3588573164361463e-07,
|
| 1790 |
+
"loss": 0.8449,
|
| 1791 |
+
"step": 2970
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 2.91,
|
| 1795 |
+
"learning_rate": 1.1056625718320334e-07,
|
| 1796 |
+
"loss": 0.8185,
|
| 1797 |
+
"step": 2980
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 2.92,
|
| 1801 |
+
"learning_rate": 8.784974907317111e-08,
|
| 1802 |
+
"loss": 0.8326,
|
| 1803 |
+
"step": 2990
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 2.93,
|
| 1807 |
+
"learning_rate": 6.773858303274483e-08,
|
| 1808 |
+
"loss": 0.84,
|
| 1809 |
+
"step": 3000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.94,
|
| 1813 |
+
"learning_rate": 5.0234862311399065e-08,
|
| 1814 |
+
"loss": 0.7393,
|
| 1815 |
+
"step": 3010
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 2.95,
|
| 1819 |
+
"learning_rate": 3.5340417468898714e-08,
|
| 1820 |
+
"loss": 0.8723,
|
| 1821 |
+
"step": 3020
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 2.96,
|
| 1825 |
+
"learning_rate": 2.3056806183865965e-08,
|
| 1826 |
+
"loss": 0.8481,
|
| 1827 |
+
"step": 3030
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 2.97,
|
| 1831 |
+
"learning_rate": 1.3385313090857887e-08,
|
| 1832 |
+
"loss": 0.8273,
|
| 1833 |
+
"step": 3040
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 2.98,
|
| 1837 |
+
"learning_rate": 6.326949646040525e-09,
|
| 1838 |
+
"loss": 0.899,
|
| 1839 |
+
"step": 3050
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 2.99,
|
| 1843 |
+
"learning_rate": 1.8824540213874255e-09,
|
| 1844 |
+
"loss": 0.8056,
|
| 1845 |
+
"step": 3060
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 3.0,
|
| 1849 |
+
"learning_rate": 5.229102749415571e-11,
|
| 1850 |
+
"loss": 0.8446,
|
| 1851 |
+
"step": 3070
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 3.0,
|
| 1855 |
+
"step": 3072,
|
| 1856 |
+
"total_flos": 1.125146154656809e+18,
|
| 1857 |
+
"train_loss": 0.862230001638333,
|
| 1858 |
+
"train_runtime": 23418.3393,
|
| 1859 |
+
"train_samples_per_second": 2.1,
|
| 1860 |
+
"train_steps_per_second": 0.131
|
| 1861 |
+
}
|
| 1862 |
+
],
|
| 1863 |
+
"logging_steps": 10,
|
| 1864 |
+
"max_steps": 3072,
|
| 1865 |
+
"num_train_epochs": 3,
|
| 1866 |
+
"save_steps": 1000,
|
| 1867 |
+
"total_flos": 1.125146154656809e+18,
|
| 1868 |
+
"trial_name": null,
|
| 1869 |
+
"trial_params": null
|
| 1870 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46cc0dbbd87649a5d53318624d851312ca1a239bb420ca253e818d53407397d5
|
| 3 |
+
size 4155
|
training_loss.png
ADDED
|