v.0.0.1
Browse files- config.json +32 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +14 -0
- trainer_state.json +2935 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "albert-base-v2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"AlbertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout_prob": 0.1,
|
| 9 |
+
"down_scale_factor": 1,
|
| 10 |
+
"embedding_size": 128,
|
| 11 |
+
"eos_token_id": 3,
|
| 12 |
+
"gap_size": 0,
|
| 13 |
+
"hidden_act": "gelu_new",
|
| 14 |
+
"hidden_dropout_prob": 0,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"inner_group_num": 1,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "albert",
|
| 22 |
+
"net_structure_type": 0,
|
| 23 |
+
"num_attention_heads": 12,
|
| 24 |
+
"num_hidden_groups": 1,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"num_memory_blocks": 0,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"transformers_version": "4.6.0.dev0",
|
| 30 |
+
"type_vocab_size": 2,
|
| 31 |
+
"vocab_size": 30000
|
| 32 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd7ae88f229a09a7c70c28efb87974eb57680f22780b1aa78ddb780b6c57c6b2
|
| 3 |
+
size 44903604
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
|
| 3 |
+
size 760289
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2"}
|
train_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"init_mem_cpu_alloc_delta": 2462601216,
|
| 4 |
+
"init_mem_cpu_peaked_delta": 0,
|
| 5 |
+
"init_mem_gpu_alloc_delta": 44891136,
|
| 6 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
+
"train_mem_cpu_alloc_delta": 47136768,
|
| 8 |
+
"train_mem_cpu_peaked_delta": 45445120,
|
| 9 |
+
"train_mem_gpu_alloc_delta": 137456128,
|
| 10 |
+
"train_mem_gpu_peaked_delta": 8017548800,
|
| 11 |
+
"train_runtime": 32291.4207,
|
| 12 |
+
"train_samples": 299542,
|
| 13 |
+
"train_samples_per_second": 3.479
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2935 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3685582876205444,
|
| 3 |
+
"best_model_checkpoint": "clinic_albert_v3/checkpoint-104500",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 112329,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 2.4500000000000003e-06,
|
| 13 |
+
"loss": 6.2872,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"eval_loss": 3.8396031856536865,
|
| 19 |
+
"eval_runtime": 92.2647,
|
| 20 |
+
"eval_samples_per_second": 161.806,
|
| 21 |
+
"step": 500
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 4.950000000000001e-06,
|
| 26 |
+
"loss": 3.6553,
|
| 27 |
+
"step": 1000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"eval_loss": 3.5483450889587402,
|
| 32 |
+
"eval_runtime": 91.9838,
|
| 33 |
+
"eval_samples_per_second": 162.3,
|
| 34 |
+
"step": 1000
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.04,
|
| 38 |
+
"learning_rate": 7.45e-06,
|
| 39 |
+
"loss": 3.4131,
|
| 40 |
+
"step": 1500
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.04,
|
| 44 |
+
"eval_loss": 3.3662946224212646,
|
| 45 |
+
"eval_runtime": 91.5787,
|
| 46 |
+
"eval_samples_per_second": 163.018,
|
| 47 |
+
"step": 1500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.05,
|
| 51 |
+
"learning_rate": 9.950000000000001e-06,
|
| 52 |
+
"loss": 3.2051,
|
| 53 |
+
"step": 2000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.05,
|
| 57 |
+
"eval_loss": 3.199434995651245,
|
| 58 |
+
"eval_runtime": 91.5904,
|
| 59 |
+
"eval_samples_per_second": 162.997,
|
| 60 |
+
"step": 2000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.07,
|
| 64 |
+
"learning_rate": 1.2450000000000001e-05,
|
| 65 |
+
"loss": 3.1553,
|
| 66 |
+
"step": 2500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.07,
|
| 70 |
+
"eval_loss": 3.091717004776001,
|
| 71 |
+
"eval_runtime": 91.2768,
|
| 72 |
+
"eval_samples_per_second": 163.557,
|
| 73 |
+
"step": 2500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.08,
|
| 77 |
+
"learning_rate": 1.4950000000000001e-05,
|
| 78 |
+
"loss": 3.0703,
|
| 79 |
+
"step": 3000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08,
|
| 83 |
+
"eval_loss": 2.9730803966522217,
|
| 84 |
+
"eval_runtime": 91.2688,
|
| 85 |
+
"eval_samples_per_second": 163.572,
|
| 86 |
+
"step": 3000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.09,
|
| 90 |
+
"learning_rate": 1.745e-05,
|
| 91 |
+
"loss": 2.9258,
|
| 92 |
+
"step": 3500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.09,
|
| 96 |
+
"eval_loss": 2.930089235305786,
|
| 97 |
+
"eval_runtime": 91.4358,
|
| 98 |
+
"eval_samples_per_second": 163.273,
|
| 99 |
+
"step": 3500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.11,
|
| 103 |
+
"learning_rate": 1.995e-05,
|
| 104 |
+
"loss": 2.8627,
|
| 105 |
+
"step": 4000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.11,
|
| 109 |
+
"eval_loss": 2.842494249343872,
|
| 110 |
+
"eval_runtime": 91.5055,
|
| 111 |
+
"eval_samples_per_second": 163.149,
|
| 112 |
+
"step": 4000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.12,
|
| 116 |
+
"learning_rate": 2.245e-05,
|
| 117 |
+
"loss": 2.797,
|
| 118 |
+
"step": 4500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.12,
|
| 122 |
+
"eval_loss": 2.8484582901000977,
|
| 123 |
+
"eval_runtime": 91.4864,
|
| 124 |
+
"eval_samples_per_second": 163.183,
|
| 125 |
+
"step": 4500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.13,
|
| 129 |
+
"learning_rate": 2.495e-05,
|
| 130 |
+
"loss": 2.7408,
|
| 131 |
+
"step": 5000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.13,
|
| 135 |
+
"eval_loss": 2.784637928009033,
|
| 136 |
+
"eval_runtime": 91.3143,
|
| 137 |
+
"eval_samples_per_second": 163.49,
|
| 138 |
+
"step": 5000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.15,
|
| 142 |
+
"learning_rate": 2.7450000000000003e-05,
|
| 143 |
+
"loss": 2.7552,
|
| 144 |
+
"step": 5500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.15,
|
| 148 |
+
"eval_loss": 2.731156349182129,
|
| 149 |
+
"eval_runtime": 91.2004,
|
| 150 |
+
"eval_samples_per_second": 163.694,
|
| 151 |
+
"step": 5500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.16,
|
| 155 |
+
"learning_rate": 2.995e-05,
|
| 156 |
+
"loss": 2.7098,
|
| 157 |
+
"step": 6000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.16,
|
| 161 |
+
"eval_loss": 2.677649736404419,
|
| 162 |
+
"eval_runtime": 91.2243,
|
| 163 |
+
"eval_samples_per_second": 163.652,
|
| 164 |
+
"step": 6000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.17,
|
| 168 |
+
"learning_rate": 3.245e-05,
|
| 169 |
+
"loss": 2.7015,
|
| 170 |
+
"step": 6500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.17,
|
| 174 |
+
"eval_loss": 2.7468419075012207,
|
| 175 |
+
"eval_runtime": 91.3379,
|
| 176 |
+
"eval_samples_per_second": 163.448,
|
| 177 |
+
"step": 6500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.19,
|
| 181 |
+
"learning_rate": 3.495e-05,
|
| 182 |
+
"loss": 2.6226,
|
| 183 |
+
"step": 7000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.19,
|
| 187 |
+
"eval_loss": 2.6828126907348633,
|
| 188 |
+
"eval_runtime": 91.2062,
|
| 189 |
+
"eval_samples_per_second": 163.684,
|
| 190 |
+
"step": 7000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.2,
|
| 194 |
+
"learning_rate": 3.745e-05,
|
| 195 |
+
"loss": 2.6738,
|
| 196 |
+
"step": 7500
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.2,
|
| 200 |
+
"eval_loss": 2.622964382171631,
|
| 201 |
+
"eval_runtime": 91.2339,
|
| 202 |
+
"eval_samples_per_second": 163.634,
|
| 203 |
+
"step": 7500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.21,
|
| 207 |
+
"learning_rate": 3.995e-05,
|
| 208 |
+
"loss": 2.6507,
|
| 209 |
+
"step": 8000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.21,
|
| 213 |
+
"eval_loss": 2.6091177463531494,
|
| 214 |
+
"eval_runtime": 91.1569,
|
| 215 |
+
"eval_samples_per_second": 163.773,
|
| 216 |
+
"step": 8000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.23,
|
| 220 |
+
"learning_rate": 4.245e-05,
|
| 221 |
+
"loss": 2.6198,
|
| 222 |
+
"step": 8500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.23,
|
| 226 |
+
"eval_loss": 2.598926067352295,
|
| 227 |
+
"eval_runtime": 91.2361,
|
| 228 |
+
"eval_samples_per_second": 163.63,
|
| 229 |
+
"step": 8500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.24,
|
| 233 |
+
"learning_rate": 4.495e-05,
|
| 234 |
+
"loss": 2.5921,
|
| 235 |
+
"step": 9000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.24,
|
| 239 |
+
"eval_loss": 2.59818959236145,
|
| 240 |
+
"eval_runtime": 91.1835,
|
| 241 |
+
"eval_samples_per_second": 163.725,
|
| 242 |
+
"step": 9000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.25,
|
| 246 |
+
"learning_rate": 4.745e-05,
|
| 247 |
+
"loss": 2.5966,
|
| 248 |
+
"step": 9500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.25,
|
| 252 |
+
"eval_loss": 2.5808210372924805,
|
| 253 |
+
"eval_runtime": 91.3208,
|
| 254 |
+
"eval_samples_per_second": 163.479,
|
| 255 |
+
"step": 9500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.27,
|
| 259 |
+
"learning_rate": 4.995e-05,
|
| 260 |
+
"loss": 2.5369,
|
| 261 |
+
"step": 10000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.27,
|
| 265 |
+
"eval_loss": 2.5975215435028076,
|
| 266 |
+
"eval_runtime": 91.1933,
|
| 267 |
+
"eval_samples_per_second": 163.707,
|
| 268 |
+
"step": 10000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.28,
|
| 272 |
+
"learning_rate": 4.9760576180750326e-05,
|
| 273 |
+
"loss": 2.5351,
|
| 274 |
+
"step": 10500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.28,
|
| 278 |
+
"eval_loss": 2.507310152053833,
|
| 279 |
+
"eval_runtime": 91.2579,
|
| 280 |
+
"eval_samples_per_second": 163.591,
|
| 281 |
+
"step": 10500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.29,
|
| 285 |
+
"learning_rate": 4.9516754781147087e-05,
|
| 286 |
+
"loss": 2.469,
|
| 287 |
+
"step": 11000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.29,
|
| 291 |
+
"eval_loss": 2.5691452026367188,
|
| 292 |
+
"eval_runtime": 91.4338,
|
| 293 |
+
"eval_samples_per_second": 163.277,
|
| 294 |
+
"step": 11000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.31,
|
| 298 |
+
"learning_rate": 4.927244476150456e-05,
|
| 299 |
+
"loss": 2.5135,
|
| 300 |
+
"step": 11500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.31,
|
| 304 |
+
"eval_loss": 2.534702777862549,
|
| 305 |
+
"eval_runtime": 91.54,
|
| 306 |
+
"eval_samples_per_second": 163.087,
|
| 307 |
+
"step": 11500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.32,
|
| 311 |
+
"learning_rate": 4.9028134741862035e-05,
|
| 312 |
+
"loss": 2.4175,
|
| 313 |
+
"step": 12000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.32,
|
| 317 |
+
"eval_loss": 2.506258726119995,
|
| 318 |
+
"eval_runtime": 91.2029,
|
| 319 |
+
"eval_samples_per_second": 163.69,
|
| 320 |
+
"step": 12000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.33,
|
| 324 |
+
"learning_rate": 4.878382472221951e-05,
|
| 325 |
+
"loss": 2.4601,
|
| 326 |
+
"step": 12500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.33,
|
| 330 |
+
"eval_loss": 2.417022228240967,
|
| 331 |
+
"eval_runtime": 91.3123,
|
| 332 |
+
"eval_samples_per_second": 163.494,
|
| 333 |
+
"step": 12500
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.35,
|
| 337 |
+
"learning_rate": 4.8539514702576984e-05,
|
| 338 |
+
"loss": 2.3867,
|
| 339 |
+
"step": 13000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.35,
|
| 343 |
+
"eval_loss": 2.41973614692688,
|
| 344 |
+
"eval_runtime": 91.3867,
|
| 345 |
+
"eval_samples_per_second": 163.361,
|
| 346 |
+
"step": 13000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.36,
|
| 350 |
+
"learning_rate": 4.829520468293446e-05,
|
| 351 |
+
"loss": 2.3704,
|
| 352 |
+
"step": 13500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.36,
|
| 356 |
+
"eval_loss": 2.3954126834869385,
|
| 357 |
+
"eval_runtime": 91.334,
|
| 358 |
+
"eval_samples_per_second": 163.455,
|
| 359 |
+
"step": 13500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.37,
|
| 363 |
+
"learning_rate": 4.805089466329193e-05,
|
| 364 |
+
"loss": 2.3152,
|
| 365 |
+
"step": 14000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.37,
|
| 369 |
+
"eval_loss": 2.3748397827148438,
|
| 370 |
+
"eval_runtime": 91.307,
|
| 371 |
+
"eval_samples_per_second": 163.503,
|
| 372 |
+
"step": 14000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.39,
|
| 376 |
+
"learning_rate": 4.7806584643649414e-05,
|
| 377 |
+
"loss": 2.3504,
|
| 378 |
+
"step": 14500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.39,
|
| 382 |
+
"eval_loss": 2.3295907974243164,
|
| 383 |
+
"eval_runtime": 91.2388,
|
| 384 |
+
"eval_samples_per_second": 163.626,
|
| 385 |
+
"step": 14500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.4,
|
| 389 |
+
"learning_rate": 4.756227462400688e-05,
|
| 390 |
+
"loss": 2.325,
|
| 391 |
+
"step": 15000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.4,
|
| 395 |
+
"eval_loss": 2.315340518951416,
|
| 396 |
+
"eval_runtime": 91.4211,
|
| 397 |
+
"eval_samples_per_second": 163.299,
|
| 398 |
+
"step": 15000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.41,
|
| 402 |
+
"learning_rate": 4.7317964604364355e-05,
|
| 403 |
+
"loss": 2.2768,
|
| 404 |
+
"step": 15500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.41,
|
| 408 |
+
"eval_loss": 2.323646306991577,
|
| 409 |
+
"eval_runtime": 91.2326,
|
| 410 |
+
"eval_samples_per_second": 163.637,
|
| 411 |
+
"step": 15500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.43,
|
| 415 |
+
"learning_rate": 4.707365458472183e-05,
|
| 416 |
+
"loss": 2.2752,
|
| 417 |
+
"step": 16000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.43,
|
| 421 |
+
"eval_loss": 2.286576747894287,
|
| 422 |
+
"eval_runtime": 91.2898,
|
| 423 |
+
"eval_samples_per_second": 163.534,
|
| 424 |
+
"step": 16000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.44,
|
| 428 |
+
"learning_rate": 4.6829344565079304e-05,
|
| 429 |
+
"loss": 2.2439,
|
| 430 |
+
"step": 16500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.44,
|
| 434 |
+
"eval_loss": 2.2795145511627197,
|
| 435 |
+
"eval_runtime": 91.3133,
|
| 436 |
+
"eval_samples_per_second": 163.492,
|
| 437 |
+
"step": 16500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.45,
|
| 441 |
+
"learning_rate": 4.6585523165476065e-05,
|
| 442 |
+
"loss": 2.2255,
|
| 443 |
+
"step": 17000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.45,
|
| 447 |
+
"eval_loss": 2.226459503173828,
|
| 448 |
+
"eval_runtime": 91.4081,
|
| 449 |
+
"eval_samples_per_second": 163.323,
|
| 450 |
+
"step": 17000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.47,
|
| 454 |
+
"learning_rate": 4.634121314583354e-05,
|
| 455 |
+
"loss": 2.177,
|
| 456 |
+
"step": 17500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.47,
|
| 460 |
+
"eval_loss": 2.252764940261841,
|
| 461 |
+
"eval_runtime": 91.6167,
|
| 462 |
+
"eval_samples_per_second": 162.951,
|
| 463 |
+
"step": 17500
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.48,
|
| 467 |
+
"learning_rate": 4.60973917462303e-05,
|
| 468 |
+
"loss": 2.2602,
|
| 469 |
+
"step": 18000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.48,
|
| 473 |
+
"eval_loss": 2.2427968978881836,
|
| 474 |
+
"eval_runtime": 91.3698,
|
| 475 |
+
"eval_samples_per_second": 163.391,
|
| 476 |
+
"step": 18000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.49,
|
| 480 |
+
"learning_rate": 4.585405896666634e-05,
|
| 481 |
+
"loss": 2.2382,
|
| 482 |
+
"step": 18500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.49,
|
| 486 |
+
"eval_loss": 2.175690174102783,
|
| 487 |
+
"eval_runtime": 91.3659,
|
| 488 |
+
"eval_samples_per_second": 163.398,
|
| 489 |
+
"step": 18500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.51,
|
| 493 |
+
"learning_rate": 4.5609748947023814e-05,
|
| 494 |
+
"loss": 2.1481,
|
| 495 |
+
"step": 19000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.51,
|
| 499 |
+
"eval_loss": 2.1878654956817627,
|
| 500 |
+
"eval_runtime": 91.3436,
|
| 501 |
+
"eval_samples_per_second": 163.438,
|
| 502 |
+
"step": 19000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.52,
|
| 506 |
+
"learning_rate": 4.5365438927381295e-05,
|
| 507 |
+
"loss": 2.0507,
|
| 508 |
+
"step": 19500
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.52,
|
| 512 |
+
"eval_loss": 2.210096597671509,
|
| 513 |
+
"eval_runtime": 91.3869,
|
| 514 |
+
"eval_samples_per_second": 163.36,
|
| 515 |
+
"step": 19500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.53,
|
| 519 |
+
"learning_rate": 4.512112890773877e-05,
|
| 520 |
+
"loss": 2.1267,
|
| 521 |
+
"step": 20000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.53,
|
| 525 |
+
"eval_loss": 2.1687960624694824,
|
| 526 |
+
"eval_runtime": 91.1987,
|
| 527 |
+
"eval_samples_per_second": 163.697,
|
| 528 |
+
"step": 20000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.55,
|
| 532 |
+
"learning_rate": 4.487681888809624e-05,
|
| 533 |
+
"loss": 2.1605,
|
| 534 |
+
"step": 20500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.55,
|
| 538 |
+
"eval_loss": 2.1389825344085693,
|
| 539 |
+
"eval_runtime": 91.269,
|
| 540 |
+
"eval_samples_per_second": 163.571,
|
| 541 |
+
"step": 20500
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.56,
|
| 545 |
+
"learning_rate": 4.463250886845372e-05,
|
| 546 |
+
"loss": 2.0474,
|
| 547 |
+
"step": 21000
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.56,
|
| 551 |
+
"eval_loss": 2.107516288757324,
|
| 552 |
+
"eval_runtime": 91.2438,
|
| 553 |
+
"eval_samples_per_second": 163.617,
|
| 554 |
+
"step": 21000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.57,
|
| 558 |
+
"learning_rate": 4.438819884881119e-05,
|
| 559 |
+
"loss": 2.1403,
|
| 560 |
+
"step": 21500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.57,
|
| 564 |
+
"eval_loss": 2.117351531982422,
|
| 565 |
+
"eval_runtime": 91.3836,
|
| 566 |
+
"eval_samples_per_second": 163.366,
|
| 567 |
+
"step": 21500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.59,
|
| 571 |
+
"learning_rate": 4.414388882916866e-05,
|
| 572 |
+
"loss": 2.1505,
|
| 573 |
+
"step": 22000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.59,
|
| 577 |
+
"eval_loss": 2.103529214859009,
|
| 578 |
+
"eval_runtime": 91.397,
|
| 579 |
+
"eval_samples_per_second": 163.342,
|
| 580 |
+
"step": 22000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.6,
|
| 584 |
+
"learning_rate": 4.3899578809526134e-05,
|
| 585 |
+
"loss": 2.0463,
|
| 586 |
+
"step": 22500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.6,
|
| 590 |
+
"eval_loss": 2.076082229614258,
|
| 591 |
+
"eval_runtime": 91.3284,
|
| 592 |
+
"eval_samples_per_second": 163.465,
|
| 593 |
+
"step": 22500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.61,
|
| 597 |
+
"learning_rate": 4.3655268789883615e-05,
|
| 598 |
+
"loss": 2.0312,
|
| 599 |
+
"step": 23000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.61,
|
| 603 |
+
"eval_loss": 2.098130702972412,
|
| 604 |
+
"eval_runtime": 91.4521,
|
| 605 |
+
"eval_samples_per_second": 163.244,
|
| 606 |
+
"step": 23000
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.63,
|
| 610 |
+
"learning_rate": 4.341095877024109e-05,
|
| 611 |
+
"loss": 2.0562,
|
| 612 |
+
"step": 23500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.63,
|
| 616 |
+
"eval_loss": 2.0372567176818848,
|
| 617 |
+
"eval_runtime": 91.2845,
|
| 618 |
+
"eval_samples_per_second": 163.544,
|
| 619 |
+
"step": 23500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.64,
|
| 623 |
+
"learning_rate": 4.316664875059856e-05,
|
| 624 |
+
"loss": 2.0185,
|
| 625 |
+
"step": 24000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.64,
|
| 629 |
+
"eval_loss": 2.0775225162506104,
|
| 630 |
+
"eval_runtime": 91.1456,
|
| 631 |
+
"eval_samples_per_second": 163.793,
|
| 632 |
+
"step": 24000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.65,
|
| 636 |
+
"learning_rate": 4.292233873095604e-05,
|
| 637 |
+
"loss": 2.012,
|
| 638 |
+
"step": 24500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.65,
|
| 642 |
+
"eval_loss": 2.040658712387085,
|
| 643 |
+
"eval_runtime": 91.1946,
|
| 644 |
+
"eval_samples_per_second": 163.705,
|
| 645 |
+
"step": 24500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.67,
|
| 649 |
+
"learning_rate": 4.267802871131351e-05,
|
| 650 |
+
"loss": 2.0448,
|
| 651 |
+
"step": 25000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.67,
|
| 655 |
+
"eval_loss": 2.0319766998291016,
|
| 656 |
+
"eval_runtime": 91.2535,
|
| 657 |
+
"eval_samples_per_second": 163.599,
|
| 658 |
+
"step": 25000
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.68,
|
| 662 |
+
"learning_rate": 4.2433718691670987e-05,
|
| 663 |
+
"loss": 1.9511,
|
| 664 |
+
"step": 25500
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.68,
|
| 668 |
+
"eval_loss": 2.034172534942627,
|
| 669 |
+
"eval_runtime": 91.3903,
|
| 670 |
+
"eval_samples_per_second": 163.354,
|
| 671 |
+
"step": 25500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.69,
|
| 675 |
+
"learning_rate": 4.218940867202846e-05,
|
| 676 |
+
"loss": 1.9424,
|
| 677 |
+
"step": 26000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.69,
|
| 681 |
+
"eval_loss": 2.0328168869018555,
|
| 682 |
+
"eval_runtime": 91.2635,
|
| 683 |
+
"eval_samples_per_second": 163.581,
|
| 684 |
+
"step": 26000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.71,
|
| 688 |
+
"learning_rate": 4.1945098652385935e-05,
|
| 689 |
+
"loss": 1.9533,
|
| 690 |
+
"step": 26500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.71,
|
| 694 |
+
"eval_loss": 1.9927563667297363,
|
| 695 |
+
"eval_runtime": 91.4616,
|
| 696 |
+
"eval_samples_per_second": 163.227,
|
| 697 |
+
"step": 26500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.72,
|
| 701 |
+
"learning_rate": 4.170078863274341e-05,
|
| 702 |
+
"loss": 1.9538,
|
| 703 |
+
"step": 27000
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.72,
|
| 707 |
+
"eval_loss": 2.0190131664276123,
|
| 708 |
+
"eval_runtime": 91.2642,
|
| 709 |
+
"eval_samples_per_second": 163.58,
|
| 710 |
+
"step": 27000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.73,
|
| 714 |
+
"learning_rate": 4.145647861310088e-05,
|
| 715 |
+
"loss": 1.9778,
|
| 716 |
+
"step": 27500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.73,
|
| 720 |
+
"eval_loss": 2.007988929748535,
|
| 721 |
+
"eval_runtime": 91.4801,
|
| 722 |
+
"eval_samples_per_second": 163.194,
|
| 723 |
+
"step": 27500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.75,
|
| 727 |
+
"learning_rate": 4.121216859345836e-05,
|
| 728 |
+
"loss": 1.9567,
|
| 729 |
+
"step": 28000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.75,
|
| 733 |
+
"eval_loss": 2.0140700340270996,
|
| 734 |
+
"eval_runtime": 91.3767,
|
| 735 |
+
"eval_samples_per_second": 163.379,
|
| 736 |
+
"step": 28000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.76,
|
| 740 |
+
"learning_rate": 4.096834719385512e-05,
|
| 741 |
+
"loss": 1.9589,
|
| 742 |
+
"step": 28500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.76,
|
| 746 |
+
"eval_loss": 1.9930866956710815,
|
| 747 |
+
"eval_runtime": 91.1168,
|
| 748 |
+
"eval_samples_per_second": 163.845,
|
| 749 |
+
"step": 28500
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.77,
|
| 753 |
+
"learning_rate": 4.072403717421259e-05,
|
| 754 |
+
"loss": 1.9605,
|
| 755 |
+
"step": 29000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.77,
|
| 759 |
+
"eval_loss": 1.9426169395446777,
|
| 760 |
+
"eval_runtime": 91.226,
|
| 761 |
+
"eval_samples_per_second": 163.648,
|
| 762 |
+
"step": 29000
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.79,
|
| 766 |
+
"learning_rate": 4.047972715457006e-05,
|
| 767 |
+
"loss": 1.9552,
|
| 768 |
+
"step": 29500
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.79,
|
| 772 |
+
"eval_loss": 1.9635326862335205,
|
| 773 |
+
"eval_runtime": 91.3172,
|
| 774 |
+
"eval_samples_per_second": 163.485,
|
| 775 |
+
"step": 29500
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.8,
|
| 779 |
+
"learning_rate": 4.023590575496682e-05,
|
| 780 |
+
"loss": 1.9112,
|
| 781 |
+
"step": 30000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.8,
|
| 785 |
+
"eval_loss": 1.9517323970794678,
|
| 786 |
+
"eval_runtime": 91.4036,
|
| 787 |
+
"eval_samples_per_second": 163.331,
|
| 788 |
+
"step": 30000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.81,
|
| 792 |
+
"learning_rate": 3.99915957353243e-05,
|
| 793 |
+
"loss": 1.8632,
|
| 794 |
+
"step": 30500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.81,
|
| 798 |
+
"eval_loss": 1.945887565612793,
|
| 799 |
+
"eval_runtime": 91.1301,
|
| 800 |
+
"eval_samples_per_second": 163.821,
|
| 801 |
+
"step": 30500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.83,
|
| 805 |
+
"learning_rate": 3.9747285715681777e-05,
|
| 806 |
+
"loss": 1.8776,
|
| 807 |
+
"step": 31000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.83,
|
| 811 |
+
"eval_loss": 1.9599124193191528,
|
| 812 |
+
"eval_runtime": 91.3256,
|
| 813 |
+
"eval_samples_per_second": 163.47,
|
| 814 |
+
"step": 31000
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.84,
|
| 818 |
+
"learning_rate": 3.9502975696039244e-05,
|
| 819 |
+
"loss": 1.8564,
|
| 820 |
+
"step": 31500
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.84,
|
| 824 |
+
"eval_loss": 1.93245530128479,
|
| 825 |
+
"eval_runtime": 91.4657,
|
| 826 |
+
"eval_samples_per_second": 163.22,
|
| 827 |
+
"step": 31500
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.85,
|
| 831 |
+
"learning_rate": 3.9259154296436005e-05,
|
| 832 |
+
"loss": 1.8988,
|
| 833 |
+
"step": 32000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.85,
|
| 837 |
+
"eval_loss": 1.9134759902954102,
|
| 838 |
+
"eval_runtime": 91.4228,
|
| 839 |
+
"eval_samples_per_second": 163.296,
|
| 840 |
+
"step": 32000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.87,
|
| 844 |
+
"learning_rate": 3.9014844276793486e-05,
|
| 845 |
+
"loss": 1.8924,
|
| 846 |
+
"step": 32500
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.87,
|
| 850 |
+
"eval_loss": 1.9036946296691895,
|
| 851 |
+
"eval_runtime": 91.2342,
|
| 852 |
+
"eval_samples_per_second": 163.634,
|
| 853 |
+
"step": 32500
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 0.88,
|
| 857 |
+
"learning_rate": 3.8771022877190246e-05,
|
| 858 |
+
"loss": 1.8543,
|
| 859 |
+
"step": 33000
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.88,
|
| 863 |
+
"eval_loss": 1.8894397020339966,
|
| 864 |
+
"eval_runtime": 91.3605,
|
| 865 |
+
"eval_samples_per_second": 163.408,
|
| 866 |
+
"step": 33000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.89,
|
| 870 |
+
"learning_rate": 3.8526712857547714e-05,
|
| 871 |
+
"loss": 1.8546,
|
| 872 |
+
"step": 33500
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.89,
|
| 876 |
+
"eval_loss": 1.8986772298812866,
|
| 877 |
+
"eval_runtime": 91.4907,
|
| 878 |
+
"eval_samples_per_second": 163.175,
|
| 879 |
+
"step": 33500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.91,
|
| 883 |
+
"learning_rate": 3.828240283790519e-05,
|
| 884 |
+
"loss": 1.7711,
|
| 885 |
+
"step": 34000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.91,
|
| 889 |
+
"eval_loss": 1.9133729934692383,
|
| 890 |
+
"eval_runtime": 91.4658,
|
| 891 |
+
"eval_samples_per_second": 163.219,
|
| 892 |
+
"step": 34000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.92,
|
| 896 |
+
"learning_rate": 3.803809281826267e-05,
|
| 897 |
+
"loss": 1.8173,
|
| 898 |
+
"step": 34500
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.92,
|
| 902 |
+
"eval_loss": 1.8876162767410278,
|
| 903 |
+
"eval_runtime": 91.3085,
|
| 904 |
+
"eval_samples_per_second": 163.501,
|
| 905 |
+
"step": 34500
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.93,
|
| 909 |
+
"learning_rate": 3.779378279862014e-05,
|
| 910 |
+
"loss": 1.8667,
|
| 911 |
+
"step": 35000
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.93,
|
| 915 |
+
"eval_loss": 1.8843164443969727,
|
| 916 |
+
"eval_runtime": 91.1747,
|
| 917 |
+
"eval_samples_per_second": 163.741,
|
| 918 |
+
"step": 35000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.95,
|
| 922 |
+
"learning_rate": 3.75499613990169e-05,
|
| 923 |
+
"loss": 1.7971,
|
| 924 |
+
"step": 35500
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.95,
|
| 928 |
+
"eval_loss": 1.8736356496810913,
|
| 929 |
+
"eval_runtime": 91.3988,
|
| 930 |
+
"eval_samples_per_second": 163.339,
|
| 931 |
+
"step": 35500
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 0.96,
|
| 935 |
+
"learning_rate": 3.730565137937437e-05,
|
| 936 |
+
"loss": 1.8363,
|
| 937 |
+
"step": 36000
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.96,
|
| 941 |
+
"eval_loss": 1.8734278678894043,
|
| 942 |
+
"eval_runtime": 91.4136,
|
| 943 |
+
"eval_samples_per_second": 163.313,
|
| 944 |
+
"step": 36000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.97,
|
| 948 |
+
"learning_rate": 3.7061341359731846e-05,
|
| 949 |
+
"loss": 1.9108,
|
| 950 |
+
"step": 36500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.97,
|
| 954 |
+
"eval_loss": 1.8428773880004883,
|
| 955 |
+
"eval_runtime": 91.3304,
|
| 956 |
+
"eval_samples_per_second": 163.461,
|
| 957 |
+
"step": 36500
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.99,
|
| 961 |
+
"learning_rate": 3.681703134008932e-05,
|
| 962 |
+
"loss": 1.7966,
|
| 963 |
+
"step": 37000
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.99,
|
| 967 |
+
"eval_loss": 1.863236427307129,
|
| 968 |
+
"eval_runtime": 91.3214,
|
| 969 |
+
"eval_samples_per_second": 163.478,
|
| 970 |
+
"step": 37000
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.0,
|
| 974 |
+
"learning_rate": 3.6572721320446795e-05,
|
| 975 |
+
"loss": 1.8191,
|
| 976 |
+
"step": 37500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.0,
|
| 980 |
+
"eval_loss": 1.826414704322815,
|
| 981 |
+
"eval_runtime": 91.3739,
|
| 982 |
+
"eval_samples_per_second": 163.384,
|
| 983 |
+
"step": 37500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.01,
|
| 987 |
+
"learning_rate": 3.632841130080427e-05,
|
| 988 |
+
"loss": 1.7991,
|
| 989 |
+
"step": 38000
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.01,
|
| 993 |
+
"eval_loss": 1.831282615661621,
|
| 994 |
+
"eval_runtime": 91.5324,
|
| 995 |
+
"eval_samples_per_second": 163.101,
|
| 996 |
+
"step": 38000
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.03,
|
| 1000 |
+
"learning_rate": 3.608410128116175e-05,
|
| 1001 |
+
"loss": 1.7797,
|
| 1002 |
+
"step": 38500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.03,
|
| 1006 |
+
"eval_loss": 1.8110054731369019,
|
| 1007 |
+
"eval_runtime": 91.6401,
|
| 1008 |
+
"eval_samples_per_second": 162.909,
|
| 1009 |
+
"step": 38500
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.04,
|
| 1013 |
+
"learning_rate": 3.583979126151922e-05,
|
| 1014 |
+
"loss": 1.7492,
|
| 1015 |
+
"step": 39000
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.04,
|
| 1019 |
+
"eval_loss": 1.827107548713684,
|
| 1020 |
+
"eval_runtime": 91.1498,
|
| 1021 |
+
"eval_samples_per_second": 163.785,
|
| 1022 |
+
"step": 39000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 1.05,
|
| 1026 |
+
"learning_rate": 3.559596986191598e-05,
|
| 1027 |
+
"loss": 1.7541,
|
| 1028 |
+
"step": 39500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.05,
|
| 1032 |
+
"eval_loss": 1.8055846691131592,
|
| 1033 |
+
"eval_runtime": 91.4418,
|
| 1034 |
+
"eval_samples_per_second": 163.262,
|
| 1035 |
+
"step": 39500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 1.07,
|
| 1039 |
+
"learning_rate": 3.535165984227345e-05,
|
| 1040 |
+
"loss": 1.7882,
|
| 1041 |
+
"step": 40000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 1.07,
|
| 1045 |
+
"eval_loss": 1.8122904300689697,
|
| 1046 |
+
"eval_runtime": 91.6628,
|
| 1047 |
+
"eval_samples_per_second": 162.869,
|
| 1048 |
+
"step": 40000
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.08,
|
| 1052 |
+
"learning_rate": 3.510734982263093e-05,
|
| 1053 |
+
"loss": 1.7544,
|
| 1054 |
+
"step": 40500
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.08,
|
| 1058 |
+
"eval_loss": 1.8098782300949097,
|
| 1059 |
+
"eval_runtime": 91.4346,
|
| 1060 |
+
"eval_samples_per_second": 163.275,
|
| 1061 |
+
"step": 40500
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 1.09,
|
| 1065 |
+
"learning_rate": 3.48630398029884e-05,
|
| 1066 |
+
"loss": 1.7338,
|
| 1067 |
+
"step": 41000
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.09,
|
| 1071 |
+
"eval_loss": 1.7867393493652344,
|
| 1072 |
+
"eval_runtime": 91.3421,
|
| 1073 |
+
"eval_samples_per_second": 163.44,
|
| 1074 |
+
"step": 41000
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.11,
|
| 1078 |
+
"learning_rate": 3.4618729783345875e-05,
|
| 1079 |
+
"loss": 1.7529,
|
| 1080 |
+
"step": 41500
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.11,
|
| 1084 |
+
"eval_loss": 1.7708940505981445,
|
| 1085 |
+
"eval_runtime": 91.2573,
|
| 1086 |
+
"eval_samples_per_second": 163.592,
|
| 1087 |
+
"step": 41500
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.12,
|
| 1091 |
+
"learning_rate": 3.437441976370335e-05,
|
| 1092 |
+
"loss": 1.7782,
|
| 1093 |
+
"step": 42000
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.12,
|
| 1097 |
+
"eval_loss": 1.7782670259475708,
|
| 1098 |
+
"eval_runtime": 91.5943,
|
| 1099 |
+
"eval_samples_per_second": 162.99,
|
| 1100 |
+
"step": 42000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.14,
|
| 1104 |
+
"learning_rate": 3.4130109744060824e-05,
|
| 1105 |
+
"loss": 1.7018,
|
| 1106 |
+
"step": 42500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.14,
|
| 1110 |
+
"eval_loss": 1.8046059608459473,
|
| 1111 |
+
"eval_runtime": 91.4265,
|
| 1112 |
+
"eval_samples_per_second": 163.29,
|
| 1113 |
+
"step": 42500
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 1.15,
|
| 1117 |
+
"learning_rate": 3.38857997244183e-05,
|
| 1118 |
+
"loss": 1.6726,
|
| 1119 |
+
"step": 43000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.15,
|
| 1123 |
+
"eval_loss": 1.7743386030197144,
|
| 1124 |
+
"eval_runtime": 91.4777,
|
| 1125 |
+
"eval_samples_per_second": 163.198,
|
| 1126 |
+
"step": 43000
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.16,
|
| 1130 |
+
"learning_rate": 3.364148970477577e-05,
|
| 1131 |
+
"loss": 1.6964,
|
| 1132 |
+
"step": 43500
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 1.16,
|
| 1136 |
+
"eval_loss": 1.781007170677185,
|
| 1137 |
+
"eval_runtime": 91.4397,
|
| 1138 |
+
"eval_samples_per_second": 163.266,
|
| 1139 |
+
"step": 43500
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.18,
|
| 1143 |
+
"learning_rate": 3.3397179685133254e-05,
|
| 1144 |
+
"loss": 1.7196,
|
| 1145 |
+
"step": 44000
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.18,
|
| 1149 |
+
"eval_loss": 1.7817639112472534,
|
| 1150 |
+
"eval_runtime": 91.6102,
|
| 1151 |
+
"eval_samples_per_second": 162.962,
|
| 1152 |
+
"step": 44000
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 1.19,
|
| 1156 |
+
"learning_rate": 3.315286966549072e-05,
|
| 1157 |
+
"loss": 1.7085,
|
| 1158 |
+
"step": 44500
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.19,
|
| 1162 |
+
"eval_loss": 1.7810941934585571,
|
| 1163 |
+
"eval_runtime": 91.3943,
|
| 1164 |
+
"eval_samples_per_second": 163.347,
|
| 1165 |
+
"step": 44500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.2,
|
| 1169 |
+
"learning_rate": 3.2908559645848195e-05,
|
| 1170 |
+
"loss": 1.729,
|
| 1171 |
+
"step": 45000
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.2,
|
| 1175 |
+
"eval_loss": 1.7492631673812866,
|
| 1176 |
+
"eval_runtime": 91.524,
|
| 1177 |
+
"eval_samples_per_second": 163.116,
|
| 1178 |
+
"step": 45000
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.22,
|
| 1182 |
+
"learning_rate": 3.2664738246244956e-05,
|
| 1183 |
+
"loss": 1.6901,
|
| 1184 |
+
"step": 45500
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.22,
|
| 1188 |
+
"eval_loss": 1.7426705360412598,
|
| 1189 |
+
"eval_runtime": 91.3863,
|
| 1190 |
+
"eval_samples_per_second": 163.362,
|
| 1191 |
+
"step": 45500
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.23,
|
| 1195 |
+
"learning_rate": 3.242042822660243e-05,
|
| 1196 |
+
"loss": 1.6651,
|
| 1197 |
+
"step": 46000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.23,
|
| 1201 |
+
"eval_loss": 1.7624448537826538,
|
| 1202 |
+
"eval_runtime": 91.3919,
|
| 1203 |
+
"eval_samples_per_second": 163.352,
|
| 1204 |
+
"step": 46000
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 1.24,
|
| 1208 |
+
"learning_rate": 3.2176118206959905e-05,
|
| 1209 |
+
"loss": 1.6679,
|
| 1210 |
+
"step": 46500
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.24,
|
| 1214 |
+
"eval_loss": 1.7611286640167236,
|
| 1215 |
+
"eval_runtime": 91.3302,
|
| 1216 |
+
"eval_samples_per_second": 163.462,
|
| 1217 |
+
"step": 46500
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.26,
|
| 1221 |
+
"learning_rate": 3.193180818731738e-05,
|
| 1222 |
+
"loss": 1.6635,
|
| 1223 |
+
"step": 47000
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 1.26,
|
| 1227 |
+
"eval_loss": 1.7588094472885132,
|
| 1228 |
+
"eval_runtime": 91.421,
|
| 1229 |
+
"eval_samples_per_second": 163.299,
|
| 1230 |
+
"step": 47000
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 1.27,
|
| 1234 |
+
"learning_rate": 3.168798678771414e-05,
|
| 1235 |
+
"loss": 1.6785,
|
| 1236 |
+
"step": 47500
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 1.27,
|
| 1240 |
+
"eval_loss": 1.7499796152114868,
|
| 1241 |
+
"eval_runtime": 91.5104,
|
| 1242 |
+
"eval_samples_per_second": 163.14,
|
| 1243 |
+
"step": 47500
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 1.28,
|
| 1247 |
+
"learning_rate": 3.1443676768071614e-05,
|
| 1248 |
+
"loss": 1.6805,
|
| 1249 |
+
"step": 48000
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.28,
|
| 1253 |
+
"eval_loss": 1.7386727333068848,
|
| 1254 |
+
"eval_runtime": 91.2579,
|
| 1255 |
+
"eval_samples_per_second": 163.591,
|
| 1256 |
+
"step": 48000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.3,
|
| 1260 |
+
"learning_rate": 3.119936674842909e-05,
|
| 1261 |
+
"loss": 1.6603,
|
| 1262 |
+
"step": 48500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.3,
|
| 1266 |
+
"eval_loss": 1.7336368560791016,
|
| 1267 |
+
"eval_runtime": 91.5612,
|
| 1268 |
+
"eval_samples_per_second": 163.049,
|
| 1269 |
+
"step": 48500
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.31,
|
| 1273 |
+
"learning_rate": 3.095505672878656e-05,
|
| 1274 |
+
"loss": 1.6551,
|
| 1275 |
+
"step": 49000
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.31,
|
| 1279 |
+
"eval_loss": 1.7313791513442993,
|
| 1280 |
+
"eval_runtime": 91.2301,
|
| 1281 |
+
"eval_samples_per_second": 163.641,
|
| 1282 |
+
"step": 49000
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 1.32,
|
| 1286 |
+
"learning_rate": 3.071123532918332e-05,
|
| 1287 |
+
"loss": 1.6739,
|
| 1288 |
+
"step": 49500
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 1.32,
|
| 1292 |
+
"eval_loss": 1.7289615869522095,
|
| 1293 |
+
"eval_runtime": 91.2197,
|
| 1294 |
+
"eval_samples_per_second": 163.66,
|
| 1295 |
+
"step": 49500
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.34,
|
| 1299 |
+
"learning_rate": 3.0466925309540794e-05,
|
| 1300 |
+
"loss": 1.677,
|
| 1301 |
+
"step": 50000
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 1.34,
|
| 1305 |
+
"eval_loss": 1.7310763597488403,
|
| 1306 |
+
"eval_runtime": 91.2875,
|
| 1307 |
+
"eval_samples_per_second": 163.538,
|
| 1308 |
+
"step": 50000
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 1.35,
|
| 1312 |
+
"learning_rate": 3.022261528989827e-05,
|
| 1313 |
+
"loss": 1.6545,
|
| 1314 |
+
"step": 50500
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.35,
|
| 1318 |
+
"eval_loss": 1.7149819135665894,
|
| 1319 |
+
"eval_runtime": 91.59,
|
| 1320 |
+
"eval_samples_per_second": 162.998,
|
| 1321 |
+
"step": 50500
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 1.36,
|
| 1325 |
+
"learning_rate": 2.9978305270255746e-05,
|
| 1326 |
+
"loss": 1.6666,
|
| 1327 |
+
"step": 51000
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 1.36,
|
| 1331 |
+
"eval_loss": 1.7039389610290527,
|
| 1332 |
+
"eval_runtime": 91.4495,
|
| 1333 |
+
"eval_samples_per_second": 163.249,
|
| 1334 |
+
"step": 51000
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.38,
|
| 1338 |
+
"learning_rate": 2.9733995250613217e-05,
|
| 1339 |
+
"loss": 1.6394,
|
| 1340 |
+
"step": 51500
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.38,
|
| 1344 |
+
"eval_loss": 1.6981836557388306,
|
| 1345 |
+
"eval_runtime": 91.1406,
|
| 1346 |
+
"eval_samples_per_second": 163.802,
|
| 1347 |
+
"step": 51500
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.39,
|
| 1351 |
+
"learning_rate": 2.948968523097069e-05,
|
| 1352 |
+
"loss": 1.6064,
|
| 1353 |
+
"step": 52000
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.39,
|
| 1357 |
+
"eval_loss": 1.7015522718429565,
|
| 1358 |
+
"eval_runtime": 91.2276,
|
| 1359 |
+
"eval_samples_per_second": 163.646,
|
| 1360 |
+
"step": 52000
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 1.4,
|
| 1364 |
+
"learning_rate": 2.9245863831367455e-05,
|
| 1365 |
+
"loss": 1.676,
|
| 1366 |
+
"step": 52500
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 1.4,
|
| 1370 |
+
"eval_loss": 1.6849902868270874,
|
| 1371 |
+
"eval_runtime": 91.3094,
|
| 1372 |
+
"eval_samples_per_second": 163.499,
|
| 1373 |
+
"step": 52500
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 1.42,
|
| 1377 |
+
"learning_rate": 2.900155381172493e-05,
|
| 1378 |
+
"loss": 1.6561,
|
| 1379 |
+
"step": 53000
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 1.42,
|
| 1383 |
+
"eval_loss": 1.6929577589035034,
|
| 1384 |
+
"eval_runtime": 91.6129,
|
| 1385 |
+
"eval_samples_per_second": 162.957,
|
| 1386 |
+
"step": 53000
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 1.43,
|
| 1390 |
+
"learning_rate": 2.87572437920824e-05,
|
| 1391 |
+
"loss": 1.6949,
|
| 1392 |
+
"step": 53500
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.43,
|
| 1396 |
+
"eval_loss": 1.6772891283035278,
|
| 1397 |
+
"eval_runtime": 91.2759,
|
| 1398 |
+
"eval_samples_per_second": 163.559,
|
| 1399 |
+
"step": 53500
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.44,
|
| 1403 |
+
"learning_rate": 2.8512933772439875e-05,
|
| 1404 |
+
"loss": 1.6279,
|
| 1405 |
+
"step": 54000
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 1.44,
|
| 1409 |
+
"eval_loss": 1.6779346466064453,
|
| 1410 |
+
"eval_runtime": 91.1313,
|
| 1411 |
+
"eval_samples_per_second": 163.819,
|
| 1412 |
+
"step": 54000
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 1.46,
|
| 1416 |
+
"learning_rate": 2.8268623752797352e-05,
|
| 1417 |
+
"loss": 1.6379,
|
| 1418 |
+
"step": 54500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.46,
|
| 1422 |
+
"eval_loss": 1.6741278171539307,
|
| 1423 |
+
"eval_runtime": 91.5237,
|
| 1424 |
+
"eval_samples_per_second": 163.116,
|
| 1425 |
+
"step": 54500
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 1.47,
|
| 1429 |
+
"learning_rate": 2.8024313733154827e-05,
|
| 1430 |
+
"loss": 1.599,
|
| 1431 |
+
"step": 55000
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.47,
|
| 1435 |
+
"eval_loss": 1.6729629039764404,
|
| 1436 |
+
"eval_runtime": 91.5904,
|
| 1437 |
+
"eval_samples_per_second": 162.997,
|
| 1438 |
+
"step": 55000
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.48,
|
| 1442 |
+
"learning_rate": 2.7780003713512298e-05,
|
| 1443 |
+
"loss": 1.5784,
|
| 1444 |
+
"step": 55500
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 1.48,
|
| 1448 |
+
"eval_loss": 1.6555140018463135,
|
| 1449 |
+
"eval_runtime": 91.3689,
|
| 1450 |
+
"eval_samples_per_second": 163.393,
|
| 1451 |
+
"step": 55500
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.5,
|
| 1455 |
+
"learning_rate": 2.7535693693869775e-05,
|
| 1456 |
+
"loss": 1.577,
|
| 1457 |
+
"step": 56000
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.5,
|
| 1461 |
+
"eval_loss": 1.665055751800537,
|
| 1462 |
+
"eval_runtime": 91.3871,
|
| 1463 |
+
"eval_samples_per_second": 163.36,
|
| 1464 |
+
"step": 56000
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 1.51,
|
| 1468 |
+
"learning_rate": 2.7291872294266536e-05,
|
| 1469 |
+
"loss": 1.6282,
|
| 1470 |
+
"step": 56500
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.51,
|
| 1474 |
+
"eval_loss": 1.6812142133712769,
|
| 1475 |
+
"eval_runtime": 91.4955,
|
| 1476 |
+
"eval_samples_per_second": 163.167,
|
| 1477 |
+
"step": 56500
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 1.52,
|
| 1481 |
+
"learning_rate": 2.704756227462401e-05,
|
| 1482 |
+
"loss": 1.5585,
|
| 1483 |
+
"step": 57000
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 1.52,
|
| 1487 |
+
"eval_loss": 1.6711357831954956,
|
| 1488 |
+
"eval_runtime": 91.5418,
|
| 1489 |
+
"eval_samples_per_second": 163.084,
|
| 1490 |
+
"step": 57000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.54,
|
| 1494 |
+
"learning_rate": 2.680325225498148e-05,
|
| 1495 |
+
"loss": 1.5593,
|
| 1496 |
+
"step": 57500
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 1.54,
|
| 1500 |
+
"eval_loss": 1.6432082653045654,
|
| 1501 |
+
"eval_runtime": 91.3937,
|
| 1502 |
+
"eval_samples_per_second": 163.348,
|
| 1503 |
+
"step": 57500
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 1.55,
|
| 1507 |
+
"learning_rate": 2.655894223533896e-05,
|
| 1508 |
+
"loss": 1.5348,
|
| 1509 |
+
"step": 58000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 1.55,
|
| 1513 |
+
"eval_loss": 1.6400490999221802,
|
| 1514 |
+
"eval_runtime": 91.215,
|
| 1515 |
+
"eval_samples_per_second": 163.668,
|
| 1516 |
+
"step": 58000
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 1.56,
|
| 1520 |
+
"learning_rate": 2.6314632215696433e-05,
|
| 1521 |
+
"loss": 1.6154,
|
| 1522 |
+
"step": 58500
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.56,
|
| 1526 |
+
"eval_loss": 1.647261381149292,
|
| 1527 |
+
"eval_runtime": 91.4792,
|
| 1528 |
+
"eval_samples_per_second": 163.196,
|
| 1529 |
+
"step": 58500
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.58,
|
| 1533 |
+
"learning_rate": 2.6070810816093187e-05,
|
| 1534 |
+
"loss": 1.5831,
|
| 1535 |
+
"step": 59000
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.58,
|
| 1539 |
+
"eval_loss": 1.6438063383102417,
|
| 1540 |
+
"eval_runtime": 91.2696,
|
| 1541 |
+
"eval_samples_per_second": 163.57,
|
| 1542 |
+
"step": 59000
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.59,
|
| 1546 |
+
"learning_rate": 2.5826500796450665e-05,
|
| 1547 |
+
"loss": 1.6009,
|
| 1548 |
+
"step": 59500
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 1.59,
|
| 1552 |
+
"eval_loss": 1.646418571472168,
|
| 1553 |
+
"eval_runtime": 91.2662,
|
| 1554 |
+
"eval_samples_per_second": 163.576,
|
| 1555 |
+
"step": 59500
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 1.6,
|
| 1559 |
+
"learning_rate": 2.558219077680814e-05,
|
| 1560 |
+
"loss": 1.5858,
|
| 1561 |
+
"step": 60000
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 1.6,
|
| 1565 |
+
"eval_loss": 1.645626425743103,
|
| 1566 |
+
"eval_runtime": 91.2497,
|
| 1567 |
+
"eval_samples_per_second": 163.606,
|
| 1568 |
+
"step": 60000
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 1.62,
|
| 1572 |
+
"learning_rate": 2.5337880757165617e-05,
|
| 1573 |
+
"loss": 1.5251,
|
| 1574 |
+
"step": 60500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 1.62,
|
| 1578 |
+
"eval_loss": 1.6241323947906494,
|
| 1579 |
+
"eval_runtime": 91.2854,
|
| 1580 |
+
"eval_samples_per_second": 163.542,
|
| 1581 |
+
"step": 60500
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 1.63,
|
| 1585 |
+
"learning_rate": 2.509405935756237e-05,
|
| 1586 |
+
"loss": 1.5767,
|
| 1587 |
+
"step": 61000
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 1.63,
|
| 1591 |
+
"eval_loss": 1.6338564157485962,
|
| 1592 |
+
"eval_runtime": 91.3908,
|
| 1593 |
+
"eval_samples_per_second": 163.353,
|
| 1594 |
+
"step": 61000
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 1.64,
|
| 1598 |
+
"learning_rate": 2.4849749337919848e-05,
|
| 1599 |
+
"loss": 1.5394,
|
| 1600 |
+
"step": 61500
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.64,
|
| 1604 |
+
"eval_loss": 1.602984070777893,
|
| 1605 |
+
"eval_runtime": 91.3335,
|
| 1606 |
+
"eval_samples_per_second": 163.456,
|
| 1607 |
+
"step": 61500
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.66,
|
| 1611 |
+
"learning_rate": 2.4605439318277322e-05,
|
| 1612 |
+
"loss": 1.5951,
|
| 1613 |
+
"step": 62000
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.66,
|
| 1617 |
+
"eval_loss": 1.6044830083847046,
|
| 1618 |
+
"eval_runtime": 91.4386,
|
| 1619 |
+
"eval_samples_per_second": 163.268,
|
| 1620 |
+
"step": 62000
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.67,
|
| 1624 |
+
"learning_rate": 2.4361129298634797e-05,
|
| 1625 |
+
"loss": 1.5563,
|
| 1626 |
+
"step": 62500
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.67,
|
| 1630 |
+
"eval_loss": 1.6318944692611694,
|
| 1631 |
+
"eval_runtime": 91.2817,
|
| 1632 |
+
"eval_samples_per_second": 163.549,
|
| 1633 |
+
"step": 62500
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.68,
|
| 1637 |
+
"learning_rate": 2.4117307899031554e-05,
|
| 1638 |
+
"loss": 1.5319,
|
| 1639 |
+
"step": 63000
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 1.68,
|
| 1643 |
+
"eval_loss": 1.5991877317428589,
|
| 1644 |
+
"eval_runtime": 91.533,
|
| 1645 |
+
"eval_samples_per_second": 163.1,
|
| 1646 |
+
"step": 63000
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 1.7,
|
| 1650 |
+
"learning_rate": 2.387299787938903e-05,
|
| 1651 |
+
"loss": 1.595,
|
| 1652 |
+
"step": 63500
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 1.7,
|
| 1656 |
+
"eval_loss": 1.583760142326355,
|
| 1657 |
+
"eval_runtime": 91.246,
|
| 1658 |
+
"eval_samples_per_second": 163.613,
|
| 1659 |
+
"step": 63500
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 1.71,
|
| 1663 |
+
"learning_rate": 2.362917647978579e-05,
|
| 1664 |
+
"loss": 1.5797,
|
| 1665 |
+
"step": 64000
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 1.71,
|
| 1669 |
+
"eval_loss": 1.6295143365859985,
|
| 1670 |
+
"eval_runtime": 90.9781,
|
| 1671 |
+
"eval_samples_per_second": 164.094,
|
| 1672 |
+
"step": 64000
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 1.72,
|
| 1676 |
+
"learning_rate": 2.3384866460143267e-05,
|
| 1677 |
+
"loss": 1.5298,
|
| 1678 |
+
"step": 64500
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 1.72,
|
| 1682 |
+
"eval_loss": 1.599826455116272,
|
| 1683 |
+
"eval_runtime": 91.406,
|
| 1684 |
+
"eval_samples_per_second": 163.326,
|
| 1685 |
+
"step": 64500
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 1.74,
|
| 1689 |
+
"learning_rate": 2.3140556440500737e-05,
|
| 1690 |
+
"loss": 1.5384,
|
| 1691 |
+
"step": 65000
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 1.74,
|
| 1695 |
+
"eval_loss": 1.6063343286514282,
|
| 1696 |
+
"eval_runtime": 91.4223,
|
| 1697 |
+
"eval_samples_per_second": 163.297,
|
| 1698 |
+
"step": 65000
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.75,
|
| 1702 |
+
"learning_rate": 2.2896246420858215e-05,
|
| 1703 |
+
"loss": 1.4986,
|
| 1704 |
+
"step": 65500
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.75,
|
| 1708 |
+
"eval_loss": 1.5949381589889526,
|
| 1709 |
+
"eval_runtime": 91.3186,
|
| 1710 |
+
"eval_samples_per_second": 163.483,
|
| 1711 |
+
"step": 65500
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.76,
|
| 1715 |
+
"learning_rate": 2.2651936401215686e-05,
|
| 1716 |
+
"loss": 1.5075,
|
| 1717 |
+
"step": 66000
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.76,
|
| 1721 |
+
"eval_loss": 1.5914294719696045,
|
| 1722 |
+
"eval_runtime": 91.3212,
|
| 1723 |
+
"eval_samples_per_second": 163.478,
|
| 1724 |
+
"step": 66000
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.78,
|
| 1728 |
+
"learning_rate": 2.2407626381573164e-05,
|
| 1729 |
+
"loss": 1.5303,
|
| 1730 |
+
"step": 66500
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 1.78,
|
| 1734 |
+
"eval_loss": 1.5806745290756226,
|
| 1735 |
+
"eval_runtime": 91.0984,
|
| 1736 |
+
"eval_samples_per_second": 163.878,
|
| 1737 |
+
"step": 66500
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.79,
|
| 1741 |
+
"learning_rate": 2.2163316361930635e-05,
|
| 1742 |
+
"loss": 1.5015,
|
| 1743 |
+
"step": 67000
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 1.79,
|
| 1747 |
+
"eval_loss": 1.5750070810317993,
|
| 1748 |
+
"eval_runtime": 91.4316,
|
| 1749 |
+
"eval_samples_per_second": 163.281,
|
| 1750 |
+
"step": 67000
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 1.8,
|
| 1754 |
+
"learning_rate": 2.1919006342288112e-05,
|
| 1755 |
+
"loss": 1.5542,
|
| 1756 |
+
"step": 67500
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 1.8,
|
| 1760 |
+
"eval_loss": 1.6114143133163452,
|
| 1761 |
+
"eval_runtime": 91.4407,
|
| 1762 |
+
"eval_samples_per_second": 163.264,
|
| 1763 |
+
"step": 67500
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 1.82,
|
| 1767 |
+
"learning_rate": 2.167518494268487e-05,
|
| 1768 |
+
"loss": 1.525,
|
| 1769 |
+
"step": 68000
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 1.82,
|
| 1773 |
+
"eval_loss": 1.5729782581329346,
|
| 1774 |
+
"eval_runtime": 91.2691,
|
| 1775 |
+
"eval_samples_per_second": 163.571,
|
| 1776 |
+
"step": 68000
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 1.83,
|
| 1780 |
+
"learning_rate": 2.1430874923042347e-05,
|
| 1781 |
+
"loss": 1.4573,
|
| 1782 |
+
"step": 68500
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 1.83,
|
| 1786 |
+
"eval_loss": 1.598924994468689,
|
| 1787 |
+
"eval_runtime": 91.2081,
|
| 1788 |
+
"eval_samples_per_second": 163.681,
|
| 1789 |
+
"step": 68500
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 1.84,
|
| 1793 |
+
"learning_rate": 2.1186564903399818e-05,
|
| 1794 |
+
"loss": 1.5125,
|
| 1795 |
+
"step": 69000
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.84,
|
| 1799 |
+
"eval_loss": 1.5879831314086914,
|
| 1800 |
+
"eval_runtime": 91.4783,
|
| 1801 |
+
"eval_samples_per_second": 163.197,
|
| 1802 |
+
"step": 69000
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.86,
|
| 1806 |
+
"learning_rate": 2.0942254883757292e-05,
|
| 1807 |
+
"loss": 1.5089,
|
| 1808 |
+
"step": 69500
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.86,
|
| 1812 |
+
"eval_loss": 1.5672917366027832,
|
| 1813 |
+
"eval_runtime": 91.4841,
|
| 1814 |
+
"eval_samples_per_second": 163.187,
|
| 1815 |
+
"step": 69500
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.87,
|
| 1819 |
+
"learning_rate": 2.0697944864114767e-05,
|
| 1820 |
+
"loss": 1.5231,
|
| 1821 |
+
"step": 70000
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 1.87,
|
| 1825 |
+
"eval_loss": 1.5848079919815063,
|
| 1826 |
+
"eval_runtime": 91.2446,
|
| 1827 |
+
"eval_samples_per_second": 163.615,
|
| 1828 |
+
"step": 70000
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 1.88,
|
| 1832 |
+
"learning_rate": 2.045363484447224e-05,
|
| 1833 |
+
"loss": 1.5283,
|
| 1834 |
+
"step": 70500
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.88,
|
| 1838 |
+
"eval_loss": 1.5898315906524658,
|
| 1839 |
+
"eval_runtime": 91.1948,
|
| 1840 |
+
"eval_samples_per_second": 163.705,
|
| 1841 |
+
"step": 70500
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 1.9,
|
| 1845 |
+
"learning_rate": 2.0209813444869e-05,
|
| 1846 |
+
"loss": 1.4879,
|
| 1847 |
+
"step": 71000
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 1.9,
|
| 1851 |
+
"eval_loss": 1.554874300956726,
|
| 1852 |
+
"eval_runtime": 91.3983,
|
| 1853 |
+
"eval_samples_per_second": 163.34,
|
| 1854 |
+
"step": 71000
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 1.91,
|
| 1858 |
+
"learning_rate": 1.9965503425226476e-05,
|
| 1859 |
+
"loss": 1.5034,
|
| 1860 |
+
"step": 71500
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 1.91,
|
| 1864 |
+
"eval_loss": 1.5682209730148315,
|
| 1865 |
+
"eval_runtime": 91.3854,
|
| 1866 |
+
"eval_samples_per_second": 163.363,
|
| 1867 |
+
"step": 71500
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 1.92,
|
| 1871 |
+
"learning_rate": 1.972119340558395e-05,
|
| 1872 |
+
"loss": 1.5024,
|
| 1873 |
+
"step": 72000
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 1.92,
|
| 1877 |
+
"eval_loss": 1.5595961809158325,
|
| 1878 |
+
"eval_runtime": 91.4495,
|
| 1879 |
+
"eval_samples_per_second": 163.249,
|
| 1880 |
+
"step": 72000
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 1.94,
|
| 1884 |
+
"learning_rate": 1.9476883385941425e-05,
|
| 1885 |
+
"loss": 1.4673,
|
| 1886 |
+
"step": 72500
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.94,
|
| 1890 |
+
"eval_loss": 1.5504151582717896,
|
| 1891 |
+
"eval_runtime": 91.2318,
|
| 1892 |
+
"eval_samples_per_second": 163.638,
|
| 1893 |
+
"step": 72500
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.95,
|
| 1897 |
+
"learning_rate": 1.92325733662989e-05,
|
| 1898 |
+
"loss": 1.4758,
|
| 1899 |
+
"step": 73000
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.95,
|
| 1903 |
+
"eval_loss": 1.5395164489746094,
|
| 1904 |
+
"eval_runtime": 91.1184,
|
| 1905 |
+
"eval_samples_per_second": 163.842,
|
| 1906 |
+
"step": 73000
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.96,
|
| 1910 |
+
"learning_rate": 1.898875196669566e-05,
|
| 1911 |
+
"loss": 1.4674,
|
| 1912 |
+
"step": 73500
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 1.96,
|
| 1916 |
+
"eval_loss": 1.5537846088409424,
|
| 1917 |
+
"eval_runtime": 91.4847,
|
| 1918 |
+
"eval_samples_per_second": 163.186,
|
| 1919 |
+
"step": 73500
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.98,
|
| 1923 |
+
"learning_rate": 1.8744441947053134e-05,
|
| 1924 |
+
"loss": 1.4528,
|
| 1925 |
+
"step": 74000
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 1.98,
|
| 1929 |
+
"eval_loss": 1.552320957183838,
|
| 1930 |
+
"eval_runtime": 91.3075,
|
| 1931 |
+
"eval_samples_per_second": 163.502,
|
| 1932 |
+
"step": 74000
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 1.99,
|
| 1936 |
+
"learning_rate": 1.8500131927410608e-05,
|
| 1937 |
+
"loss": 1.4829,
|
| 1938 |
+
"step": 74500
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 1.99,
|
| 1942 |
+
"eval_loss": 1.5265352725982666,
|
| 1943 |
+
"eval_runtime": 91.4875,
|
| 1944 |
+
"eval_samples_per_second": 163.181,
|
| 1945 |
+
"step": 74500
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 2.0,
|
| 1949 |
+
"learning_rate": 1.8255821907768082e-05,
|
| 1950 |
+
"loss": 1.4611,
|
| 1951 |
+
"step": 75000
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 2.0,
|
| 1955 |
+
"eval_loss": 1.5295826196670532,
|
| 1956 |
+
"eval_runtime": 91.5744,
|
| 1957 |
+
"eval_samples_per_second": 163.026,
|
| 1958 |
+
"step": 75000
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 2.02,
|
| 1962 |
+
"learning_rate": 1.8012000508164843e-05,
|
| 1963 |
+
"loss": 1.4442,
|
| 1964 |
+
"step": 75500
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 2.02,
|
| 1968 |
+
"eval_loss": 1.5388405323028564,
|
| 1969 |
+
"eval_runtime": 91.8129,
|
| 1970 |
+
"eval_samples_per_second": 162.602,
|
| 1971 |
+
"step": 75500
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 2.03,
|
| 1975 |
+
"learning_rate": 1.7767690488522314e-05,
|
| 1976 |
+
"loss": 1.4465,
|
| 1977 |
+
"step": 76000
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.03,
|
| 1981 |
+
"eval_loss": 1.5279512405395508,
|
| 1982 |
+
"eval_runtime": 91.5443,
|
| 1983 |
+
"eval_samples_per_second": 163.08,
|
| 1984 |
+
"step": 76000
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.04,
|
| 1988 |
+
"learning_rate": 1.752338046887979e-05,
|
| 1989 |
+
"loss": 1.4253,
|
| 1990 |
+
"step": 76500
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 2.04,
|
| 1994 |
+
"eval_loss": 1.5250307321548462,
|
| 1995 |
+
"eval_runtime": 91.2655,
|
| 1996 |
+
"eval_samples_per_second": 163.578,
|
| 1997 |
+
"step": 76500
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 2.06,
|
| 2001 |
+
"learning_rate": 1.7279070449237263e-05,
|
| 2002 |
+
"loss": 1.4236,
|
| 2003 |
+
"step": 77000
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 2.06,
|
| 2007 |
+
"eval_loss": 1.5277702808380127,
|
| 2008 |
+
"eval_runtime": 91.3984,
|
| 2009 |
+
"eval_samples_per_second": 163.34,
|
| 2010 |
+
"step": 77000
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 2.07,
|
| 2014 |
+
"learning_rate": 1.703476042959474e-05,
|
| 2015 |
+
"loss": 1.4749,
|
| 2016 |
+
"step": 77500
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 2.07,
|
| 2020 |
+
"eval_loss": 1.5159269571304321,
|
| 2021 |
+
"eval_runtime": 91.6205,
|
| 2022 |
+
"eval_samples_per_second": 162.944,
|
| 2023 |
+
"step": 77500
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 2.08,
|
| 2027 |
+
"learning_rate": 1.6790450409952215e-05,
|
| 2028 |
+
"loss": 1.4373,
|
| 2029 |
+
"step": 78000
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 2.08,
|
| 2033 |
+
"eval_loss": 1.4971988201141357,
|
| 2034 |
+
"eval_runtime": 91.5971,
|
| 2035 |
+
"eval_samples_per_second": 162.985,
|
| 2036 |
+
"step": 78000
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 2.1,
|
| 2040 |
+
"learning_rate": 1.654614039030969e-05,
|
| 2041 |
+
"loss": 1.4307,
|
| 2042 |
+
"step": 78500
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 2.1,
|
| 2046 |
+
"eval_loss": 1.5140836238861084,
|
| 2047 |
+
"eval_runtime": 91.3406,
|
| 2048 |
+
"eval_samples_per_second": 163.443,
|
| 2049 |
+
"step": 78500
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 2.11,
|
| 2053 |
+
"learning_rate": 1.6301830370667163e-05,
|
| 2054 |
+
"loss": 1.4237,
|
| 2055 |
+
"step": 79000
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 2.11,
|
| 2059 |
+
"eval_loss": 1.5364242792129517,
|
| 2060 |
+
"eval_runtime": 91.2725,
|
| 2061 |
+
"eval_samples_per_second": 163.565,
|
| 2062 |
+
"step": 79000
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 2.12,
|
| 2066 |
+
"learning_rate": 1.6058008971063924e-05,
|
| 2067 |
+
"loss": 1.429,
|
| 2068 |
+
"step": 79500
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.12,
|
| 2072 |
+
"eval_loss": 1.5153831243515015,
|
| 2073 |
+
"eval_runtime": 91.5247,
|
| 2074 |
+
"eval_samples_per_second": 163.114,
|
| 2075 |
+
"step": 79500
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.14,
|
| 2079 |
+
"learning_rate": 1.581418757146068e-05,
|
| 2080 |
+
"loss": 1.4359,
|
| 2081 |
+
"step": 80000
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 2.14,
|
| 2085 |
+
"eval_loss": 1.5109397172927856,
|
| 2086 |
+
"eval_runtime": 91.5239,
|
| 2087 |
+
"eval_samples_per_second": 163.116,
|
| 2088 |
+
"step": 80000
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 2.15,
|
| 2092 |
+
"learning_rate": 1.556987755181816e-05,
|
| 2093 |
+
"loss": 1.3969,
|
| 2094 |
+
"step": 80500
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 2.15,
|
| 2098 |
+
"eval_loss": 1.5034611225128174,
|
| 2099 |
+
"eval_runtime": 91.2642,
|
| 2100 |
+
"eval_samples_per_second": 163.58,
|
| 2101 |
+
"step": 80500
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 2.16,
|
| 2105 |
+
"learning_rate": 1.532556753217563e-05,
|
| 2106 |
+
"loss": 1.4011,
|
| 2107 |
+
"step": 81000
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 2.16,
|
| 2111 |
+
"eval_loss": 1.5004990100860596,
|
| 2112 |
+
"eval_runtime": 91.4331,
|
| 2113 |
+
"eval_samples_per_second": 163.278,
|
| 2114 |
+
"step": 81000
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 2.18,
|
| 2118 |
+
"learning_rate": 1.5081257512533104e-05,
|
| 2119 |
+
"loss": 1.4231,
|
| 2120 |
+
"step": 81500
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 2.18,
|
| 2124 |
+
"eval_loss": 1.4998698234558105,
|
| 2125 |
+
"eval_runtime": 91.3964,
|
| 2126 |
+
"eval_samples_per_second": 163.343,
|
| 2127 |
+
"step": 81500
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 2.19,
|
| 2131 |
+
"learning_rate": 1.483694749289058e-05,
|
| 2132 |
+
"loss": 1.4476,
|
| 2133 |
+
"step": 82000
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 2.19,
|
| 2137 |
+
"eval_loss": 1.5173091888427734,
|
| 2138 |
+
"eval_runtime": 91.4077,
|
| 2139 |
+
"eval_samples_per_second": 163.323,
|
| 2140 |
+
"step": 82000
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 2.2,
|
| 2144 |
+
"learning_rate": 1.4592637473248052e-05,
|
| 2145 |
+
"loss": 1.4455,
|
| 2146 |
+
"step": 82500
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 2.2,
|
| 2150 |
+
"eval_loss": 1.4715697765350342,
|
| 2151 |
+
"eval_runtime": 91.3644,
|
| 2152 |
+
"eval_samples_per_second": 163.401,
|
| 2153 |
+
"step": 82500
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 2.22,
|
| 2157 |
+
"learning_rate": 1.4348327453605528e-05,
|
| 2158 |
+
"loss": 1.402,
|
| 2159 |
+
"step": 83000
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.22,
|
| 2163 |
+
"eval_loss": 1.4942283630371094,
|
| 2164 |
+
"eval_runtime": 91.1381,
|
| 2165 |
+
"eval_samples_per_second": 163.806,
|
| 2166 |
+
"step": 83000
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.23,
|
| 2170 |
+
"learning_rate": 1.4104506054002287e-05,
|
| 2171 |
+
"loss": 1.4352,
|
| 2172 |
+
"step": 83500
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 2.23,
|
| 2176 |
+
"eval_loss": 1.4948195219039917,
|
| 2177 |
+
"eval_runtime": 91.3982,
|
| 2178 |
+
"eval_samples_per_second": 163.34,
|
| 2179 |
+
"step": 83500
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 2.24,
|
| 2183 |
+
"learning_rate": 1.3860196034359763e-05,
|
| 2184 |
+
"loss": 1.4316,
|
| 2185 |
+
"step": 84000
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 2.24,
|
| 2189 |
+
"eval_loss": 1.4814602136611938,
|
| 2190 |
+
"eval_runtime": 91.536,
|
| 2191 |
+
"eval_samples_per_second": 163.094,
|
| 2192 |
+
"step": 84000
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 2.26,
|
| 2196 |
+
"learning_rate": 1.3615886014717236e-05,
|
| 2197 |
+
"loss": 1.413,
|
| 2198 |
+
"step": 84500
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 2.26,
|
| 2202 |
+
"eval_loss": 1.492964267730713,
|
| 2203 |
+
"eval_runtime": 91.5767,
|
| 2204 |
+
"eval_samples_per_second": 163.022,
|
| 2205 |
+
"step": 84500
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 2.27,
|
| 2209 |
+
"learning_rate": 1.3371575995074712e-05,
|
| 2210 |
+
"loss": 1.3647,
|
| 2211 |
+
"step": 85000
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 2.27,
|
| 2215 |
+
"eval_loss": 1.5028858184814453,
|
| 2216 |
+
"eval_runtime": 91.453,
|
| 2217 |
+
"eval_samples_per_second": 163.242,
|
| 2218 |
+
"step": 85000
|
| 2219 |
+
},
|
| 2220 |
+
{
|
| 2221 |
+
"epoch": 2.28,
|
| 2222 |
+
"learning_rate": 1.3127265975432185e-05,
|
| 2223 |
+
"loss": 1.3549,
|
| 2224 |
+
"step": 85500
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 2.28,
|
| 2228 |
+
"eval_loss": 1.4676295518875122,
|
| 2229 |
+
"eval_runtime": 91.2539,
|
| 2230 |
+
"eval_samples_per_second": 163.598,
|
| 2231 |
+
"step": 85500
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 2.3,
|
| 2235 |
+
"learning_rate": 1.288295595578966e-05,
|
| 2236 |
+
"loss": 1.4649,
|
| 2237 |
+
"step": 86000
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 2.3,
|
| 2241 |
+
"eval_loss": 1.4584786891937256,
|
| 2242 |
+
"eval_runtime": 91.7498,
|
| 2243 |
+
"eval_samples_per_second": 162.714,
|
| 2244 |
+
"step": 86000
|
| 2245 |
+
},
|
| 2246 |
+
{
|
| 2247 |
+
"epoch": 2.31,
|
| 2248 |
+
"learning_rate": 1.2638645936147133e-05,
|
| 2249 |
+
"loss": 1.401,
|
| 2250 |
+
"step": 86500
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.31,
|
| 2254 |
+
"eval_loss": 1.478485107421875,
|
| 2255 |
+
"eval_runtime": 91.4585,
|
| 2256 |
+
"eval_samples_per_second": 163.232,
|
| 2257 |
+
"step": 86500
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.32,
|
| 2261 |
+
"learning_rate": 1.2394335916504608e-05,
|
| 2262 |
+
"loss": 1.4047,
|
| 2263 |
+
"step": 87000
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 2.32,
|
| 2267 |
+
"eval_loss": 1.4770060777664185,
|
| 2268 |
+
"eval_runtime": 91.2763,
|
| 2269 |
+
"eval_samples_per_second": 163.558,
|
| 2270 |
+
"step": 87000
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 2.34,
|
| 2274 |
+
"learning_rate": 1.2150025896862084e-05,
|
| 2275 |
+
"loss": 1.3718,
|
| 2276 |
+
"step": 87500
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 2.34,
|
| 2280 |
+
"eval_loss": 1.4772363901138306,
|
| 2281 |
+
"eval_runtime": 91.3427,
|
| 2282 |
+
"eval_samples_per_second": 163.439,
|
| 2283 |
+
"step": 87500
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 2.35,
|
| 2287 |
+
"learning_rate": 1.1906693117298127e-05,
|
| 2288 |
+
"loss": 1.4123,
|
| 2289 |
+
"step": 88000
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 2.35,
|
| 2293 |
+
"eval_loss": 1.4651228189468384,
|
| 2294 |
+
"eval_runtime": 91.4724,
|
| 2295 |
+
"eval_samples_per_second": 163.208,
|
| 2296 |
+
"step": 88000
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 2.36,
|
| 2300 |
+
"learning_rate": 1.1662383097655601e-05,
|
| 2301 |
+
"loss": 1.3914,
|
| 2302 |
+
"step": 88500
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 2.36,
|
| 2306 |
+
"eval_loss": 1.439155101776123,
|
| 2307 |
+
"eval_runtime": 91.387,
|
| 2308 |
+
"eval_samples_per_second": 163.36,
|
| 2309 |
+
"step": 88500
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 2.38,
|
| 2313 |
+
"learning_rate": 1.1418073078013077e-05,
|
| 2314 |
+
"loss": 1.3936,
|
| 2315 |
+
"step": 89000
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 2.38,
|
| 2319 |
+
"eval_loss": 1.4595708847045898,
|
| 2320 |
+
"eval_runtime": 91.5308,
|
| 2321 |
+
"eval_samples_per_second": 163.104,
|
| 2322 |
+
"step": 89000
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 2.39,
|
| 2326 |
+
"learning_rate": 1.1173763058370552e-05,
|
| 2327 |
+
"loss": 1.3448,
|
| 2328 |
+
"step": 89500
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 2.39,
|
| 2332 |
+
"eval_loss": 1.4761011600494385,
|
| 2333 |
+
"eval_runtime": 91.6432,
|
| 2334 |
+
"eval_samples_per_second": 162.903,
|
| 2335 |
+
"step": 89500
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 2.4,
|
| 2339 |
+
"learning_rate": 1.0929453038728024e-05,
|
| 2340 |
+
"loss": 1.352,
|
| 2341 |
+
"step": 90000
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.4,
|
| 2345 |
+
"eval_loss": 1.468656063079834,
|
| 2346 |
+
"eval_runtime": 91.6903,
|
| 2347 |
+
"eval_samples_per_second": 162.82,
|
| 2348 |
+
"step": 90000
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.42,
|
| 2352 |
+
"learning_rate": 1.0685143019085499e-05,
|
| 2353 |
+
"loss": 1.3459,
|
| 2354 |
+
"step": 90500
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 2.42,
|
| 2358 |
+
"eval_loss": 1.4411649703979492,
|
| 2359 |
+
"eval_runtime": 91.7674,
|
| 2360 |
+
"eval_samples_per_second": 162.683,
|
| 2361 |
+
"step": 90500
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 2.43,
|
| 2365 |
+
"learning_rate": 1.0440832999442973e-05,
|
| 2366 |
+
"loss": 1.3732,
|
| 2367 |
+
"step": 91000
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 2.43,
|
| 2371 |
+
"eval_loss": 1.4545894861221313,
|
| 2372 |
+
"eval_runtime": 91.5374,
|
| 2373 |
+
"eval_samples_per_second": 163.092,
|
| 2374 |
+
"step": 91000
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 2.44,
|
| 2378 |
+
"learning_rate": 1.0196522979800447e-05,
|
| 2379 |
+
"loss": 1.3586,
|
| 2380 |
+
"step": 91500
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 2.44,
|
| 2384 |
+
"eval_loss": 1.4413018226623535,
|
| 2385 |
+
"eval_runtime": 91.6716,
|
| 2386 |
+
"eval_samples_per_second": 162.853,
|
| 2387 |
+
"step": 91500
|
| 2388 |
+
},
|
| 2389 |
+
{
|
| 2390 |
+
"epoch": 2.46,
|
| 2391 |
+
"learning_rate": 9.952212960157921e-06,
|
| 2392 |
+
"loss": 1.3578,
|
| 2393 |
+
"step": 92000
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 2.46,
|
| 2397 |
+
"eval_loss": 1.4500373601913452,
|
| 2398 |
+
"eval_runtime": 91.7404,
|
| 2399 |
+
"eval_samples_per_second": 162.731,
|
| 2400 |
+
"step": 92000
|
| 2401 |
+
},
|
| 2402 |
+
{
|
| 2403 |
+
"epoch": 2.47,
|
| 2404 |
+
"learning_rate": 9.708391560554682e-06,
|
| 2405 |
+
"loss": 1.3847,
|
| 2406 |
+
"step": 92500
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 2.47,
|
| 2410 |
+
"eval_loss": 1.4499620199203491,
|
| 2411 |
+
"eval_runtime": 91.826,
|
| 2412 |
+
"eval_samples_per_second": 162.579,
|
| 2413 |
+
"step": 92500
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 2.48,
|
| 2417 |
+
"learning_rate": 9.464081540912156e-06,
|
| 2418 |
+
"loss": 1.4119,
|
| 2419 |
+
"step": 93000
|
| 2420 |
+
},
|
| 2421 |
+
{
|
| 2422 |
+
"epoch": 2.48,
|
| 2423 |
+
"eval_loss": 1.4416851997375488,
|
| 2424 |
+
"eval_runtime": 91.623,
|
| 2425 |
+
"eval_samples_per_second": 162.939,
|
| 2426 |
+
"step": 93000
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 2.5,
|
| 2430 |
+
"learning_rate": 9.21977152126963e-06,
|
| 2431 |
+
"loss": 1.3674,
|
| 2432 |
+
"step": 93500
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 2.5,
|
| 2436 |
+
"eval_loss": 1.4545212984085083,
|
| 2437 |
+
"eval_runtime": 91.714,
|
| 2438 |
+
"eval_samples_per_second": 162.778,
|
| 2439 |
+
"step": 93500
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 2.51,
|
| 2443 |
+
"learning_rate": 8.975461501627105e-06,
|
| 2444 |
+
"loss": 1.3805,
|
| 2445 |
+
"step": 94000
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 2.51,
|
| 2449 |
+
"eval_loss": 1.4539984464645386,
|
| 2450 |
+
"eval_runtime": 91.7771,
|
| 2451 |
+
"eval_samples_per_second": 162.666,
|
| 2452 |
+
"step": 94000
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 2.52,
|
| 2456 |
+
"learning_rate": 8.731640102023866e-06,
|
| 2457 |
+
"loss": 1.341,
|
| 2458 |
+
"step": 94500
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 2.52,
|
| 2462 |
+
"eval_loss": 1.4235692024230957,
|
| 2463 |
+
"eval_runtime": 91.8087,
|
| 2464 |
+
"eval_samples_per_second": 162.61,
|
| 2465 |
+
"step": 94500
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 2.54,
|
| 2469 |
+
"learning_rate": 8.48733008238134e-06,
|
| 2470 |
+
"loss": 1.3635,
|
| 2471 |
+
"step": 95000
|
| 2472 |
+
},
|
| 2473 |
+
{
|
| 2474 |
+
"epoch": 2.54,
|
| 2475 |
+
"eval_loss": 1.427968144416809,
|
| 2476 |
+
"eval_runtime": 91.7853,
|
| 2477 |
+
"eval_samples_per_second": 162.651,
|
| 2478 |
+
"step": 95000
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 2.55,
|
| 2482 |
+
"learning_rate": 8.243020062738814e-06,
|
| 2483 |
+
"loss": 1.3217,
|
| 2484 |
+
"step": 95500
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 2.55,
|
| 2488 |
+
"eval_loss": 1.4452221393585205,
|
| 2489 |
+
"eval_runtime": 91.4571,
|
| 2490 |
+
"eval_samples_per_second": 163.235,
|
| 2491 |
+
"step": 95500
|
| 2492 |
+
},
|
| 2493 |
+
{
|
| 2494 |
+
"epoch": 2.56,
|
| 2495 |
+
"learning_rate": 7.998710043096287e-06,
|
| 2496 |
+
"loss": 1.3753,
|
| 2497 |
+
"step": 96000
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 2.56,
|
| 2501 |
+
"eval_loss": 1.4172078371047974,
|
| 2502 |
+
"eval_runtime": 91.6806,
|
| 2503 |
+
"eval_samples_per_second": 162.837,
|
| 2504 |
+
"step": 96000
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 2.58,
|
| 2508 |
+
"learning_rate": 7.754400023453761e-06,
|
| 2509 |
+
"loss": 1.3509,
|
| 2510 |
+
"step": 96500
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 2.58,
|
| 2514 |
+
"eval_loss": 1.426705002784729,
|
| 2515 |
+
"eval_runtime": 91.7131,
|
| 2516 |
+
"eval_samples_per_second": 162.779,
|
| 2517 |
+
"step": 96500
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 2.59,
|
| 2521 |
+
"learning_rate": 7.510578623850522e-06,
|
| 2522 |
+
"loss": 1.35,
|
| 2523 |
+
"step": 97000
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 2.59,
|
| 2527 |
+
"eval_loss": 1.4170763492584229,
|
| 2528 |
+
"eval_runtime": 91.523,
|
| 2529 |
+
"eval_samples_per_second": 163.118,
|
| 2530 |
+
"step": 97000
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 2.6,
|
| 2534 |
+
"learning_rate": 7.266268604207996e-06,
|
| 2535 |
+
"loss": 1.3277,
|
| 2536 |
+
"step": 97500
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 2.6,
|
| 2540 |
+
"eval_loss": 1.4099535942077637,
|
| 2541 |
+
"eval_runtime": 91.6084,
|
| 2542 |
+
"eval_samples_per_second": 162.965,
|
| 2543 |
+
"step": 97500
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 2.62,
|
| 2547 |
+
"learning_rate": 7.02195858456547e-06,
|
| 2548 |
+
"loss": 1.3574,
|
| 2549 |
+
"step": 98000
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 2.62,
|
| 2553 |
+
"eval_loss": 1.429254174232483,
|
| 2554 |
+
"eval_runtime": 91.6665,
|
| 2555 |
+
"eval_samples_per_second": 162.862,
|
| 2556 |
+
"step": 98000
|
| 2557 |
+
},
|
| 2558 |
+
{
|
| 2559 |
+
"epoch": 2.63,
|
| 2560 |
+
"learning_rate": 6.7776485649229446e-06,
|
| 2561 |
+
"loss": 1.3347,
|
| 2562 |
+
"step": 98500
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 2.63,
|
| 2566 |
+
"eval_loss": 1.3997344970703125,
|
| 2567 |
+
"eval_runtime": 91.8372,
|
| 2568 |
+
"eval_samples_per_second": 162.559,
|
| 2569 |
+
"step": 98500
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"epoch": 2.64,
|
| 2573 |
+
"learning_rate": 6.533827165319704e-06,
|
| 2574 |
+
"loss": 1.3655,
|
| 2575 |
+
"step": 99000
|
| 2576 |
+
},
|
| 2577 |
+
{
|
| 2578 |
+
"epoch": 2.64,
|
| 2579 |
+
"eval_loss": 1.414544701576233,
|
| 2580 |
+
"eval_runtime": 91.8567,
|
| 2581 |
+
"eval_samples_per_second": 162.525,
|
| 2582 |
+
"step": 99000
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 2.66,
|
| 2586 |
+
"learning_rate": 6.289517145677179e-06,
|
| 2587 |
+
"loss": 1.3037,
|
| 2588 |
+
"step": 99500
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 2.66,
|
| 2592 |
+
"eval_loss": 1.4175053834915161,
|
| 2593 |
+
"eval_runtime": 91.5715,
|
| 2594 |
+
"eval_samples_per_second": 163.031,
|
| 2595 |
+
"step": 99500
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 2.67,
|
| 2599 |
+
"learning_rate": 6.045207126034654e-06,
|
| 2600 |
+
"loss": 1.3632,
|
| 2601 |
+
"step": 100000
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 2.67,
|
| 2605 |
+
"eval_loss": 1.411368489265442,
|
| 2606 |
+
"eval_runtime": 91.9948,
|
| 2607 |
+
"eval_samples_per_second": 162.281,
|
| 2608 |
+
"step": 100000
|
| 2609 |
+
},
|
| 2610 |
+
{
|
| 2611 |
+
"epoch": 2.68,
|
| 2612 |
+
"learning_rate": 5.800897106392127e-06,
|
| 2613 |
+
"loss": 1.3346,
|
| 2614 |
+
"step": 100500
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 2.68,
|
| 2618 |
+
"eval_loss": 1.4163134098052979,
|
| 2619 |
+
"eval_runtime": 91.6974,
|
| 2620 |
+
"eval_samples_per_second": 162.807,
|
| 2621 |
+
"step": 100500
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 2.7,
|
| 2625 |
+
"learning_rate": 5.5565870867496015e-06,
|
| 2626 |
+
"loss": 1.3371,
|
| 2627 |
+
"step": 101000
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 2.7,
|
| 2631 |
+
"eval_loss": 1.4231865406036377,
|
| 2632 |
+
"eval_runtime": 91.7114,
|
| 2633 |
+
"eval_samples_per_second": 162.782,
|
| 2634 |
+
"step": 101000
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 2.71,
|
| 2638 |
+
"learning_rate": 5.312765687146361e-06,
|
| 2639 |
+
"loss": 1.3077,
|
| 2640 |
+
"step": 101500
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 2.71,
|
| 2644 |
+
"eval_loss": 1.4206013679504395,
|
| 2645 |
+
"eval_runtime": 91.6392,
|
| 2646 |
+
"eval_samples_per_second": 162.911,
|
| 2647 |
+
"step": 101500
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 2.72,
|
| 2651 |
+
"learning_rate": 5.068455667503836e-06,
|
| 2652 |
+
"loss": 1.3352,
|
| 2653 |
+
"step": 102000
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 2.72,
|
| 2657 |
+
"eval_loss": 1.4135525226593018,
|
| 2658 |
+
"eval_runtime": 91.6091,
|
| 2659 |
+
"eval_samples_per_second": 162.964,
|
| 2660 |
+
"step": 102000
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 2.74,
|
| 2664 |
+
"learning_rate": 4.824145647861311e-06,
|
| 2665 |
+
"loss": 1.3442,
|
| 2666 |
+
"step": 102500
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 2.74,
|
| 2670 |
+
"eval_loss": 1.413482904434204,
|
| 2671 |
+
"eval_runtime": 91.795,
|
| 2672 |
+
"eval_samples_per_second": 162.634,
|
| 2673 |
+
"step": 102500
|
| 2674 |
+
},
|
| 2675 |
+
{
|
| 2676 |
+
"epoch": 2.75,
|
| 2677 |
+
"learning_rate": 4.579835628218785e-06,
|
| 2678 |
+
"loss": 1.3061,
|
| 2679 |
+
"step": 103000
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 2.75,
|
| 2683 |
+
"eval_loss": 1.4136689901351929,
|
| 2684 |
+
"eval_runtime": 92.0252,
|
| 2685 |
+
"eval_samples_per_second": 162.227,
|
| 2686 |
+
"step": 103000
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 2.76,
|
| 2690 |
+
"learning_rate": 4.336014228615544e-06,
|
| 2691 |
+
"loss": 1.3456,
|
| 2692 |
+
"step": 103500
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 2.76,
|
| 2696 |
+
"eval_loss": 1.40234375,
|
| 2697 |
+
"eval_runtime": 92.0442,
|
| 2698 |
+
"eval_samples_per_second": 162.194,
|
| 2699 |
+
"step": 103500
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 2.78,
|
| 2703 |
+
"learning_rate": 4.091704208973018e-06,
|
| 2704 |
+
"loss": 1.2899,
|
| 2705 |
+
"step": 104000
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 2.78,
|
| 2709 |
+
"eval_loss": 1.3845499753952026,
|
| 2710 |
+
"eval_runtime": 91.7463,
|
| 2711 |
+
"eval_samples_per_second": 162.72,
|
| 2712 |
+
"step": 104000
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 2.79,
|
| 2716 |
+
"learning_rate": 3.8473941893304926e-06,
|
| 2717 |
+
"loss": 1.313,
|
| 2718 |
+
"step": 104500
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 2.79,
|
| 2722 |
+
"eval_loss": 1.3685582876205444,
|
| 2723 |
+
"eval_runtime": 91.9455,
|
| 2724 |
+
"eval_samples_per_second": 162.368,
|
| 2725 |
+
"step": 104500
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 2.8,
|
| 2729 |
+
"learning_rate": 3.6030841696879673e-06,
|
| 2730 |
+
"loss": 1.3106,
|
| 2731 |
+
"step": 105000
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 2.8,
|
| 2735 |
+
"eval_loss": 1.3997061252593994,
|
| 2736 |
+
"eval_runtime": 91.5804,
|
| 2737 |
+
"eval_samples_per_second": 163.015,
|
| 2738 |
+
"step": 105000
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 2.82,
|
| 2742 |
+
"learning_rate": 3.358774150045442e-06,
|
| 2743 |
+
"loss": 1.2682,
|
| 2744 |
+
"step": 105500
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"epoch": 2.82,
|
| 2748 |
+
"eval_loss": 1.3713297843933105,
|
| 2749 |
+
"eval_runtime": 91.77,
|
| 2750 |
+
"eval_samples_per_second": 162.678,
|
| 2751 |
+
"step": 105500
|
| 2752 |
+
},
|
| 2753 |
+
{
|
| 2754 |
+
"epoch": 2.83,
|
| 2755 |
+
"learning_rate": 3.1149527504422013e-06,
|
| 2756 |
+
"loss": 1.3131,
|
| 2757 |
+
"step": 106000
|
| 2758 |
+
},
|
| 2759 |
+
{
|
| 2760 |
+
"epoch": 2.83,
|
| 2761 |
+
"eval_loss": 1.381724238395691,
|
| 2762 |
+
"eval_runtime": 91.533,
|
| 2763 |
+
"eval_samples_per_second": 163.1,
|
| 2764 |
+
"step": 106000
|
| 2765 |
+
},
|
| 2766 |
+
{
|
| 2767 |
+
"epoch": 2.84,
|
| 2768 |
+
"learning_rate": 2.8706427307996756e-06,
|
| 2769 |
+
"loss": 1.3206,
|
| 2770 |
+
"step": 106500
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 2.84,
|
| 2774 |
+
"eval_loss": 1.3894230127334595,
|
| 2775 |
+
"eval_runtime": 91.9557,
|
| 2776 |
+
"eval_samples_per_second": 162.35,
|
| 2777 |
+
"step": 106500
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 2.86,
|
| 2781 |
+
"learning_rate": 2.62633271115715e-06,
|
| 2782 |
+
"loss": 1.3516,
|
| 2783 |
+
"step": 107000
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 2.86,
|
| 2787 |
+
"eval_loss": 1.3866136074066162,
|
| 2788 |
+
"eval_runtime": 91.8786,
|
| 2789 |
+
"eval_samples_per_second": 162.486,
|
| 2790 |
+
"step": 107000
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"epoch": 2.87,
|
| 2794 |
+
"learning_rate": 2.3820226915146242e-06,
|
| 2795 |
+
"loss": 1.271,
|
| 2796 |
+
"step": 107500
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 2.87,
|
| 2800 |
+
"eval_loss": 1.3788957595825195,
|
| 2801 |
+
"eval_runtime": 91.4774,
|
| 2802 |
+
"eval_samples_per_second": 163.199,
|
| 2803 |
+
"step": 107500
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 2.88,
|
| 2807 |
+
"learning_rate": 2.138201291911384e-06,
|
| 2808 |
+
"loss": 1.3023,
|
| 2809 |
+
"step": 108000
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 2.88,
|
| 2813 |
+
"eval_loss": 1.3791213035583496,
|
| 2814 |
+
"eval_runtime": 91.8238,
|
| 2815 |
+
"eval_samples_per_second": 162.583,
|
| 2816 |
+
"step": 108000
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 2.9,
|
| 2820 |
+
"learning_rate": 1.8938912722688583e-06,
|
| 2821 |
+
"loss": 1.3217,
|
| 2822 |
+
"step": 108500
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 2.9,
|
| 2826 |
+
"eval_loss": 1.393075704574585,
|
| 2827 |
+
"eval_runtime": 91.8262,
|
| 2828 |
+
"eval_samples_per_second": 162.579,
|
| 2829 |
+
"step": 108500
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 2.91,
|
| 2833 |
+
"learning_rate": 1.6495812526263328e-06,
|
| 2834 |
+
"loss": 1.3333,
|
| 2835 |
+
"step": 109000
|
| 2836 |
+
},
|
| 2837 |
+
{
|
| 2838 |
+
"epoch": 2.91,
|
| 2839 |
+
"eval_loss": 1.3756201267242432,
|
| 2840 |
+
"eval_runtime": 91.6059,
|
| 2841 |
+
"eval_samples_per_second": 162.97,
|
| 2842 |
+
"step": 109000
|
| 2843 |
+
},
|
| 2844 |
+
{
|
| 2845 |
+
"epoch": 2.92,
|
| 2846 |
+
"learning_rate": 1.4052712329838073e-06,
|
| 2847 |
+
"loss": 1.2818,
|
| 2848 |
+
"step": 109500
|
| 2849 |
+
},
|
| 2850 |
+
{
|
| 2851 |
+
"epoch": 2.92,
|
| 2852 |
+
"eval_loss": 1.3732881546020508,
|
| 2853 |
+
"eval_runtime": 91.7604,
|
| 2854 |
+
"eval_samples_per_second": 162.696,
|
| 2855 |
+
"step": 109500
|
| 2856 |
+
},
|
| 2857 |
+
{
|
| 2858 |
+
"epoch": 2.94,
|
| 2859 |
+
"learning_rate": 1.1614498333805667e-06,
|
| 2860 |
+
"loss": 1.2944,
|
| 2861 |
+
"step": 110000
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 2.94,
|
| 2865 |
+
"eval_loss": 1.3781006336212158,
|
| 2866 |
+
"eval_runtime": 91.6872,
|
| 2867 |
+
"eval_samples_per_second": 162.825,
|
| 2868 |
+
"step": 110000
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 2.95,
|
| 2872 |
+
"learning_rate": 9.171398137380411e-07,
|
| 2873 |
+
"loss": 1.312,
|
| 2874 |
+
"step": 110500
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 2.95,
|
| 2878 |
+
"eval_loss": 1.3845880031585693,
|
| 2879 |
+
"eval_runtime": 92.0248,
|
| 2880 |
+
"eval_samples_per_second": 162.228,
|
| 2881 |
+
"step": 110500
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 2.96,
|
| 2885 |
+
"learning_rate": 6.728297940955155e-07,
|
| 2886 |
+
"loss": 1.3098,
|
| 2887 |
+
"step": 111000
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 2.96,
|
| 2891 |
+
"eval_loss": 1.383412480354309,
|
| 2892 |
+
"eval_runtime": 92.0563,
|
| 2893 |
+
"eval_samples_per_second": 162.172,
|
| 2894 |
+
"step": 111000
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 2.98,
|
| 2898 |
+
"learning_rate": 4.285197744529899e-07,
|
| 2899 |
+
"loss": 1.2995,
|
| 2900 |
+
"step": 111500
|
| 2901 |
+
},
|
| 2902 |
+
{
|
| 2903 |
+
"epoch": 2.98,
|
| 2904 |
+
"eval_loss": 1.381857991218567,
|
| 2905 |
+
"eval_runtime": 91.7462,
|
| 2906 |
+
"eval_samples_per_second": 162.721,
|
| 2907 |
+
"step": 111500
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 2.99,
|
| 2911 |
+
"learning_rate": 1.842097548104643e-07,
|
| 2912 |
+
"loss": 1.2507,
|
| 2913 |
+
"step": 112000
|
| 2914 |
+
},
|
| 2915 |
+
{
|
| 2916 |
+
"epoch": 2.99,
|
| 2917 |
+
"eval_loss": 1.3710229396820068,
|
| 2918 |
+
"eval_runtime": 92.2003,
|
| 2919 |
+
"eval_samples_per_second": 161.919,
|
| 2920 |
+
"step": 112000
|
| 2921 |
+
},
|
| 2922 |
+
{
|
| 2923 |
+
"epoch": 3.0,
|
| 2924 |
+
"step": 112329,
|
| 2925 |
+
"total_flos": 15705683781120.0,
|
| 2926 |
+
"train_runtime": 32291.4207,
|
| 2927 |
+
"train_samples_per_second": 3.479
|
| 2928 |
+
}
|
| 2929 |
+
],
|
| 2930 |
+
"max_steps": 112329,
|
| 2931 |
+
"num_train_epochs": 3,
|
| 2932 |
+
"total_flos": 15705683781120.0,
|
| 2933 |
+
"trial_name": null,
|
| 2934 |
+
"trial_params": null
|
| 2935 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7b2ff3f718fd321dcba244b9f00a62600549c80a86e4e3608c6590059f5fde4
|
| 3 |
+
size 2415
|