Commit
•
5014a75
1
Parent(s):
e80467c
Compatibile model codeparrot-small for code rationales (#1)
Browse files- Compatibile model codeparrot-small for code rationales (806fe9fe4264b9f59fec340f1851163cf72ec3af)
- config.json +40 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +828 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "codeparrot/codeparrot-small",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"reorder_and_upcast_attn": true,
|
| 22 |
+
"resid_pdrop": 0.1,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": true,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"summary_activation": null,
|
| 26 |
+
"summary_first_dropout": 0.1,
|
| 27 |
+
"summary_proj_to_labels": true,
|
| 28 |
+
"summary_type": "cls_index",
|
| 29 |
+
"summary_use_proj": true,
|
| 30 |
+
"task_specific_params": {
|
| 31 |
+
"text-generation": {
|
| 32 |
+
"do_sample": true,
|
| 33 |
+
"max_length": 50
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.11.0.dev0",
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 32768
|
| 40 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac06e1f8beb15229a24ed8a35eb084d4a0875056c261c86ffd77250d1c2edbfb
|
| 3 |
+
size 888151601
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5747a4feaf520dceb413fba771307a1746a925a050ef16e780e388c3b424df53
|
| 3 |
+
size 456677609
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e052b9a832ca9c86b049e34fb5cb7f6b8d8e4010d43a288c69c03e54c04091b
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95e902b248717ad1661f70606acf9e135032cc0946468749ebf3a54435035614
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "codeparrot/codeparrot-small", "tokenizer_class": "GPT2Tokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,828 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.002146082027547257,
|
| 5 |
+
"global_step": 29000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 5e-05,
|
| 13 |
+
"loss": 2.6876,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.0,
|
| 18 |
+
"eval_loss": 1.4209991693496704,
|
| 19 |
+
"eval_runtime": 29774.1937,
|
| 20 |
+
"eval_samples_per_second": 24.175,
|
| 21 |
+
"eval_steps_per_second": 6.044,
|
| 22 |
+
"step": 500
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.0,
|
| 26 |
+
"learning_rate": 5e-05,
|
| 27 |
+
"loss": 2.4255,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.0,
|
| 32 |
+
"eval_loss": 1.4117300510406494,
|
| 33 |
+
"eval_runtime": 29117.2533,
|
| 34 |
+
"eval_samples_per_second": 24.72,
|
| 35 |
+
"eval_steps_per_second": 6.18,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.0,
|
| 40 |
+
"learning_rate": 5e-05,
|
| 41 |
+
"loss": 2.2975,
|
| 42 |
+
"step": 1500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.0,
|
| 46 |
+
"eval_loss": 1.3992412090301514,
|
| 47 |
+
"eval_runtime": 29718.2883,
|
| 48 |
+
"eval_samples_per_second": 24.22,
|
| 49 |
+
"eval_steps_per_second": 6.055,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.0,
|
| 54 |
+
"learning_rate": 5e-05,
|
| 55 |
+
"loss": 2.3514,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.0,
|
| 60 |
+
"eval_loss": 1.4060639142990112,
|
| 61 |
+
"eval_runtime": 28900.2542,
|
| 62 |
+
"eval_samples_per_second": 24.906,
|
| 63 |
+
"eval_steps_per_second": 6.226,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.0,
|
| 68 |
+
"learning_rate": 5e-05,
|
| 69 |
+
"loss": 2.3757,
|
| 70 |
+
"step": 2500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.0,
|
| 74 |
+
"eval_loss": 1.399295687675476,
|
| 75 |
+
"eval_runtime": 29509.4537,
|
| 76 |
+
"eval_samples_per_second": 24.392,
|
| 77 |
+
"eval_steps_per_second": 6.098,
|
| 78 |
+
"step": 2500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.0,
|
| 82 |
+
"learning_rate": 5e-05,
|
| 83 |
+
"loss": 2.295,
|
| 84 |
+
"step": 3000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.0,
|
| 88 |
+
"eval_loss": 1.393278956413269,
|
| 89 |
+
"eval_runtime": 28449.3173,
|
| 90 |
+
"eval_samples_per_second": 25.301,
|
| 91 |
+
"eval_steps_per_second": 6.325,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.0,
|
| 96 |
+
"learning_rate": 5e-05,
|
| 97 |
+
"loss": 2.2565,
|
| 98 |
+
"step": 3500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.0,
|
| 102 |
+
"eval_loss": 1.3863052129745483,
|
| 103 |
+
"eval_runtime": 28789.7552,
|
| 104 |
+
"eval_samples_per_second": 25.001,
|
| 105 |
+
"eval_steps_per_second": 6.25,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.0,
|
| 110 |
+
"learning_rate": 5e-05,
|
| 111 |
+
"loss": 2.3095,
|
| 112 |
+
"step": 4000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.0,
|
| 116 |
+
"eval_loss": 1.3882980346679688,
|
| 117 |
+
"eval_runtime": 28567.3896,
|
| 118 |
+
"eval_samples_per_second": 25.196,
|
| 119 |
+
"eval_steps_per_second": 6.299,
|
| 120 |
+
"step": 4000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.0,
|
| 124 |
+
"learning_rate": 5e-05,
|
| 125 |
+
"loss": 2.3021,
|
| 126 |
+
"step": 4500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.0,
|
| 130 |
+
"eval_loss": 1.3863459825515747,
|
| 131 |
+
"eval_runtime": 28424.5337,
|
| 132 |
+
"eval_samples_per_second": 25.323,
|
| 133 |
+
"eval_steps_per_second": 6.331,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.0,
|
| 138 |
+
"learning_rate": 5e-05,
|
| 139 |
+
"loss": 2.2299,
|
| 140 |
+
"step": 5000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.0,
|
| 144 |
+
"eval_loss": 1.3776334524154663,
|
| 145 |
+
"eval_runtime": 28753.4447,
|
| 146 |
+
"eval_samples_per_second": 25.033,
|
| 147 |
+
"eval_steps_per_second": 6.258,
|
| 148 |
+
"step": 5000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.0,
|
| 152 |
+
"learning_rate": 5e-05,
|
| 153 |
+
"loss": 2.2306,
|
| 154 |
+
"step": 5500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.0,
|
| 158 |
+
"eval_loss": 1.3795045614242554,
|
| 159 |
+
"eval_runtime": 28113.3911,
|
| 160 |
+
"eval_samples_per_second": 25.603,
|
| 161 |
+
"eval_steps_per_second": 6.401,
|
| 162 |
+
"step": 5500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.0,
|
| 166 |
+
"learning_rate": 5e-05,
|
| 167 |
+
"loss": 2.2425,
|
| 168 |
+
"step": 6000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.0,
|
| 172 |
+
"eval_loss": 1.3737467527389526,
|
| 173 |
+
"eval_runtime": 28752.4369,
|
| 174 |
+
"eval_samples_per_second": 25.034,
|
| 175 |
+
"eval_steps_per_second": 6.258,
|
| 176 |
+
"step": 6000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.0,
|
| 180 |
+
"learning_rate": 5e-05,
|
| 181 |
+
"loss": 2.1932,
|
| 182 |
+
"step": 6500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.0,
|
| 186 |
+
"eval_loss": 1.3799411058425903,
|
| 187 |
+
"eval_runtime": 27577.5799,
|
| 188 |
+
"eval_samples_per_second": 26.1,
|
| 189 |
+
"eval_steps_per_second": 6.525,
|
| 190 |
+
"step": 6500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.0,
|
| 194 |
+
"learning_rate": 5e-05,
|
| 195 |
+
"loss": 2.2312,
|
| 196 |
+
"step": 7000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.0,
|
| 200 |
+
"eval_loss": 1.3715393543243408,
|
| 201 |
+
"eval_runtime": 28034.4873,
|
| 202 |
+
"eval_samples_per_second": 25.675,
|
| 203 |
+
"eval_steps_per_second": 6.419,
|
| 204 |
+
"step": 7000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.0,
|
| 208 |
+
"learning_rate": 5e-05,
|
| 209 |
+
"loss": 2.2841,
|
| 210 |
+
"step": 7500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.0,
|
| 214 |
+
"eval_loss": 1.3804839849472046,
|
| 215 |
+
"eval_runtime": 28127.7804,
|
| 216 |
+
"eval_samples_per_second": 25.59,
|
| 217 |
+
"eval_steps_per_second": 6.397,
|
| 218 |
+
"step": 7500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.0,
|
| 222 |
+
"learning_rate": 5e-05,
|
| 223 |
+
"loss": 2.1463,
|
| 224 |
+
"step": 8000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.0,
|
| 228 |
+
"eval_loss": 1.3776183128356934,
|
| 229 |
+
"eval_runtime": 27577.1163,
|
| 230 |
+
"eval_samples_per_second": 26.101,
|
| 231 |
+
"eval_steps_per_second": 6.525,
|
| 232 |
+
"step": 8000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.0,
|
| 236 |
+
"learning_rate": 5e-05,
|
| 237 |
+
"loss": 2.1313,
|
| 238 |
+
"step": 8500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.0,
|
| 242 |
+
"eval_loss": 1.3699731826782227,
|
| 243 |
+
"eval_runtime": 28190.8614,
|
| 244 |
+
"eval_samples_per_second": 25.533,
|
| 245 |
+
"eval_steps_per_second": 6.383,
|
| 246 |
+
"step": 8500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.0,
|
| 250 |
+
"learning_rate": 5e-05,
|
| 251 |
+
"loss": 2.2267,
|
| 252 |
+
"step": 9000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.0,
|
| 256 |
+
"eval_loss": 1.366495132446289,
|
| 257 |
+
"eval_runtime": 28103.2881,
|
| 258 |
+
"eval_samples_per_second": 25.612,
|
| 259 |
+
"eval_steps_per_second": 6.403,
|
| 260 |
+
"step": 9000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.0,
|
| 264 |
+
"learning_rate": 5e-05,
|
| 265 |
+
"loss": 2.1866,
|
| 266 |
+
"step": 9500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.0,
|
| 270 |
+
"eval_loss": 1.3763595819473267,
|
| 271 |
+
"eval_runtime": 27696.0614,
|
| 272 |
+
"eval_samples_per_second": 25.989,
|
| 273 |
+
"eval_steps_per_second": 6.497,
|
| 274 |
+
"step": 9500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.0,
|
| 278 |
+
"learning_rate": 5e-05,
|
| 279 |
+
"loss": 2.2347,
|
| 280 |
+
"step": 10000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.0,
|
| 284 |
+
"eval_loss": 1.3777934312820435,
|
| 285 |
+
"eval_runtime": 28118.8859,
|
| 286 |
+
"eval_samples_per_second": 25.598,
|
| 287 |
+
"eval_steps_per_second": 6.399,
|
| 288 |
+
"step": 10000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.0,
|
| 292 |
+
"learning_rate": 5e-05,
|
| 293 |
+
"loss": 2.1514,
|
| 294 |
+
"step": 10500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.0,
|
| 298 |
+
"eval_loss": 1.370295763015747,
|
| 299 |
+
"eval_runtime": 27665.6655,
|
| 300 |
+
"eval_samples_per_second": 26.017,
|
| 301 |
+
"eval_steps_per_second": 6.504,
|
| 302 |
+
"step": 10500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.0,
|
| 306 |
+
"learning_rate": 5e-05,
|
| 307 |
+
"loss": 2.2867,
|
| 308 |
+
"step": 11000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.0,
|
| 312 |
+
"eval_loss": 1.372216820716858,
|
| 313 |
+
"eval_runtime": 28029.069,
|
| 314 |
+
"eval_samples_per_second": 25.68,
|
| 315 |
+
"eval_steps_per_second": 6.42,
|
| 316 |
+
"step": 11000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.0,
|
| 320 |
+
"learning_rate": 5e-05,
|
| 321 |
+
"loss": 2.3031,
|
| 322 |
+
"step": 11500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.0,
|
| 326 |
+
"eval_loss": 1.3675533533096313,
|
| 327 |
+
"eval_runtime": 28060.4111,
|
| 328 |
+
"eval_samples_per_second": 25.651,
|
| 329 |
+
"eval_steps_per_second": 6.413,
|
| 330 |
+
"step": 11500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.0,
|
| 334 |
+
"learning_rate": 5e-05,
|
| 335 |
+
"loss": 2.2353,
|
| 336 |
+
"step": 12000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.0,
|
| 340 |
+
"eval_loss": 1.3742448091506958,
|
| 341 |
+
"eval_runtime": 27439.4619,
|
| 342 |
+
"eval_samples_per_second": 26.232,
|
| 343 |
+
"eval_steps_per_second": 6.558,
|
| 344 |
+
"step": 12000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.0,
|
| 348 |
+
"learning_rate": 5e-05,
|
| 349 |
+
"loss": 2.2022,
|
| 350 |
+
"step": 12500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.0,
|
| 354 |
+
"eval_loss": 1.3690038919448853,
|
| 355 |
+
"eval_runtime": 28177.5616,
|
| 356 |
+
"eval_samples_per_second": 25.545,
|
| 357 |
+
"eval_steps_per_second": 6.386,
|
| 358 |
+
"step": 12500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.0,
|
| 362 |
+
"learning_rate": 5e-05,
|
| 363 |
+
"loss": 2.1925,
|
| 364 |
+
"step": 13000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.0,
|
| 368 |
+
"eval_loss": 1.3660128116607666,
|
| 369 |
+
"eval_runtime": 28183.7194,
|
| 370 |
+
"eval_samples_per_second": 25.539,
|
| 371 |
+
"eval_steps_per_second": 6.385,
|
| 372 |
+
"step": 13000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.0,
|
| 376 |
+
"learning_rate": 5e-05,
|
| 377 |
+
"loss": 2.2097,
|
| 378 |
+
"step": 13500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.0,
|
| 382 |
+
"eval_loss": 1.3706327676773071,
|
| 383 |
+
"eval_runtime": 27638.252,
|
| 384 |
+
"eval_samples_per_second": 26.043,
|
| 385 |
+
"eval_steps_per_second": 6.511,
|
| 386 |
+
"step": 13500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.0,
|
| 390 |
+
"learning_rate": 5e-05,
|
| 391 |
+
"loss": 2.1606,
|
| 392 |
+
"step": 14000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.0,
|
| 396 |
+
"eval_loss": 1.369661569595337,
|
| 397 |
+
"eval_runtime": 28259.5204,
|
| 398 |
+
"eval_samples_per_second": 25.47,
|
| 399 |
+
"eval_steps_per_second": 6.368,
|
| 400 |
+
"step": 14000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.0,
|
| 404 |
+
"learning_rate": 5e-05,
|
| 405 |
+
"loss": 2.2216,
|
| 406 |
+
"step": 14500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.0,
|
| 410 |
+
"eval_loss": 1.368302822113037,
|
| 411 |
+
"eval_runtime": 28149.9769,
|
| 412 |
+
"eval_samples_per_second": 25.57,
|
| 413 |
+
"eval_steps_per_second": 6.392,
|
| 414 |
+
"step": 14500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.0,
|
| 418 |
+
"learning_rate": 5e-05,
|
| 419 |
+
"loss": 2.1916,
|
| 420 |
+
"step": 15000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.0,
|
| 424 |
+
"eval_loss": 1.3689770698547363,
|
| 425 |
+
"eval_runtime": 27702.5821,
|
| 426 |
+
"eval_samples_per_second": 25.983,
|
| 427 |
+
"eval_steps_per_second": 6.496,
|
| 428 |
+
"step": 15000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.0,
|
| 432 |
+
"learning_rate": 5e-05,
|
| 433 |
+
"loss": 2.2369,
|
| 434 |
+
"step": 15500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.0,
|
| 438 |
+
"eval_loss": 1.3695650100708008,
|
| 439 |
+
"eval_runtime": 28082.9192,
|
| 440 |
+
"eval_samples_per_second": 25.631,
|
| 441 |
+
"eval_steps_per_second": 6.408,
|
| 442 |
+
"step": 15500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.0,
|
| 446 |
+
"learning_rate": 5e-05,
|
| 447 |
+
"loss": 2.1862,
|
| 448 |
+
"step": 16000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.0,
|
| 452 |
+
"eval_loss": 1.3672432899475098,
|
| 453 |
+
"eval_runtime": 27790.3978,
|
| 454 |
+
"eval_samples_per_second": 25.9,
|
| 455 |
+
"eval_steps_per_second": 6.475,
|
| 456 |
+
"step": 16000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.0,
|
| 460 |
+
"learning_rate": 5e-05,
|
| 461 |
+
"loss": 2.1875,
|
| 462 |
+
"step": 16500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.0,
|
| 466 |
+
"eval_loss": 1.372326135635376,
|
| 467 |
+
"eval_runtime": 27957.8295,
|
| 468 |
+
"eval_samples_per_second": 25.745,
|
| 469 |
+
"eval_steps_per_second": 6.436,
|
| 470 |
+
"step": 16500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.0,
|
| 474 |
+
"learning_rate": 5e-05,
|
| 475 |
+
"loss": 2.2237,
|
| 476 |
+
"step": 17000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.0,
|
| 480 |
+
"eval_loss": 1.3708332777023315,
|
| 481 |
+
"eval_runtime": 28123.0687,
|
| 482 |
+
"eval_samples_per_second": 25.594,
|
| 483 |
+
"eval_steps_per_second": 6.399,
|
| 484 |
+
"step": 17000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 0.0,
|
| 488 |
+
"learning_rate": 5e-05,
|
| 489 |
+
"loss": 2.1123,
|
| 490 |
+
"step": 17500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.0,
|
| 494 |
+
"eval_loss": 1.3687807321548462,
|
| 495 |
+
"eval_runtime": 27597.4681,
|
| 496 |
+
"eval_samples_per_second": 26.082,
|
| 497 |
+
"eval_steps_per_second": 6.52,
|
| 498 |
+
"step": 17500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.0,
|
| 502 |
+
"learning_rate": 5e-05,
|
| 503 |
+
"loss": 2.1219,
|
| 504 |
+
"step": 18000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.0,
|
| 508 |
+
"eval_loss": 1.376206874847412,
|
| 509 |
+
"eval_runtime": 28127.0268,
|
| 510 |
+
"eval_samples_per_second": 25.59,
|
| 511 |
+
"eval_steps_per_second": 6.398,
|
| 512 |
+
"step": 18000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.0,
|
| 516 |
+
"learning_rate": 5e-05,
|
| 517 |
+
"loss": 2.1776,
|
| 518 |
+
"step": 18500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.0,
|
| 522 |
+
"eval_loss": 1.368283748626709,
|
| 523 |
+
"eval_runtime": 28116.6088,
|
| 524 |
+
"eval_samples_per_second": 25.6,
|
| 525 |
+
"eval_steps_per_second": 6.4,
|
| 526 |
+
"step": 18500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.0,
|
| 530 |
+
"learning_rate": 5e-05,
|
| 531 |
+
"loss": 2.1627,
|
| 532 |
+
"step": 19000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.0,
|
| 536 |
+
"eval_loss": 1.3710017204284668,
|
| 537 |
+
"eval_runtime": 27585.1366,
|
| 538 |
+
"eval_samples_per_second": 26.093,
|
| 539 |
+
"eval_steps_per_second": 6.523,
|
| 540 |
+
"step": 19000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.0,
|
| 544 |
+
"learning_rate": 5e-05,
|
| 545 |
+
"loss": 2.0627,
|
| 546 |
+
"step": 19500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.0,
|
| 550 |
+
"eval_loss": 1.3697084188461304,
|
| 551 |
+
"eval_runtime": 28272.5185,
|
| 552 |
+
"eval_samples_per_second": 25.459,
|
| 553 |
+
"eval_steps_per_second": 6.365,
|
| 554 |
+
"step": 19500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.0,
|
| 558 |
+
"learning_rate": 5e-05,
|
| 559 |
+
"loss": 2.0632,
|
| 560 |
+
"step": 20000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.0,
|
| 564 |
+
"eval_loss": 1.3792474269866943,
|
| 565 |
+
"eval_runtime": 28381.2307,
|
| 566 |
+
"eval_samples_per_second": 25.361,
|
| 567 |
+
"eval_steps_per_second": 6.34,
|
| 568 |
+
"step": 20000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.0,
|
| 572 |
+
"learning_rate": 5e-05,
|
| 573 |
+
"loss": 2.2426,
|
| 574 |
+
"step": 20500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.0,
|
| 578 |
+
"eval_loss": 1.373166799545288,
|
| 579 |
+
"eval_runtime": 28634.6137,
|
| 580 |
+
"eval_samples_per_second": 25.137,
|
| 581 |
+
"eval_steps_per_second": 6.284,
|
| 582 |
+
"step": 20500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.0,
|
| 586 |
+
"learning_rate": 5e-05,
|
| 587 |
+
"loss": 2.1263,
|
| 588 |
+
"step": 21000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.0,
|
| 592 |
+
"eval_loss": 1.3743404150009155,
|
| 593 |
+
"eval_runtime": 28674.6776,
|
| 594 |
+
"eval_samples_per_second": 25.102,
|
| 595 |
+
"eval_steps_per_second": 6.275,
|
| 596 |
+
"step": 21000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.0,
|
| 600 |
+
"learning_rate": 5e-05,
|
| 601 |
+
"loss": 2.1131,
|
| 602 |
+
"step": 21500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.0,
|
| 606 |
+
"eval_loss": 1.3682280778884888,
|
| 607 |
+
"eval_runtime": 28099.2766,
|
| 608 |
+
"eval_samples_per_second": 25.616,
|
| 609 |
+
"eval_steps_per_second": 6.404,
|
| 610 |
+
"step": 21500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.0,
|
| 614 |
+
"learning_rate": 5e-05,
|
| 615 |
+
"loss": 2.0595,
|
| 616 |
+
"step": 22000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.0,
|
| 620 |
+
"eval_loss": 1.3719111680984497,
|
| 621 |
+
"eval_runtime": 28695.4529,
|
| 622 |
+
"eval_samples_per_second": 25.084,
|
| 623 |
+
"eval_steps_per_second": 6.271,
|
| 624 |
+
"step": 22000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.0,
|
| 628 |
+
"learning_rate": 5e-05,
|
| 629 |
+
"loss": 2.1468,
|
| 630 |
+
"step": 22500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.0,
|
| 634 |
+
"eval_loss": 1.3663983345031738,
|
| 635 |
+
"eval_runtime": 28026.4183,
|
| 636 |
+
"eval_samples_per_second": 25.682,
|
| 637 |
+
"eval_steps_per_second": 6.421,
|
| 638 |
+
"step": 22500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.0,
|
| 642 |
+
"learning_rate": 5e-05,
|
| 643 |
+
"loss": 2.184,
|
| 644 |
+
"step": 23000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.0,
|
| 648 |
+
"eval_loss": 1.3723489046096802,
|
| 649 |
+
"eval_runtime": 28690.9854,
|
| 650 |
+
"eval_samples_per_second": 25.087,
|
| 651 |
+
"eval_steps_per_second": 6.272,
|
| 652 |
+
"step": 23000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 0.0,
|
| 656 |
+
"learning_rate": 5e-05,
|
| 657 |
+
"loss": 2.1262,
|
| 658 |
+
"step": 23500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.0,
|
| 662 |
+
"eval_loss": 1.3714051246643066,
|
| 663 |
+
"eval_runtime": 28156.2291,
|
| 664 |
+
"eval_samples_per_second": 25.564,
|
| 665 |
+
"eval_steps_per_second": 6.391,
|
| 666 |
+
"step": 23500
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.0,
|
| 670 |
+
"learning_rate": 5e-05,
|
| 671 |
+
"loss": 2.1758,
|
| 672 |
+
"step": 24000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.0,
|
| 676 |
+
"eval_loss": 1.368726134300232,
|
| 677 |
+
"eval_runtime": 28657.2462,
|
| 678 |
+
"eval_samples_per_second": 25.117,
|
| 679 |
+
"eval_steps_per_second": 6.279,
|
| 680 |
+
"step": 24000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.0,
|
| 684 |
+
"learning_rate": 5e-05,
|
| 685 |
+
"loss": 2.0438,
|
| 686 |
+
"step": 24500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.0,
|
| 690 |
+
"eval_loss": 1.3730684518814087,
|
| 691 |
+
"eval_runtime": 28686.5378,
|
| 692 |
+
"eval_samples_per_second": 25.091,
|
| 693 |
+
"eval_steps_per_second": 6.273,
|
| 694 |
+
"step": 24500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.0,
|
| 698 |
+
"learning_rate": 5e-05,
|
| 699 |
+
"loss": 2.1404,
|
| 700 |
+
"step": 25000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.0,
|
| 704 |
+
"eval_loss": 1.3706409931182861,
|
| 705 |
+
"eval_runtime": 28123.1244,
|
| 706 |
+
"eval_samples_per_second": 25.594,
|
| 707 |
+
"eval_steps_per_second": 6.399,
|
| 708 |
+
"step": 25000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.0,
|
| 712 |
+
"learning_rate": 5e-05,
|
| 713 |
+
"loss": 2.1135,
|
| 714 |
+
"step": 25500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.0,
|
| 718 |
+
"eval_loss": 1.3763220310211182,
|
| 719 |
+
"eval_runtime": 28682.6176,
|
| 720 |
+
"eval_samples_per_second": 25.095,
|
| 721 |
+
"eval_steps_per_second": 6.274,
|
| 722 |
+
"step": 25500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.0,
|
| 726 |
+
"learning_rate": 5e-05,
|
| 727 |
+
"loss": 2.0536,
|
| 728 |
+
"step": 26000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.0,
|
| 732 |
+
"eval_loss": 1.3709115982055664,
|
| 733 |
+
"eval_runtime": 28032.6358,
|
| 734 |
+
"eval_samples_per_second": 25.677,
|
| 735 |
+
"eval_steps_per_second": 6.419,
|
| 736 |
+
"step": 26000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.0,
|
| 740 |
+
"learning_rate": 5e-05,
|
| 741 |
+
"loss": 2.1203,
|
| 742 |
+
"step": 26500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.0,
|
| 746 |
+
"eval_loss": 1.3710169792175293,
|
| 747 |
+
"eval_runtime": 28678.3157,
|
| 748 |
+
"eval_samples_per_second": 25.099,
|
| 749 |
+
"eval_steps_per_second": 6.275,
|
| 750 |
+
"step": 26500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.0,
|
| 754 |
+
"learning_rate": 5e-05,
|
| 755 |
+
"loss": 2.0784,
|
| 756 |
+
"step": 27000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.0,
|
| 760 |
+
"eval_loss": 1.370123028755188,
|
| 761 |
+
"eval_runtime": 28008.2176,
|
| 762 |
+
"eval_samples_per_second": 25.699,
|
| 763 |
+
"eval_steps_per_second": 6.425,
|
| 764 |
+
"step": 27000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.0,
|
| 768 |
+
"learning_rate": 5e-05,
|
| 769 |
+
"loss": 2.0521,
|
| 770 |
+
"step": 27500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.0,
|
| 774 |
+
"eval_loss": 1.3733536005020142,
|
| 775 |
+
"eval_runtime": 17990.0293,
|
| 776 |
+
"eval_samples_per_second": 40.01,
|
| 777 |
+
"eval_steps_per_second": 10.003,
|
| 778 |
+
"step": 27500
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.0,
|
| 782 |
+
"learning_rate": 5e-05,
|
| 783 |
+
"loss": 2.1773,
|
| 784 |
+
"step": 28000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.0,
|
| 788 |
+
"eval_loss": 1.3757646083831787,
|
| 789 |
+
"eval_runtime": 18000.6521,
|
| 790 |
+
"eval_samples_per_second": 39.987,
|
| 791 |
+
"eval_steps_per_second": 9.997,
|
| 792 |
+
"step": 28000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.0,
|
| 796 |
+
"learning_rate": 5e-05,
|
| 797 |
+
"loss": 2.1688,
|
| 798 |
+
"step": 28500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.0,
|
| 802 |
+
"eval_loss": 1.3776638507843018,
|
| 803 |
+
"eval_runtime": 17989.8584,
|
| 804 |
+
"eval_samples_per_second": 40.011,
|
| 805 |
+
"eval_steps_per_second": 10.003,
|
| 806 |
+
"step": 28500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.0,
|
| 810 |
+
"learning_rate": 5e-05,
|
| 811 |
+
"loss": 2.0855,
|
| 812 |
+
"step": 29000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.0,
|
| 816 |
+
"eval_loss": 1.3749734163284302,
|
| 817 |
+
"eval_runtime": 17990.6544,
|
| 818 |
+
"eval_samples_per_second": 40.009,
|
| 819 |
+
"eval_steps_per_second": 10.002,
|
| 820 |
+
"step": 29000
|
| 821 |
+
}
|
| 822 |
+
],
|
| 823 |
+
"max_steps": 30000,
|
| 824 |
+
"num_train_epochs": 1,
|
| 825 |
+
"total_flos": 1.5154937856e+16,
|
| 826 |
+
"trial_name": null,
|
| 827 |
+
"trial_params": null
|
| 828 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:787e1daf7779e9459fcfaef465541d7afcd7dea8b1bf9560c3af7958defad081
|
| 3 |
+
size 2735
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|