Training in progress, step 72000, checkpoint
Browse files- checkpoint-72000/added_tokens.json +5 -0
- checkpoint-72000/config.json +46 -0
- checkpoint-72000/merges.txt +0 -0
- checkpoint-72000/optimizer.pt +3 -0
- checkpoint-72000/pytorch_model.bin +3 -0
- checkpoint-72000/rng_state.pth +3 -0
- checkpoint-72000/scheduler.pt +3 -0
- checkpoint-72000/special_tokens_map.json +6 -0
- checkpoint-72000/tokenizer_config.json +7 -0
- checkpoint-72000/trainer_state.json +1105 -0
- checkpoint-72000/training_args.bin +3 -0
- checkpoint-72000/vocab.json +0 -0
checkpoint-72000/added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<bos>": 40478,
|
| 3 |
+
"<eos>": 40479,
|
| 4 |
+
"<pad>": 40480
|
| 5 |
+
}
|
checkpoint-72000/config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai-gpt",
|
| 3 |
+
"afn": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"OpenAIGPTForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"id2label": {
|
| 10 |
+
"0": "entailment",
|
| 11 |
+
"1": "neutral",
|
| 12 |
+
"2": "contradiction"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"label2id": {
|
| 16 |
+
"contradiction": 2,
|
| 17 |
+
"entailment": 0,
|
| 18 |
+
"neutral": 1
|
| 19 |
+
},
|
| 20 |
+
"layer_norm_epsilon": 1e-05,
|
| 21 |
+
"model_type": "openai-gpt",
|
| 22 |
+
"n_ctx": 512,
|
| 23 |
+
"n_embd": 768,
|
| 24 |
+
"n_head": 16,
|
| 25 |
+
"n_layer": 12,
|
| 26 |
+
"n_positions": 512,
|
| 27 |
+
"n_special": 0,
|
| 28 |
+
"pad_token_id": 40480,
|
| 29 |
+
"predict_special_tokens": true,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"resid_pdrop": 0.1,
|
| 32 |
+
"summary_activation": null,
|
| 33 |
+
"summary_first_dropout": 0.1,
|
| 34 |
+
"summary_proj_to_labels": true,
|
| 35 |
+
"summary_type": "cls_index",
|
| 36 |
+
"summary_use_proj": true,
|
| 37 |
+
"task_specific_params": {
|
| 38 |
+
"text-generation": {
|
| 39 |
+
"do_sample": true,
|
| 40 |
+
"max_length": 50
|
| 41 |
+
}
|
| 42 |
+
},
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.33.0.dev0",
|
| 45 |
+
"vocab_size": 40481
|
| 46 |
+
}
|
checkpoint-72000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-72000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b3cbf2d43077066faebb19996cd05cd904c6a2966f227e4cb122a55f679ab13
|
| 3 |
+
size 932401605
|
checkpoint-72000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7c7e0973fc0164faf1aa1e83f1168d0a482d8792aa68281d4ec335ef8bce41b
|
| 3 |
+
size 466205145
|
checkpoint-72000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61d60a1145f26a9bd7cb9661639f94feb9bd18a7df8ee49299733949140b3748
|
| 3 |
+
size 14575
|
checkpoint-72000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0f6c1a9ffb956449bc025e408836d6adb7736f5f1fd67435b68545ccc65d2f9
|
| 3 |
+
size 627
|
checkpoint-72000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<bos>",
|
| 3 |
+
"eos_token": "<eos>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
checkpoint-72000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"model_max_length": 512,
|
| 4 |
+
"padding_side": "left",
|
| 5 |
+
"tokenizer_class": "OpenAIGPTTokenizer",
|
| 6 |
+
"unk_token": "<unk>"
|
| 7 |
+
}
|
checkpoint-72000/trainer_state.json
ADDED
|
@@ -0,0 +1,1105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9758180975914001,
|
| 3 |
+
"best_model_checkpoint": "/kaggle/output/checkpoint-68000",
|
| 4 |
+
"epoch": 2.9335071707953064,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 72000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 2.7777777777777777e-11,
|
| 14 |
+
"loss": 1.0722,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 2.7750000000000004e-08,
|
| 20 |
+
"loss": 1.1407,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"eval_accuracy": 0.32914171656686625,
|
| 26 |
+
"eval_loss": 1.1048731803894043,
|
| 27 |
+
"eval_runtime": 57.3781,
|
| 28 |
+
"eval_samples_per_second": 87.316,
|
| 29 |
+
"eval_steps_per_second": 10.928,
|
| 30 |
+
"step": 1000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08,
|
| 34 |
+
"learning_rate": 5.5527777777777784e-08,
|
| 35 |
+
"loss": 1.1253,
|
| 36 |
+
"step": 2000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.08,
|
| 40 |
+
"eval_accuracy": 0.3377245508982036,
|
| 41 |
+
"eval_loss": 1.1033366918563843,
|
| 42 |
+
"eval_runtime": 57.3237,
|
| 43 |
+
"eval_samples_per_second": 87.398,
|
| 44 |
+
"eval_steps_per_second": 10.938,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12,
|
| 49 |
+
"learning_rate": 8.327777777777778e-08,
|
| 50 |
+
"loss": 1.1179,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.12,
|
| 55 |
+
"eval_accuracy": 0.3502994011976048,
|
| 56 |
+
"eval_loss": 1.104222059249878,
|
| 57 |
+
"eval_runtime": 57.4527,
|
| 58 |
+
"eval_samples_per_second": 87.202,
|
| 59 |
+
"eval_steps_per_second": 10.913,
|
| 60 |
+
"step": 3000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.16,
|
| 64 |
+
"learning_rate": 1.1105555555555557e-07,
|
| 65 |
+
"loss": 1.1197,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.16,
|
| 70 |
+
"eval_accuracy": 0.3457085828343313,
|
| 71 |
+
"eval_loss": 1.1000728607177734,
|
| 72 |
+
"eval_runtime": 57.5257,
|
| 73 |
+
"eval_samples_per_second": 87.091,
|
| 74 |
+
"eval_steps_per_second": 10.899,
|
| 75 |
+
"step": 4000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.2,
|
| 79 |
+
"learning_rate": 1.3883333333333335e-07,
|
| 80 |
+
"loss": 1.1202,
|
| 81 |
+
"step": 5000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.2,
|
| 85 |
+
"eval_accuracy": 0.3383233532934132,
|
| 86 |
+
"eval_loss": 1.099381923675537,
|
| 87 |
+
"eval_runtime": 57.825,
|
| 88 |
+
"eval_samples_per_second": 86.641,
|
| 89 |
+
"eval_steps_per_second": 10.843,
|
| 90 |
+
"step": 5000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.24,
|
| 94 |
+
"learning_rate": 1.6661111111111112e-07,
|
| 95 |
+
"loss": 1.1166,
|
| 96 |
+
"step": 6000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.24,
|
| 100 |
+
"eval_accuracy": 0.35409181636726544,
|
| 101 |
+
"eval_loss": 1.0975825786590576,
|
| 102 |
+
"eval_runtime": 57.6509,
|
| 103 |
+
"eval_samples_per_second": 86.902,
|
| 104 |
+
"eval_steps_per_second": 10.876,
|
| 105 |
+
"step": 6000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.29,
|
| 109 |
+
"learning_rate": 1.9436111111111112e-07,
|
| 110 |
+
"loss": 1.1126,
|
| 111 |
+
"step": 7000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.29,
|
| 115 |
+
"eval_accuracy": 0.35508982035928144,
|
| 116 |
+
"eval_loss": 1.0957295894622803,
|
| 117 |
+
"eval_runtime": 57.5423,
|
| 118 |
+
"eval_samples_per_second": 87.066,
|
| 119 |
+
"eval_steps_per_second": 10.896,
|
| 120 |
+
"step": 7000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.33,
|
| 124 |
+
"learning_rate": 2.2213888888888891e-07,
|
| 125 |
+
"loss": 1.1091,
|
| 126 |
+
"step": 8000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.33,
|
| 130 |
+
"eval_accuracy": 0.36666666666666664,
|
| 131 |
+
"eval_loss": 1.093665599822998,
|
| 132 |
+
"eval_runtime": 57.2594,
|
| 133 |
+
"eval_samples_per_second": 87.497,
|
| 134 |
+
"eval_steps_per_second": 10.95,
|
| 135 |
+
"step": 8000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.37,
|
| 139 |
+
"learning_rate": 2.4988888888888893e-07,
|
| 140 |
+
"loss": 1.1069,
|
| 141 |
+
"step": 9000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.37,
|
| 145 |
+
"eval_accuracy": 0.35129740518962077,
|
| 146 |
+
"eval_loss": 1.1007317304611206,
|
| 147 |
+
"eval_runtime": 57.5122,
|
| 148 |
+
"eval_samples_per_second": 87.112,
|
| 149 |
+
"eval_steps_per_second": 10.902,
|
| 150 |
+
"step": 9000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.41,
|
| 154 |
+
"learning_rate": 2.776666666666667e-07,
|
| 155 |
+
"loss": 1.1054,
|
| 156 |
+
"step": 10000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.41,
|
| 160 |
+
"eval_accuracy": 0.38143712574850297,
|
| 161 |
+
"eval_loss": 1.092604398727417,
|
| 162 |
+
"eval_runtime": 57.5161,
|
| 163 |
+
"eval_samples_per_second": 87.106,
|
| 164 |
+
"eval_steps_per_second": 10.901,
|
| 165 |
+
"step": 10000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.45,
|
| 169 |
+
"learning_rate": 3.0541666666666667e-07,
|
| 170 |
+
"loss": 1.1041,
|
| 171 |
+
"step": 11000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.45,
|
| 175 |
+
"eval_accuracy": 0.37704590818363276,
|
| 176 |
+
"eval_loss": 1.0923383235931396,
|
| 177 |
+
"eval_runtime": 57.5839,
|
| 178 |
+
"eval_samples_per_second": 87.003,
|
| 179 |
+
"eval_steps_per_second": 10.888,
|
| 180 |
+
"step": 11000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.49,
|
| 184 |
+
"learning_rate": 3.3319444444444444e-07,
|
| 185 |
+
"loss": 1.1047,
|
| 186 |
+
"step": 12000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.49,
|
| 190 |
+
"eval_accuracy": 0.3914171656686627,
|
| 191 |
+
"eval_loss": 1.0889469385147095,
|
| 192 |
+
"eval_runtime": 57.877,
|
| 193 |
+
"eval_samples_per_second": 86.563,
|
| 194 |
+
"eval_steps_per_second": 10.833,
|
| 195 |
+
"step": 12000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.53,
|
| 199 |
+
"learning_rate": 3.6094444444444446e-07,
|
| 200 |
+
"loss": 1.1015,
|
| 201 |
+
"step": 13000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.53,
|
| 205 |
+
"eval_accuracy": 0.3437125748502994,
|
| 206 |
+
"eval_loss": 1.095380187034607,
|
| 207 |
+
"eval_runtime": 57.5214,
|
| 208 |
+
"eval_samples_per_second": 87.098,
|
| 209 |
+
"eval_steps_per_second": 10.9,
|
| 210 |
+
"step": 13000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.57,
|
| 214 |
+
"learning_rate": 3.8872222222222223e-07,
|
| 215 |
+
"loss": 1.0997,
|
| 216 |
+
"step": 14000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.57,
|
| 220 |
+
"eval_accuracy": 0.3596806387225549,
|
| 221 |
+
"eval_loss": 1.096056580543518,
|
| 222 |
+
"eval_runtime": 57.4747,
|
| 223 |
+
"eval_samples_per_second": 87.169,
|
| 224 |
+
"eval_steps_per_second": 10.909,
|
| 225 |
+
"step": 14000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.61,
|
| 229 |
+
"learning_rate": 4.1650000000000006e-07,
|
| 230 |
+
"loss": 1.1022,
|
| 231 |
+
"step": 15000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.61,
|
| 235 |
+
"eval_accuracy": 0.38882235528942116,
|
| 236 |
+
"eval_loss": 1.089142084121704,
|
| 237 |
+
"eval_runtime": 57.778,
|
| 238 |
+
"eval_samples_per_second": 86.711,
|
| 239 |
+
"eval_steps_per_second": 10.852,
|
| 240 |
+
"step": 15000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.65,
|
| 244 |
+
"learning_rate": 4.4427777777777783e-07,
|
| 245 |
+
"loss": 1.0985,
|
| 246 |
+
"step": 16000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.65,
|
| 250 |
+
"eval_accuracy": 0.3930139720558882,
|
| 251 |
+
"eval_loss": 1.0844948291778564,
|
| 252 |
+
"eval_runtime": 57.5695,
|
| 253 |
+
"eval_samples_per_second": 87.025,
|
| 254 |
+
"eval_steps_per_second": 10.891,
|
| 255 |
+
"step": 16000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.69,
|
| 259 |
+
"learning_rate": 4.7202777777777785e-07,
|
| 260 |
+
"loss": 1.0966,
|
| 261 |
+
"step": 17000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.69,
|
| 265 |
+
"eval_accuracy": 0.40459081836327343,
|
| 266 |
+
"eval_loss": 1.083156704902649,
|
| 267 |
+
"eval_runtime": 57.5224,
|
| 268 |
+
"eval_samples_per_second": 87.096,
|
| 269 |
+
"eval_steps_per_second": 10.9,
|
| 270 |
+
"step": 17000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.73,
|
| 274 |
+
"learning_rate": 4.998055555555556e-07,
|
| 275 |
+
"loss": 1.0985,
|
| 276 |
+
"step": 18000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.73,
|
| 280 |
+
"eval_accuracy": 0.4055888223552894,
|
| 281 |
+
"eval_loss": 1.0858113765716553,
|
| 282 |
+
"eval_runtime": 57.413,
|
| 283 |
+
"eval_samples_per_second": 87.263,
|
| 284 |
+
"eval_steps_per_second": 10.921,
|
| 285 |
+
"step": 18000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.77,
|
| 289 |
+
"learning_rate": 5.275277777777778e-07,
|
| 290 |
+
"loss": 1.0933,
|
| 291 |
+
"step": 19000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.77,
|
| 295 |
+
"eval_accuracy": 0.3996007984031936,
|
| 296 |
+
"eval_loss": 1.0827423334121704,
|
| 297 |
+
"eval_runtime": 57.2851,
|
| 298 |
+
"eval_samples_per_second": 87.457,
|
| 299 |
+
"eval_steps_per_second": 10.945,
|
| 300 |
+
"step": 19000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.81,
|
| 304 |
+
"learning_rate": 5.553055555555556e-07,
|
| 305 |
+
"loss": 1.094,
|
| 306 |
+
"step": 20000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.81,
|
| 310 |
+
"eval_accuracy": 0.4059880239520958,
|
| 311 |
+
"eval_loss": 1.0834325551986694,
|
| 312 |
+
"eval_runtime": 57.4875,
|
| 313 |
+
"eval_samples_per_second": 87.149,
|
| 314 |
+
"eval_steps_per_second": 10.907,
|
| 315 |
+
"step": 20000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.86,
|
| 319 |
+
"learning_rate": 5.830555555555556e-07,
|
| 320 |
+
"loss": 1.0924,
|
| 321 |
+
"step": 21000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.86,
|
| 325 |
+
"eval_accuracy": 0.3850299401197605,
|
| 326 |
+
"eval_loss": 1.0823787450790405,
|
| 327 |
+
"eval_runtime": 57.0913,
|
| 328 |
+
"eval_samples_per_second": 87.754,
|
| 329 |
+
"eval_steps_per_second": 10.982,
|
| 330 |
+
"step": 21000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.9,
|
| 334 |
+
"learning_rate": 6.108333333333333e-07,
|
| 335 |
+
"loss": 1.0894,
|
| 336 |
+
"step": 22000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.9,
|
| 340 |
+
"eval_accuracy": 0.4101796407185629,
|
| 341 |
+
"eval_loss": 1.0732710361480713,
|
| 342 |
+
"eval_runtime": 57.1315,
|
| 343 |
+
"eval_samples_per_second": 87.692,
|
| 344 |
+
"eval_steps_per_second": 10.975,
|
| 345 |
+
"step": 22000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.94,
|
| 349 |
+
"learning_rate": 6.386111111111112e-07,
|
| 350 |
+
"loss": 1.0812,
|
| 351 |
+
"step": 23000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.94,
|
| 355 |
+
"eval_accuracy": 0.43333333333333335,
|
| 356 |
+
"eval_loss": 1.063122034072876,
|
| 357 |
+
"eval_runtime": 57.1173,
|
| 358 |
+
"eval_samples_per_second": 87.714,
|
| 359 |
+
"eval_steps_per_second": 10.977,
|
| 360 |
+
"step": 23000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.98,
|
| 364 |
+
"learning_rate": 6.663611111111112e-07,
|
| 365 |
+
"loss": 1.0751,
|
| 366 |
+
"step": 24000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.98,
|
| 370 |
+
"eval_accuracy": 0.43972055888223555,
|
| 371 |
+
"eval_loss": 1.055448055267334,
|
| 372 |
+
"eval_runtime": 57.3035,
|
| 373 |
+
"eval_samples_per_second": 87.429,
|
| 374 |
+
"eval_steps_per_second": 10.942,
|
| 375 |
+
"step": 24000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.02,
|
| 379 |
+
"learning_rate": 6.94138888888889e-07,
|
| 380 |
+
"loss": 1.0724,
|
| 381 |
+
"step": 25000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.02,
|
| 385 |
+
"eval_accuracy": 0.436127744510978,
|
| 386 |
+
"eval_loss": 1.0547080039978027,
|
| 387 |
+
"eval_runtime": 57.4811,
|
| 388 |
+
"eval_samples_per_second": 87.159,
|
| 389 |
+
"eval_steps_per_second": 10.908,
|
| 390 |
+
"step": 25000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.06,
|
| 394 |
+
"learning_rate": 7.219166666666666e-07,
|
| 395 |
+
"loss": 1.0682,
|
| 396 |
+
"step": 26000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.06,
|
| 400 |
+
"eval_accuracy": 0.4297405189620758,
|
| 401 |
+
"eval_loss": 1.0550919771194458,
|
| 402 |
+
"eval_runtime": 57.4375,
|
| 403 |
+
"eval_samples_per_second": 87.225,
|
| 404 |
+
"eval_steps_per_second": 10.916,
|
| 405 |
+
"step": 26000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.1,
|
| 409 |
+
"learning_rate": 7.496666666666667e-07,
|
| 410 |
+
"loss": 1.0675,
|
| 411 |
+
"step": 27000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.1,
|
| 415 |
+
"eval_accuracy": 0.43812375249500995,
|
| 416 |
+
"eval_loss": 1.0507142543792725,
|
| 417 |
+
"eval_runtime": 57.1993,
|
| 418 |
+
"eval_samples_per_second": 87.589,
|
| 419 |
+
"eval_steps_per_second": 10.962,
|
| 420 |
+
"step": 27000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.14,
|
| 424 |
+
"learning_rate": 7.774444444444445e-07,
|
| 425 |
+
"loss": 1.0642,
|
| 426 |
+
"step": 28000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.14,
|
| 430 |
+
"eval_accuracy": 0.4291417165668663,
|
| 431 |
+
"eval_loss": 1.0485388040542603,
|
| 432 |
+
"eval_runtime": 57.1444,
|
| 433 |
+
"eval_samples_per_second": 87.673,
|
| 434 |
+
"eval_steps_per_second": 10.972,
|
| 435 |
+
"step": 28000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.18,
|
| 439 |
+
"learning_rate": 8.051944444444445e-07,
|
| 440 |
+
"loss": 1.0593,
|
| 441 |
+
"step": 29000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.18,
|
| 445 |
+
"eval_accuracy": 0.4413173652694611,
|
| 446 |
+
"eval_loss": 1.0438047647476196,
|
| 447 |
+
"eval_runtime": 57.4046,
|
| 448 |
+
"eval_samples_per_second": 87.275,
|
| 449 |
+
"eval_steps_per_second": 10.922,
|
| 450 |
+
"step": 29000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.22,
|
| 454 |
+
"learning_rate": 8.329722222222223e-07,
|
| 455 |
+
"loss": 1.0601,
|
| 456 |
+
"step": 30000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.22,
|
| 460 |
+
"eval_accuracy": 0.43852295409181635,
|
| 461 |
+
"eval_loss": 1.0402766466140747,
|
| 462 |
+
"eval_runtime": 57.3546,
|
| 463 |
+
"eval_samples_per_second": 87.351,
|
| 464 |
+
"eval_steps_per_second": 10.932,
|
| 465 |
+
"step": 30000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.26,
|
| 469 |
+
"learning_rate": 8.607222222222223e-07,
|
| 470 |
+
"loss": 1.0634,
|
| 471 |
+
"step": 31000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.26,
|
| 475 |
+
"eval_accuracy": 0.4481037924151697,
|
| 476 |
+
"eval_loss": 1.04641854763031,
|
| 477 |
+
"eval_runtime": 57.3392,
|
| 478 |
+
"eval_samples_per_second": 87.375,
|
| 479 |
+
"eval_steps_per_second": 10.935,
|
| 480 |
+
"step": 31000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.3,
|
| 484 |
+
"learning_rate": 8.885e-07,
|
| 485 |
+
"loss": 1.0589,
|
| 486 |
+
"step": 32000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.3,
|
| 490 |
+
"eval_accuracy": 0.4303393213572854,
|
| 491 |
+
"eval_loss": 1.0385456085205078,
|
| 492 |
+
"eval_runtime": 57.4244,
|
| 493 |
+
"eval_samples_per_second": 87.245,
|
| 494 |
+
"eval_steps_per_second": 10.919,
|
| 495 |
+
"step": 32000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.34,
|
| 499 |
+
"learning_rate": 9.162500000000001e-07,
|
| 500 |
+
"loss": 1.0543,
|
| 501 |
+
"step": 33000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.34,
|
| 505 |
+
"eval_accuracy": 0.4536926147704591,
|
| 506 |
+
"eval_loss": 1.033170223236084,
|
| 507 |
+
"eval_runtime": 57.3319,
|
| 508 |
+
"eval_samples_per_second": 87.386,
|
| 509 |
+
"eval_steps_per_second": 10.936,
|
| 510 |
+
"step": 33000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.39,
|
| 514 |
+
"learning_rate": 9.440277777777779e-07,
|
| 515 |
+
"loss": 1.0481,
|
| 516 |
+
"step": 34000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.39,
|
| 520 |
+
"eval_accuracy": 0.4489021956087824,
|
| 521 |
+
"eval_loss": 1.0322452783584595,
|
| 522 |
+
"eval_runtime": 57.6214,
|
| 523 |
+
"eval_samples_per_second": 86.947,
|
| 524 |
+
"eval_steps_per_second": 10.881,
|
| 525 |
+
"step": 34000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.43,
|
| 529 |
+
"learning_rate": 9.71777777777778e-07,
|
| 530 |
+
"loss": 1.0525,
|
| 531 |
+
"step": 35000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.43,
|
| 535 |
+
"eval_accuracy": 0.45069860279441115,
|
| 536 |
+
"eval_loss": 1.0243780612945557,
|
| 537 |
+
"eval_runtime": 57.4229,
|
| 538 |
+
"eval_samples_per_second": 87.247,
|
| 539 |
+
"eval_steps_per_second": 10.919,
|
| 540 |
+
"step": 35000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.47,
|
| 544 |
+
"learning_rate": 9.995555555555557e-07,
|
| 545 |
+
"loss": 1.05,
|
| 546 |
+
"step": 36000
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.47,
|
| 550 |
+
"eval_accuracy": 0.4598802395209581,
|
| 551 |
+
"eval_loss": 1.020882487297058,
|
| 552 |
+
"eval_runtime": 57.5219,
|
| 553 |
+
"eval_samples_per_second": 87.097,
|
| 554 |
+
"eval_steps_per_second": 10.9,
|
| 555 |
+
"step": 36000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.51,
|
| 559 |
+
"learning_rate": 1.0273055555555556e-06,
|
| 560 |
+
"loss": 1.0471,
|
| 561 |
+
"step": 37000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.51,
|
| 565 |
+
"eval_accuracy": 0.45189620758483035,
|
| 566 |
+
"eval_loss": 1.0195881128311157,
|
| 567 |
+
"eval_runtime": 57.338,
|
| 568 |
+
"eval_samples_per_second": 87.377,
|
| 569 |
+
"eval_steps_per_second": 10.935,
|
| 570 |
+
"step": 37000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.55,
|
| 574 |
+
"learning_rate": 1.0550833333333334e-06,
|
| 575 |
+
"loss": 1.0471,
|
| 576 |
+
"step": 38000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.55,
|
| 580 |
+
"eval_accuracy": 0.4532934131736527,
|
| 581 |
+
"eval_loss": 1.0168437957763672,
|
| 582 |
+
"eval_runtime": 57.6557,
|
| 583 |
+
"eval_samples_per_second": 86.895,
|
| 584 |
+
"eval_steps_per_second": 10.875,
|
| 585 |
+
"step": 38000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.59,
|
| 589 |
+
"learning_rate": 1.0828611111111111e-06,
|
| 590 |
+
"loss": 1.0467,
|
| 591 |
+
"step": 39000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.59,
|
| 595 |
+
"eval_accuracy": 0.4491017964071856,
|
| 596 |
+
"eval_loss": 1.020241379737854,
|
| 597 |
+
"eval_runtime": 57.5714,
|
| 598 |
+
"eval_samples_per_second": 87.022,
|
| 599 |
+
"eval_steps_per_second": 10.891,
|
| 600 |
+
"step": 39000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.63,
|
| 604 |
+
"learning_rate": 1.1106111111111112e-06,
|
| 605 |
+
"loss": 1.0378,
|
| 606 |
+
"step": 40000
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.63,
|
| 610 |
+
"eval_accuracy": 0.455688622754491,
|
| 611 |
+
"eval_loss": 1.0142648220062256,
|
| 612 |
+
"eval_runtime": 57.4804,
|
| 613 |
+
"eval_samples_per_second": 87.16,
|
| 614 |
+
"eval_steps_per_second": 10.908,
|
| 615 |
+
"step": 40000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.67,
|
| 619 |
+
"learning_rate": 1.138388888888889e-06,
|
| 620 |
+
"loss": 1.043,
|
| 621 |
+
"step": 41000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.67,
|
| 625 |
+
"eval_accuracy": 0.4600798403193613,
|
| 626 |
+
"eval_loss": 1.021972417831421,
|
| 627 |
+
"eval_runtime": 57.3072,
|
| 628 |
+
"eval_samples_per_second": 87.424,
|
| 629 |
+
"eval_steps_per_second": 10.941,
|
| 630 |
+
"step": 41000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.71,
|
| 634 |
+
"learning_rate": 1.166138888888889e-06,
|
| 635 |
+
"loss": 1.0358,
|
| 636 |
+
"step": 42000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.71,
|
| 640 |
+
"eval_accuracy": 0.4654690618762475,
|
| 641 |
+
"eval_loss": 1.007388710975647,
|
| 642 |
+
"eval_runtime": 57.1318,
|
| 643 |
+
"eval_samples_per_second": 87.692,
|
| 644 |
+
"eval_steps_per_second": 10.975,
|
| 645 |
+
"step": 42000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.75,
|
| 649 |
+
"learning_rate": 1.1939166666666668e-06,
|
| 650 |
+
"loss": 1.035,
|
| 651 |
+
"step": 43000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.75,
|
| 655 |
+
"eval_accuracy": 0.449500998003992,
|
| 656 |
+
"eval_loss": 1.032967448234558,
|
| 657 |
+
"eval_runtime": 57.4098,
|
| 658 |
+
"eval_samples_per_second": 87.267,
|
| 659 |
+
"eval_steps_per_second": 10.921,
|
| 660 |
+
"step": 43000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.79,
|
| 664 |
+
"learning_rate": 1.2216666666666667e-06,
|
| 665 |
+
"loss": 1.0396,
|
| 666 |
+
"step": 44000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.79,
|
| 670 |
+
"eval_accuracy": 0.4724550898203593,
|
| 671 |
+
"eval_loss": 1.0092512369155884,
|
| 672 |
+
"eval_runtime": 57.0784,
|
| 673 |
+
"eval_samples_per_second": 87.774,
|
| 674 |
+
"eval_steps_per_second": 10.985,
|
| 675 |
+
"step": 44000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.83,
|
| 679 |
+
"learning_rate": 1.2494444444444447e-06,
|
| 680 |
+
"loss": 1.0376,
|
| 681 |
+
"step": 45000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.83,
|
| 685 |
+
"eval_accuracy": 0.4728542914171657,
|
| 686 |
+
"eval_loss": 1.0083069801330566,
|
| 687 |
+
"eval_runtime": 57.0664,
|
| 688 |
+
"eval_samples_per_second": 87.792,
|
| 689 |
+
"eval_steps_per_second": 10.987,
|
| 690 |
+
"step": 45000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.87,
|
| 694 |
+
"learning_rate": 1.2771944444444445e-06,
|
| 695 |
+
"loss": 1.0362,
|
| 696 |
+
"step": 46000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.87,
|
| 700 |
+
"eval_accuracy": 0.47025948103792414,
|
| 701 |
+
"eval_loss": 1.0166049003601074,
|
| 702 |
+
"eval_runtime": 57.4608,
|
| 703 |
+
"eval_samples_per_second": 87.19,
|
| 704 |
+
"eval_steps_per_second": 10.912,
|
| 705 |
+
"step": 46000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.91,
|
| 709 |
+
"learning_rate": 1.3049722222222223e-06,
|
| 710 |
+
"loss": 1.0297,
|
| 711 |
+
"step": 47000
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.91,
|
| 715 |
+
"eval_accuracy": 0.4780439121756487,
|
| 716 |
+
"eval_loss": 1.0005145072937012,
|
| 717 |
+
"eval_runtime": 57.6118,
|
| 718 |
+
"eval_samples_per_second": 86.961,
|
| 719 |
+
"eval_steps_per_second": 10.883,
|
| 720 |
+
"step": 47000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.96,
|
| 724 |
+
"learning_rate": 1.3327222222222224e-06,
|
| 725 |
+
"loss": 1.0343,
|
| 726 |
+
"step": 48000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 1.96,
|
| 730 |
+
"eval_accuracy": 0.468063872255489,
|
| 731 |
+
"eval_loss": 1.0198135375976562,
|
| 732 |
+
"eval_runtime": 57.6866,
|
| 733 |
+
"eval_samples_per_second": 86.849,
|
| 734 |
+
"eval_steps_per_second": 10.869,
|
| 735 |
+
"step": 48000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.0,
|
| 739 |
+
"learning_rate": 1.3605000000000001e-06,
|
| 740 |
+
"loss": 1.0268,
|
| 741 |
+
"step": 49000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.0,
|
| 745 |
+
"eval_accuracy": 0.49860279441117766,
|
| 746 |
+
"eval_loss": 0.9925333857536316,
|
| 747 |
+
"eval_runtime": 57.3038,
|
| 748 |
+
"eval_samples_per_second": 87.429,
|
| 749 |
+
"eval_steps_per_second": 10.942,
|
| 750 |
+
"step": 49000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.04,
|
| 754 |
+
"learning_rate": 1.3882500000000002e-06,
|
| 755 |
+
"loss": 1.0277,
|
| 756 |
+
"step": 50000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.04,
|
| 760 |
+
"eval_accuracy": 0.4818363273453094,
|
| 761 |
+
"eval_loss": 1.0050703287124634,
|
| 762 |
+
"eval_runtime": 57.3896,
|
| 763 |
+
"eval_samples_per_second": 87.298,
|
| 764 |
+
"eval_steps_per_second": 10.925,
|
| 765 |
+
"step": 50000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.08,
|
| 769 |
+
"learning_rate": 1.416027777777778e-06,
|
| 770 |
+
"loss": 1.0272,
|
| 771 |
+
"step": 51000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.08,
|
| 775 |
+
"eval_accuracy": 0.4944111776447106,
|
| 776 |
+
"eval_loss": 0.992728590965271,
|
| 777 |
+
"eval_runtime": 57.0364,
|
| 778 |
+
"eval_samples_per_second": 87.839,
|
| 779 |
+
"eval_steps_per_second": 10.993,
|
| 780 |
+
"step": 51000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.12,
|
| 784 |
+
"learning_rate": 1.4437777777777779e-06,
|
| 785 |
+
"loss": 1.0236,
|
| 786 |
+
"step": 52000
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.12,
|
| 790 |
+
"eval_accuracy": 0.48223552894211574,
|
| 791 |
+
"eval_loss": 1.015480637550354,
|
| 792 |
+
"eval_runtime": 57.7958,
|
| 793 |
+
"eval_samples_per_second": 86.684,
|
| 794 |
+
"eval_steps_per_second": 10.849,
|
| 795 |
+
"step": 52000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.16,
|
| 799 |
+
"learning_rate": 1.4715555555555556e-06,
|
| 800 |
+
"loss": 1.0263,
|
| 801 |
+
"step": 53000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.16,
|
| 805 |
+
"eval_accuracy": 0.49640718562874253,
|
| 806 |
+
"eval_loss": 0.9908563494682312,
|
| 807 |
+
"eval_runtime": 57.3714,
|
| 808 |
+
"eval_samples_per_second": 87.326,
|
| 809 |
+
"eval_steps_per_second": 10.929,
|
| 810 |
+
"step": 53000
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.2,
|
| 814 |
+
"learning_rate": 1.4993055555555557e-06,
|
| 815 |
+
"loss": 1.0241,
|
| 816 |
+
"step": 54000
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.2,
|
| 820 |
+
"eval_accuracy": 0.49261477045908186,
|
| 821 |
+
"eval_loss": 0.9966863393783569,
|
| 822 |
+
"eval_runtime": 56.9916,
|
| 823 |
+
"eval_samples_per_second": 87.908,
|
| 824 |
+
"eval_steps_per_second": 11.002,
|
| 825 |
+
"step": 54000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.24,
|
| 829 |
+
"learning_rate": 1.5270833333333335e-06,
|
| 830 |
+
"loss": 1.0248,
|
| 831 |
+
"step": 55000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.24,
|
| 835 |
+
"eval_accuracy": 0.49800399201596807,
|
| 836 |
+
"eval_loss": 0.9907840490341187,
|
| 837 |
+
"eval_runtime": 57.3005,
|
| 838 |
+
"eval_samples_per_second": 87.434,
|
| 839 |
+
"eval_steps_per_second": 10.942,
|
| 840 |
+
"step": 55000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.28,
|
| 844 |
+
"learning_rate": 1.5548333333333335e-06,
|
| 845 |
+
"loss": 1.0175,
|
| 846 |
+
"step": 56000
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 2.28,
|
| 850 |
+
"eval_accuracy": 0.4658682634730539,
|
| 851 |
+
"eval_loss": 1.023374319076538,
|
| 852 |
+
"eval_runtime": 57.2038,
|
| 853 |
+
"eval_samples_per_second": 87.582,
|
| 854 |
+
"eval_steps_per_second": 10.961,
|
| 855 |
+
"step": 56000
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.32,
|
| 859 |
+
"learning_rate": 1.582611111111111e-06,
|
| 860 |
+
"loss": 1.0166,
|
| 861 |
+
"step": 57000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.32,
|
| 865 |
+
"eval_accuracy": 0.49560878243512974,
|
| 866 |
+
"eval_loss": 0.9929796457290649,
|
| 867 |
+
"eval_runtime": 57.3288,
|
| 868 |
+
"eval_samples_per_second": 87.391,
|
| 869 |
+
"eval_steps_per_second": 10.937,
|
| 870 |
+
"step": 57000
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.36,
|
| 874 |
+
"learning_rate": 1.6103611111111112e-06,
|
| 875 |
+
"loss": 1.0186,
|
| 876 |
+
"step": 58000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 2.36,
|
| 880 |
+
"eval_accuracy": 0.4936127744510978,
|
| 881 |
+
"eval_loss": 1.0019296407699585,
|
| 882 |
+
"eval_runtime": 57.0058,
|
| 883 |
+
"eval_samples_per_second": 87.886,
|
| 884 |
+
"eval_steps_per_second": 10.999,
|
| 885 |
+
"step": 58000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.4,
|
| 889 |
+
"learning_rate": 1.6381388888888892e-06,
|
| 890 |
+
"loss": 1.0148,
|
| 891 |
+
"step": 59000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.4,
|
| 895 |
+
"eval_accuracy": 0.5029940119760479,
|
| 896 |
+
"eval_loss": 0.9875914454460144,
|
| 897 |
+
"eval_runtime": 57.5353,
|
| 898 |
+
"eval_samples_per_second": 87.077,
|
| 899 |
+
"eval_steps_per_second": 10.898,
|
| 900 |
+
"step": 59000
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.44,
|
| 904 |
+
"learning_rate": 1.665888888888889e-06,
|
| 905 |
+
"loss": 1.0223,
|
| 906 |
+
"step": 60000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.44,
|
| 910 |
+
"eval_accuracy": 0.5055888223552895,
|
| 911 |
+
"eval_loss": 0.9868785738945007,
|
| 912 |
+
"eval_runtime": 57.6545,
|
| 913 |
+
"eval_samples_per_second": 86.897,
|
| 914 |
+
"eval_steps_per_second": 10.875,
|
| 915 |
+
"step": 60000
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.49,
|
| 919 |
+
"learning_rate": 1.6936666666666666e-06,
|
| 920 |
+
"loss": 1.018,
|
| 921 |
+
"step": 61000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.49,
|
| 925 |
+
"eval_accuracy": 0.5075848303393213,
|
| 926 |
+
"eval_loss": 0.984302282333374,
|
| 927 |
+
"eval_runtime": 57.7585,
|
| 928 |
+
"eval_samples_per_second": 86.74,
|
| 929 |
+
"eval_steps_per_second": 10.856,
|
| 930 |
+
"step": 61000
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 2.53,
|
| 934 |
+
"learning_rate": 1.7214166666666666e-06,
|
| 935 |
+
"loss": 1.019,
|
| 936 |
+
"step": 62000
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 2.53,
|
| 940 |
+
"eval_accuracy": 0.4944111776447106,
|
| 941 |
+
"eval_loss": 1.000705599784851,
|
| 942 |
+
"eval_runtime": 57.992,
|
| 943 |
+
"eval_samples_per_second": 86.391,
|
| 944 |
+
"eval_steps_per_second": 10.812,
|
| 945 |
+
"step": 62000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.57,
|
| 949 |
+
"learning_rate": 1.7491944444444446e-06,
|
| 950 |
+
"loss": 1.0142,
|
| 951 |
+
"step": 63000
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 2.57,
|
| 955 |
+
"eval_accuracy": 0.5051896207584831,
|
| 956 |
+
"eval_loss": 0.9869201183319092,
|
| 957 |
+
"eval_runtime": 57.9567,
|
| 958 |
+
"eval_samples_per_second": 86.444,
|
| 959 |
+
"eval_steps_per_second": 10.818,
|
| 960 |
+
"step": 63000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 2.61,
|
| 964 |
+
"learning_rate": 1.7769444444444447e-06,
|
| 965 |
+
"loss": 1.0155,
|
| 966 |
+
"step": 64000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 2.61,
|
| 970 |
+
"eval_accuracy": 0.5067864271457085,
|
| 971 |
+
"eval_loss": 0.9842376708984375,
|
| 972 |
+
"eval_runtime": 57.7146,
|
| 973 |
+
"eval_samples_per_second": 86.806,
|
| 974 |
+
"eval_steps_per_second": 10.864,
|
| 975 |
+
"step": 64000
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.65,
|
| 979 |
+
"learning_rate": 1.8047222222222223e-06,
|
| 980 |
+
"loss": 1.0153,
|
| 981 |
+
"step": 65000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 2.65,
|
| 985 |
+
"eval_accuracy": 0.5065868263473053,
|
| 986 |
+
"eval_loss": 0.9822392463684082,
|
| 987 |
+
"eval_runtime": 57.6853,
|
| 988 |
+
"eval_samples_per_second": 86.85,
|
| 989 |
+
"eval_steps_per_second": 10.869,
|
| 990 |
+
"step": 65000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.69,
|
| 994 |
+
"learning_rate": 1.8324722222222223e-06,
|
| 995 |
+
"loss": 1.015,
|
| 996 |
+
"step": 66000
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 2.69,
|
| 1000 |
+
"eval_accuracy": 0.5041916167664671,
|
| 1001 |
+
"eval_loss": 0.9796720743179321,
|
| 1002 |
+
"eval_runtime": 57.6908,
|
| 1003 |
+
"eval_samples_per_second": 86.842,
|
| 1004 |
+
"eval_steps_per_second": 10.868,
|
| 1005 |
+
"step": 66000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 2.73,
|
| 1009 |
+
"learning_rate": 1.86025e-06,
|
| 1010 |
+
"loss": 1.0139,
|
| 1011 |
+
"step": 67000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.73,
|
| 1015 |
+
"eval_accuracy": 0.48942115768463074,
|
| 1016 |
+
"eval_loss": 0.9911311268806458,
|
| 1017 |
+
"eval_runtime": 57.5982,
|
| 1018 |
+
"eval_samples_per_second": 86.982,
|
| 1019 |
+
"eval_steps_per_second": 10.886,
|
| 1020 |
+
"step": 67000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.77,
|
| 1024 |
+
"learning_rate": 1.8880000000000002e-06,
|
| 1025 |
+
"loss": 1.0147,
|
| 1026 |
+
"step": 68000
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 2.77,
|
| 1030 |
+
"eval_accuracy": 0.5145708582834332,
|
| 1031 |
+
"eval_loss": 0.9758180975914001,
|
| 1032 |
+
"eval_runtime": 57.5723,
|
| 1033 |
+
"eval_samples_per_second": 87.021,
|
| 1034 |
+
"eval_steps_per_second": 10.891,
|
| 1035 |
+
"step": 68000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 2.81,
|
| 1039 |
+
"learning_rate": 1.915777777777778e-06,
|
| 1040 |
+
"loss": 1.0116,
|
| 1041 |
+
"step": 69000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 2.81,
|
| 1045 |
+
"eval_accuracy": 0.5127744510978044,
|
| 1046 |
+
"eval_loss": 0.9761058688163757,
|
| 1047 |
+
"eval_runtime": 57.854,
|
| 1048 |
+
"eval_samples_per_second": 86.597,
|
| 1049 |
+
"eval_steps_per_second": 10.838,
|
| 1050 |
+
"step": 69000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.85,
|
| 1054 |
+
"learning_rate": 1.943527777777778e-06,
|
| 1055 |
+
"loss": 1.0134,
|
| 1056 |
+
"step": 70000
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 2.85,
|
| 1060 |
+
"eval_accuracy": 0.5103792415169661,
|
| 1061 |
+
"eval_loss": 0.9818203449249268,
|
| 1062 |
+
"eval_runtime": 57.9236,
|
| 1063 |
+
"eval_samples_per_second": 86.493,
|
| 1064 |
+
"eval_steps_per_second": 10.825,
|
| 1065 |
+
"step": 70000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.89,
|
| 1069 |
+
"learning_rate": 1.971305555555556e-06,
|
| 1070 |
+
"loss": 1.002,
|
| 1071 |
+
"step": 71000
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 2.89,
|
| 1075 |
+
"eval_accuracy": 0.5081836327345309,
|
| 1076 |
+
"eval_loss": 0.9803311228752136,
|
| 1077 |
+
"eval_runtime": 57.9829,
|
| 1078 |
+
"eval_samples_per_second": 86.405,
|
| 1079 |
+
"eval_steps_per_second": 10.814,
|
| 1080 |
+
"step": 71000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 2.93,
|
| 1084 |
+
"learning_rate": 1.9990555555555557e-06,
|
| 1085 |
+
"loss": 1.0102,
|
| 1086 |
+
"step": 72000
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 2.93,
|
| 1090 |
+
"eval_accuracy": 0.5013972055888224,
|
| 1091 |
+
"eval_loss": 0.9986135363578796,
|
| 1092 |
+
"eval_runtime": 57.9726,
|
| 1093 |
+
"eval_samples_per_second": 86.42,
|
| 1094 |
+
"eval_steps_per_second": 10.815,
|
| 1095 |
+
"step": 72000
|
| 1096 |
+
}
|
| 1097 |
+
],
|
| 1098 |
+
"logging_steps": 1000,
|
| 1099 |
+
"max_steps": 10000000,
|
| 1100 |
+
"num_train_epochs": 408,
|
| 1101 |
+
"save_steps": 1000,
|
| 1102 |
+
"total_flos": 1.505050467977134e+17,
|
| 1103 |
+
"trial_name": null,
|
| 1104 |
+
"trial_params": null
|
| 1105 |
+
}
|
checkpoint-72000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8af4e8c39ae573c6926360f2e6c7a6b3b1c14fa26faafd45dd19e679cb946fd
|
| 3 |
+
size 4091
|
checkpoint-72000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|