Training in progress, step 1000, checkpoint
Browse files- checkpoint-1000/config.json +36 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +11 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer_config.json +72 -0
- checkpoint-1000/trainer_state.json +637 -0
- checkpoint-1000/training_args.bin +3 -0
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/polyglot-ko-1.3b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": 0.1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout": 0.0,
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 8192,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-05,
|
| 22 |
+
"max_position_embeddings": 2048,
|
| 23 |
+
"model_type": "gpt_neox",
|
| 24 |
+
"num_attention_heads": 16,
|
| 25 |
+
"num_hidden_layers": 24,
|
| 26 |
+
"pad_token_id": 2,
|
| 27 |
+
"rope_scaling": null,
|
| 28 |
+
"rotary_emb_base": 10000,
|
| 29 |
+
"rotary_pct": 0.5,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.34.1",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"use_parallel_residual": true,
|
| 35 |
+
"vocab_size": 30080
|
| 36 |
+
}
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e59fda1c0328c4b4003081ae66841109b803fc9ebe500710adfef8b37a725fa
|
| 3 |
+
size 10161845830
|
checkpoint-1000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1193f1fff7ef1810d0b0f2ab6da502b7712d60830c694b0eb933bc65d6d5133
|
| 3 |
+
size 5080945162
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc2a8c38c08f1c54af11f6e56ce09e99031f4aed646720481429c722ff84dcf0
|
| 3 |
+
size 14308
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:540f743368648583bfbe93f831faaa59204ebbbad409be2aa0a617b922c9376a
|
| 3 |
+
size 1064
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|sep|>",
|
| 5 |
+
"<|acc|>",
|
| 6 |
+
"<|tel|>",
|
| 7 |
+
"<|rrn|>"
|
| 8 |
+
],
|
| 9 |
+
"eos_token": "<|endoftext|>",
|
| 10 |
+
"pad_token": "<|endoftext|>"
|
| 11 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<|unused0|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|unused1|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<|endoftext|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<|sep|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"30000": {
|
| 36 |
+
"content": "<|acc|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30001": {
|
| 44 |
+
"content": "<|tel|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"30002": {
|
| 52 |
+
"content": "<|rrn|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"additional_special_tokens": [
|
| 61 |
+
"<|endoftext|>",
|
| 62 |
+
"<|sep|>",
|
| 63 |
+
"<|acc|>",
|
| 64 |
+
"<|tel|>",
|
| 65 |
+
"<|rrn|>"
|
| 66 |
+
],
|
| 67 |
+
"clean_up_tokenization_spaces": true,
|
| 68 |
+
"eos_token": "<|endoftext|>",
|
| 69 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 70 |
+
"pad_token": "<|endoftext|>",
|
| 71 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 72 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,637 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1425801300330786,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 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": 8.999954848325688e-06,
|
| 14 |
+
"loss": 0.7277,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 8.999819394208827e-06,
|
| 20 |
+
"loss": 0.6455,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0,
|
| 25 |
+
"learning_rate": 8.999593640367633e-06,
|
| 26 |
+
"loss": 0.5428,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 8.9992775913324e-06,
|
| 32 |
+
"loss": 0.3486,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 8.998871253445414e-06,
|
| 38 |
+
"loss": 0.3524,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.01,
|
| 43 |
+
"learning_rate": 8.998374634860822e-06,
|
| 44 |
+
"loss": 0.2701,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01,
|
| 49 |
+
"learning_rate": 8.997787745544478e-06,
|
| 50 |
+
"loss": 0.2106,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"learning_rate": 8.997110597273727e-06,
|
| 56 |
+
"loss": 0.2596,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.01,
|
| 61 |
+
"learning_rate": 8.996343203637181e-06,
|
| 62 |
+
"loss": 0.2015,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.01,
|
| 67 |
+
"learning_rate": 8.995485580034448e-06,
|
| 68 |
+
"loss": 0.2462,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.02,
|
| 73 |
+
"learning_rate": 8.99453774367581e-06,
|
| 74 |
+
"loss": 0.2172,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.02,
|
| 79 |
+
"learning_rate": 8.993499713581887e-06,
|
| 80 |
+
"loss": 0.2655,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.02,
|
| 85 |
+
"learning_rate": 8.992371510583257e-06,
|
| 86 |
+
"loss": 0.1823,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02,
|
| 91 |
+
"learning_rate": 8.991153157320033e-06,
|
| 92 |
+
"loss": 0.227,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.02,
|
| 97 |
+
"learning_rate": 8.989844678241412e-06,
|
| 98 |
+
"loss": 0.2243,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.02,
|
| 103 |
+
"learning_rate": 8.988446099605179e-06,
|
| 104 |
+
"loss": 0.1787,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.02,
|
| 109 |
+
"learning_rate": 8.986957449477188e-06,
|
| 110 |
+
"loss": 0.2211,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.03,
|
| 115 |
+
"learning_rate": 8.98537875773079e-06,
|
| 116 |
+
"loss": 0.1683,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.03,
|
| 121 |
+
"learning_rate": 8.983710056046243e-06,
|
| 122 |
+
"loss": 0.1879,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.03,
|
| 127 |
+
"learning_rate": 8.98195137791007e-06,
|
| 128 |
+
"loss": 0.1809,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.03,
|
| 133 |
+
"learning_rate": 8.980102758614384e-06,
|
| 134 |
+
"loss": 0.2204,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.03,
|
| 139 |
+
"learning_rate": 8.978164235256191e-06,
|
| 140 |
+
"loss": 0.189,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.03,
|
| 145 |
+
"learning_rate": 8.976135846736634e-06,
|
| 146 |
+
"loss": 0.1389,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.03,
|
| 151 |
+
"learning_rate": 8.97401763376022e-06,
|
| 152 |
+
"loss": 0.1231,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.04,
|
| 157 |
+
"learning_rate": 8.971809638833998e-06,
|
| 158 |
+
"loss": 0.2018,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.04,
|
| 163 |
+
"learning_rate": 8.96951190626671e-06,
|
| 164 |
+
"loss": 0.1271,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.04,
|
| 169 |
+
"learning_rate": 8.967124482167896e-06,
|
| 170 |
+
"loss": 0.1364,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.04,
|
| 175 |
+
"learning_rate": 8.964647414446981e-06,
|
| 176 |
+
"loss": 0.1658,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.04,
|
| 181 |
+
"learning_rate": 8.9620807528123e-06,
|
| 182 |
+
"loss": 0.1479,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.04,
|
| 187 |
+
"learning_rate": 8.959424548770104e-06,
|
| 188 |
+
"loss": 0.1353,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.04,
|
| 193 |
+
"learning_rate": 8.95667885562353e-06,
|
| 194 |
+
"loss": 0.1761,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.05,
|
| 199 |
+
"learning_rate": 8.953843728471533e-06,
|
| 200 |
+
"loss": 0.1391,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.05,
|
| 205 |
+
"learning_rate": 8.950919224207774e-06,
|
| 206 |
+
"loss": 0.1776,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.05,
|
| 211 |
+
"learning_rate": 8.94790540151948e-06,
|
| 212 |
+
"loss": 0.2089,
|
| 213 |
+
"step": 340
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.05,
|
| 217 |
+
"learning_rate": 8.94480232088627e-06,
|
| 218 |
+
"loss": 0.1368,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.05,
|
| 223 |
+
"learning_rate": 8.941610044578937e-06,
|
| 224 |
+
"loss": 0.1501,
|
| 225 |
+
"step": 360
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.05,
|
| 229 |
+
"learning_rate": 8.938328636658202e-06,
|
| 230 |
+
"loss": 0.1807,
|
| 231 |
+
"step": 370
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.05,
|
| 235 |
+
"learning_rate": 8.934958162973425e-06,
|
| 236 |
+
"loss": 0.13,
|
| 237 |
+
"step": 380
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.06,
|
| 241 |
+
"learning_rate": 8.931498691161287e-06,
|
| 242 |
+
"loss": 0.1437,
|
| 243 |
+
"step": 390
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.06,
|
| 247 |
+
"learning_rate": 8.92795029064443e-06,
|
| 248 |
+
"loss": 0.0828,
|
| 249 |
+
"step": 400
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.06,
|
| 253 |
+
"learning_rate": 8.924313032630063e-06,
|
| 254 |
+
"loss": 0.1041,
|
| 255 |
+
"step": 410
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.06,
|
| 259 |
+
"learning_rate": 8.920586990108539e-06,
|
| 260 |
+
"loss": 0.2663,
|
| 261 |
+
"step": 420
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.06,
|
| 265 |
+
"learning_rate": 8.916772237851882e-06,
|
| 266 |
+
"loss": 0.2055,
|
| 267 |
+
"step": 430
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.06,
|
| 271 |
+
"learning_rate": 8.912868852412294e-06,
|
| 272 |
+
"loss": 0.151,
|
| 273 |
+
"step": 440
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.06,
|
| 277 |
+
"learning_rate": 8.908876912120614e-06,
|
| 278 |
+
"loss": 0.1638,
|
| 279 |
+
"step": 450
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.07,
|
| 283 |
+
"learning_rate": 8.904796497084747e-06,
|
| 284 |
+
"loss": 0.1399,
|
| 285 |
+
"step": 460
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.07,
|
| 289 |
+
"learning_rate": 8.900627689188059e-06,
|
| 290 |
+
"loss": 0.1615,
|
| 291 |
+
"step": 470
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.07,
|
| 295 |
+
"learning_rate": 8.89637057208773e-06,
|
| 296 |
+
"loss": 0.1209,
|
| 297 |
+
"step": 480
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.07,
|
| 301 |
+
"learning_rate": 8.892025231213077e-06,
|
| 302 |
+
"loss": 0.1605,
|
| 303 |
+
"step": 490
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.07,
|
| 307 |
+
"learning_rate": 8.887591753763842e-06,
|
| 308 |
+
"loss": 0.124,
|
| 309 |
+
"step": 500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.07,
|
| 313 |
+
"eval_accuracy": 0.0,
|
| 314 |
+
"eval_loss": 0.13451002538204193,
|
| 315 |
+
"eval_runtime": 446.6893,
|
| 316 |
+
"eval_samples_per_second": 52.338,
|
| 317 |
+
"eval_steps_per_second": 8.724,
|
| 318 |
+
"step": 500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.07,
|
| 322 |
+
"learning_rate": 8.883070228708436e-06,
|
| 323 |
+
"loss": 0.1045,
|
| 324 |
+
"step": 510
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.07,
|
| 328 |
+
"learning_rate": 8.878460746782163e-06,
|
| 329 |
+
"loss": 0.2208,
|
| 330 |
+
"step": 520
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.08,
|
| 334 |
+
"learning_rate": 8.873763400485387e-06,
|
| 335 |
+
"loss": 0.1483,
|
| 336 |
+
"step": 530
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.08,
|
| 340 |
+
"learning_rate": 8.868978284081688e-06,
|
| 341 |
+
"loss": 0.1322,
|
| 342 |
+
"step": 540
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.08,
|
| 346 |
+
"learning_rate": 8.864105493595962e-06,
|
| 347 |
+
"loss": 0.1227,
|
| 348 |
+
"step": 550
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.08,
|
| 352 |
+
"learning_rate": 8.859145126812497e-06,
|
| 353 |
+
"loss": 0.1371,
|
| 354 |
+
"step": 560
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.08,
|
| 358 |
+
"learning_rate": 8.854097283273012e-06,
|
| 359 |
+
"loss": 0.1909,
|
| 360 |
+
"step": 570
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.08,
|
| 364 |
+
"learning_rate": 8.848962064274655e-06,
|
| 365 |
+
"loss": 0.0993,
|
| 366 |
+
"step": 580
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.08,
|
| 370 |
+
"learning_rate": 8.843739572867977e-06,
|
| 371 |
+
"loss": 0.1053,
|
| 372 |
+
"step": 590
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.09,
|
| 376 |
+
"learning_rate": 8.838429913854859e-06,
|
| 377 |
+
"loss": 0.1401,
|
| 378 |
+
"step": 600
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.09,
|
| 382 |
+
"learning_rate": 8.83303319378641e-06,
|
| 383 |
+
"loss": 0.09,
|
| 384 |
+
"step": 610
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.09,
|
| 388 |
+
"learning_rate": 8.827549520960827e-06,
|
| 389 |
+
"loss": 0.1667,
|
| 390 |
+
"step": 620
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.09,
|
| 394 |
+
"learning_rate": 8.821979005421223e-06,
|
| 395 |
+
"loss": 0.1069,
|
| 396 |
+
"step": 630
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.09,
|
| 400 |
+
"learning_rate": 8.816321758953426e-06,
|
| 401 |
+
"loss": 0.1659,
|
| 402 |
+
"step": 640
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.09,
|
| 406 |
+
"learning_rate": 8.810577895083726e-06,
|
| 407 |
+
"loss": 0.1309,
|
| 408 |
+
"step": 650
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.09,
|
| 412 |
+
"learning_rate": 8.804747529076592e-06,
|
| 413 |
+
"loss": 0.16,
|
| 414 |
+
"step": 660
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.1,
|
| 418 |
+
"learning_rate": 8.79883077793238e-06,
|
| 419 |
+
"loss": 0.1041,
|
| 420 |
+
"step": 670
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.1,
|
| 424 |
+
"learning_rate": 8.792827760384965e-06,
|
| 425 |
+
"loss": 0.1344,
|
| 426 |
+
"step": 680
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.1,
|
| 430 |
+
"learning_rate": 8.786738596899362e-06,
|
| 431 |
+
"loss": 0.0922,
|
| 432 |
+
"step": 690
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.1,
|
| 436 |
+
"learning_rate": 8.780563409669322e-06,
|
| 437 |
+
"loss": 0.0813,
|
| 438 |
+
"step": 700
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.1,
|
| 442 |
+
"learning_rate": 8.774302322614858e-06,
|
| 443 |
+
"loss": 0.1795,
|
| 444 |
+
"step": 710
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.1,
|
| 448 |
+
"learning_rate": 8.767955461379783e-06,
|
| 449 |
+
"loss": 0.1409,
|
| 450 |
+
"step": 720
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.1,
|
| 454 |
+
"learning_rate": 8.761522953329163e-06,
|
| 455 |
+
"loss": 0.1362,
|
| 456 |
+
"step": 730
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.11,
|
| 460 |
+
"learning_rate": 8.75500492754678e-06,
|
| 461 |
+
"loss": 0.1227,
|
| 462 |
+
"step": 740
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.11,
|
| 466 |
+
"learning_rate": 8.74840151483254e-06,
|
| 467 |
+
"loss": 0.0643,
|
| 468 |
+
"step": 750
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.11,
|
| 472 |
+
"learning_rate": 8.741712847699832e-06,
|
| 473 |
+
"loss": 0.1895,
|
| 474 |
+
"step": 760
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.11,
|
| 478 |
+
"learning_rate": 8.734939060372892e-06,
|
| 479 |
+
"loss": 0.0959,
|
| 480 |
+
"step": 770
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.11,
|
| 484 |
+
"learning_rate": 8.72808028878409e-06,
|
| 485 |
+
"loss": 0.1089,
|
| 486 |
+
"step": 780
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.11,
|
| 490 |
+
"learning_rate": 8.721136670571216e-06,
|
| 491 |
+
"loss": 0.0959,
|
| 492 |
+
"step": 790
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.11,
|
| 496 |
+
"learning_rate": 8.714108345074704e-06,
|
| 497 |
+
"loss": 0.1264,
|
| 498 |
+
"step": 800
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.12,
|
| 502 |
+
"learning_rate": 8.706995453334855e-06,
|
| 503 |
+
"loss": 0.1078,
|
| 504 |
+
"step": 810
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.12,
|
| 508 |
+
"learning_rate": 8.699798138088988e-06,
|
| 509 |
+
"loss": 0.1278,
|
| 510 |
+
"step": 820
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.12,
|
| 514 |
+
"learning_rate": 8.692516543768581e-06,
|
| 515 |
+
"loss": 0.1337,
|
| 516 |
+
"step": 830
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.12,
|
| 520 |
+
"learning_rate": 8.685150816496384e-06,
|
| 521 |
+
"loss": 0.0815,
|
| 522 |
+
"step": 840
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.12,
|
| 526 |
+
"learning_rate": 8.677701104083467e-06,
|
| 527 |
+
"loss": 0.1033,
|
| 528 |
+
"step": 850
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.12,
|
| 532 |
+
"learning_rate": 8.670167556026274e-06,
|
| 533 |
+
"loss": 0.1412,
|
| 534 |
+
"step": 860
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.12,
|
| 538 |
+
"learning_rate": 8.662550323503606e-06,
|
| 539 |
+
"loss": 0.197,
|
| 540 |
+
"step": 870
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.13,
|
| 544 |
+
"learning_rate": 8.654849559373595e-06,
|
| 545 |
+
"loss": 0.1118,
|
| 546 |
+
"step": 880
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.13,
|
| 550 |
+
"learning_rate": 8.647065418170644e-06,
|
| 551 |
+
"loss": 0.1132,
|
| 552 |
+
"step": 890
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.13,
|
| 556 |
+
"learning_rate": 8.639198056102309e-06,
|
| 557 |
+
"loss": 0.0928,
|
| 558 |
+
"step": 900
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.13,
|
| 562 |
+
"learning_rate": 8.631247631046176e-06,
|
| 563 |
+
"loss": 0.0723,
|
| 564 |
+
"step": 910
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.13,
|
| 568 |
+
"learning_rate": 8.623214302546691e-06,
|
| 569 |
+
"loss": 0.126,
|
| 570 |
+
"step": 920
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.13,
|
| 574 |
+
"learning_rate": 8.615098231811958e-06,
|
| 575 |
+
"loss": 0.1363,
|
| 576 |
+
"step": 930
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.13,
|
| 580 |
+
"learning_rate": 8.606899581710505e-06,
|
| 581 |
+
"loss": 0.1243,
|
| 582 |
+
"step": 940
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.14,
|
| 586 |
+
"learning_rate": 8.598618516768005e-06,
|
| 587 |
+
"loss": 0.0382,
|
| 588 |
+
"step": 950
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.14,
|
| 592 |
+
"learning_rate": 8.590255203163995e-06,
|
| 593 |
+
"loss": 0.1295,
|
| 594 |
+
"step": 960
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.14,
|
| 598 |
+
"learning_rate": 8.581809808728524e-06,
|
| 599 |
+
"loss": 0.1145,
|
| 600 |
+
"step": 970
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.14,
|
| 604 |
+
"learning_rate": 8.573282502938791e-06,
|
| 605 |
+
"loss": 0.0915,
|
| 606 |
+
"step": 980
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.14,
|
| 610 |
+
"learning_rate": 8.564673456915746e-06,
|
| 611 |
+
"loss": 0.1918,
|
| 612 |
+
"step": 990
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.14,
|
| 616 |
+
"learning_rate": 8.55598284342065e-06,
|
| 617 |
+
"loss": 0.1732,
|
| 618 |
+
"step": 1000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.14,
|
| 622 |
+
"eval_accuracy": 0.0,
|
| 623 |
+
"eval_loss": 0.12965914607048035,
|
| 624 |
+
"eval_runtime": 448.5256,
|
| 625 |
+
"eval_samples_per_second": 52.124,
|
| 626 |
+
"eval_steps_per_second": 8.688,
|
| 627 |
+
"step": 1000
|
| 628 |
+
}
|
| 629 |
+
],
|
| 630 |
+
"logging_steps": 10,
|
| 631 |
+
"max_steps": 7013,
|
| 632 |
+
"num_train_epochs": 1,
|
| 633 |
+
"save_steps": 500,
|
| 634 |
+
"total_flos": 0.0,
|
| 635 |
+
"trial_name": null,
|
| 636 |
+
"trial_params": null
|
| 637 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbd473640b089575e3b93f40caac6d96b1006088b463e865229fad92539da1e0
|
| 3 |
+
size 4600
|