Upload 13 files
Browse files- config.json +74 -0
- generation_config.json +10 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +2043 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": null,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "bart",
|
| 43 |
+
"no_repeat_ngram_size": null,
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": true,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"summarization": {
|
| 52 |
+
"length_penalty": 1.0,
|
| 53 |
+
"max_length": 128,
|
| 54 |
+
"min_length": 12,
|
| 55 |
+
"num_beams": 4
|
| 56 |
+
},
|
| 57 |
+
"summarization_cnn": {
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"num_beams": 4
|
| 62 |
+
},
|
| 63 |
+
"summarization_xsum": {
|
| 64 |
+
"length_penalty": 1.0,
|
| 65 |
+
"max_length": 62,
|
| 66 |
+
"min_length": 11,
|
| 67 |
+
"num_beams": 6
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.46.3",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"early_stopping": true,
|
| 3 |
+
"forced_bos_token_id": 0,
|
| 4 |
+
"length_penalty": 2.0,
|
| 5 |
+
"max_length": 1024,
|
| 6 |
+
"min_length": 56,
|
| 7 |
+
"no_repeat_ngram_size": 3,
|
| 8 |
+
"num_beams": 4,
|
| 9 |
+
"transformers_version": "4.46.3"
|
| 10 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d27324ab0a7f10ea61e75c3434678e9c1d358304b4a2b1ba714cd17491ce997
|
| 3 |
+
size 557912620
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77f8510480debbbca611dfd14dae7ed1d42907cd83388cdf388d82de1aae27df
|
| 3 |
+
size 1115579834
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7de9f401d65252ab0ea9cb76dbee18cf4d6f63639ff76ac2a232c5e6b4ce7437
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c648055dadde4a82f7bb8d4e5c6e318f6ee8699b4eddc2b5bc31fa924728c1e
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2043 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.601110577583313,
|
| 3 |
+
"best_model_checkpoint": "outputs/checkpoint-13300",
|
| 4 |
+
"epoch": 2.999832822513235,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 13458,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.022290331568682084,
|
| 13 |
+
"grad_norm": 820153.75,
|
| 14 |
+
"learning_rate": 6e-06,
|
| 15 |
+
"loss": 3.4337,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.022290331568682084,
|
| 20 |
+
"eval_loss": 2.219454050064087,
|
| 21 |
+
"eval_runtime": 63.1076,
|
| 22 |
+
"eval_samples_per_second": 211.829,
|
| 23 |
+
"eval_steps_per_second": 13.247,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04458066313736417,
|
| 28 |
+
"grad_norm": 595487.125,
|
| 29 |
+
"learning_rate": 1.2e-05,
|
| 30 |
+
"loss": 2.4245,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.04458066313736417,
|
| 35 |
+
"eval_loss": 1.938194990158081,
|
| 36 |
+
"eval_runtime": 63.043,
|
| 37 |
+
"eval_samples_per_second": 212.046,
|
| 38 |
+
"eval_steps_per_second": 13.261,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.06687099470604625,
|
| 43 |
+
"grad_norm": 613520.625,
|
| 44 |
+
"learning_rate": 1.8e-05,
|
| 45 |
+
"loss": 2.2722,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.06687099470604625,
|
| 50 |
+
"eval_loss": 1.8768234252929688,
|
| 51 |
+
"eval_runtime": 63.5969,
|
| 52 |
+
"eval_samples_per_second": 210.199,
|
| 53 |
+
"eval_steps_per_second": 13.145,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.08916132627472834,
|
| 58 |
+
"grad_norm": 566655.875,
|
| 59 |
+
"learning_rate": 2.4e-05,
|
| 60 |
+
"loss": 2.1739,
|
| 61 |
+
"step": 400
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.08916132627472834,
|
| 65 |
+
"eval_loss": 1.8509334325790405,
|
| 66 |
+
"eval_runtime": 63.6581,
|
| 67 |
+
"eval_samples_per_second": 209.997,
|
| 68 |
+
"eval_steps_per_second": 13.133,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.11145165784341042,
|
| 73 |
+
"grad_norm": 618861.25,
|
| 74 |
+
"learning_rate": 3e-05,
|
| 75 |
+
"loss": 2.1388,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.11145165784341042,
|
| 80 |
+
"eval_loss": 1.8238554000854492,
|
| 81 |
+
"eval_runtime": 63.0746,
|
| 82 |
+
"eval_samples_per_second": 211.939,
|
| 83 |
+
"eval_steps_per_second": 13.254,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.1337419894120925,
|
| 88 |
+
"grad_norm": 594465.5,
|
| 89 |
+
"learning_rate": 2.9768482790554097e-05,
|
| 90 |
+
"loss": 2.1116,
|
| 91 |
+
"step": 600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.1337419894120925,
|
| 95 |
+
"eval_loss": 1.813140869140625,
|
| 96 |
+
"eval_runtime": 63.2719,
|
| 97 |
+
"eval_samples_per_second": 211.279,
|
| 98 |
+
"eval_steps_per_second": 13.213,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.1560323209807746,
|
| 103 |
+
"grad_norm": 528193.5625,
|
| 104 |
+
"learning_rate": 2.9536965581108196e-05,
|
| 105 |
+
"loss": 2.0772,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.1560323209807746,
|
| 110 |
+
"eval_loss": 1.7901383638381958,
|
| 111 |
+
"eval_runtime": 63.0937,
|
| 112 |
+
"eval_samples_per_second": 211.876,
|
| 113 |
+
"eval_steps_per_second": 13.25,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.17832265254945667,
|
| 118 |
+
"grad_norm": 500452.375,
|
| 119 |
+
"learning_rate": 2.9305448371662296e-05,
|
| 120 |
+
"loss": 2.0526,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.17832265254945667,
|
| 125 |
+
"eval_loss": 1.7764878273010254,
|
| 126 |
+
"eval_runtime": 63.8628,
|
| 127 |
+
"eval_samples_per_second": 209.324,
|
| 128 |
+
"eval_steps_per_second": 13.091,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.20061298411813877,
|
| 133 |
+
"grad_norm": 492339.875,
|
| 134 |
+
"learning_rate": 2.9073931162216392e-05,
|
| 135 |
+
"loss": 2.0419,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.20061298411813877,
|
| 140 |
+
"eval_loss": 1.7795604467391968,
|
| 141 |
+
"eval_runtime": 63.1552,
|
| 142 |
+
"eval_samples_per_second": 211.669,
|
| 143 |
+
"eval_steps_per_second": 13.237,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.22290331568682084,
|
| 148 |
+
"grad_norm": 549590.1875,
|
| 149 |
+
"learning_rate": 2.884241395277049e-05,
|
| 150 |
+
"loss": 2.0305,
|
| 151 |
+
"step": 1000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.22290331568682084,
|
| 155 |
+
"eval_loss": 1.7810730934143066,
|
| 156 |
+
"eval_runtime": 62.8059,
|
| 157 |
+
"eval_samples_per_second": 212.846,
|
| 158 |
+
"eval_steps_per_second": 13.311,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.24519364725550294,
|
| 163 |
+
"grad_norm": 463470.46875,
|
| 164 |
+
"learning_rate": 2.8610896743324588e-05,
|
| 165 |
+
"loss": 2.0123,
|
| 166 |
+
"step": 1100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.24519364725550294,
|
| 170 |
+
"eval_loss": 1.739020586013794,
|
| 171 |
+
"eval_runtime": 63.3157,
|
| 172 |
+
"eval_samples_per_second": 211.133,
|
| 173 |
+
"eval_steps_per_second": 13.204,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.267483978824185,
|
| 178 |
+
"grad_norm": 483440.3125,
|
| 179 |
+
"learning_rate": 2.8379379533878684e-05,
|
| 180 |
+
"loss": 2.0051,
|
| 181 |
+
"step": 1200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.267483978824185,
|
| 185 |
+
"eval_loss": 1.754070520401001,
|
| 186 |
+
"eval_runtime": 63.6661,
|
| 187 |
+
"eval_samples_per_second": 209.97,
|
| 188 |
+
"eval_steps_per_second": 13.131,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.2897743103928671,
|
| 193 |
+
"grad_norm": 515932.6875,
|
| 194 |
+
"learning_rate": 2.8147862324432783e-05,
|
| 195 |
+
"loss": 2.0018,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.2897743103928671,
|
| 200 |
+
"eval_loss": 1.7487035989761353,
|
| 201 |
+
"eval_runtime": 63.3358,
|
| 202 |
+
"eval_samples_per_second": 211.065,
|
| 203 |
+
"eval_steps_per_second": 13.199,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.3120646419615492,
|
| 208 |
+
"grad_norm": 510042.875,
|
| 209 |
+
"learning_rate": 2.7916345114986883e-05,
|
| 210 |
+
"loss": 1.9878,
|
| 211 |
+
"step": 1400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.3120646419615492,
|
| 215 |
+
"eval_loss": 1.7291030883789062,
|
| 216 |
+
"eval_runtime": 63.1739,
|
| 217 |
+
"eval_samples_per_second": 211.607,
|
| 218 |
+
"eval_steps_per_second": 13.233,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.33435497353023125,
|
| 223 |
+
"grad_norm": 508744.25,
|
| 224 |
+
"learning_rate": 2.768482790554098e-05,
|
| 225 |
+
"loss": 1.9885,
|
| 226 |
+
"step": 1500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.33435497353023125,
|
| 230 |
+
"eval_loss": 1.7247428894042969,
|
| 231 |
+
"eval_runtime": 63.3733,
|
| 232 |
+
"eval_samples_per_second": 210.941,
|
| 233 |
+
"eval_steps_per_second": 13.192,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.35664530509891335,
|
| 238 |
+
"grad_norm": 512775.4375,
|
| 239 |
+
"learning_rate": 2.7453310696095075e-05,
|
| 240 |
+
"loss": 1.9864,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.35664530509891335,
|
| 245 |
+
"eval_loss": 1.7243812084197998,
|
| 246 |
+
"eval_runtime": 63.6899,
|
| 247 |
+
"eval_samples_per_second": 209.892,
|
| 248 |
+
"eval_steps_per_second": 13.126,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.37893563666759544,
|
| 253 |
+
"grad_norm": 480830.6875,
|
| 254 |
+
"learning_rate": 2.7221793486649175e-05,
|
| 255 |
+
"loss": 1.9735,
|
| 256 |
+
"step": 1700
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.37893563666759544,
|
| 260 |
+
"eval_loss": 1.7244142293930054,
|
| 261 |
+
"eval_runtime": 63.3501,
|
| 262 |
+
"eval_samples_per_second": 211.018,
|
| 263 |
+
"eval_steps_per_second": 13.196,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.40122596823627754,
|
| 268 |
+
"grad_norm": 554714.125,
|
| 269 |
+
"learning_rate": 2.6990276277203274e-05,
|
| 270 |
+
"loss": 1.9756,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.40122596823627754,
|
| 275 |
+
"eval_loss": 1.7170045375823975,
|
| 276 |
+
"eval_runtime": 62.9859,
|
| 277 |
+
"eval_samples_per_second": 212.238,
|
| 278 |
+
"eval_steps_per_second": 13.273,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.4235162998049596,
|
| 283 |
+
"grad_norm": 464572.84375,
|
| 284 |
+
"learning_rate": 2.675875906775737e-05,
|
| 285 |
+
"loss": 1.9538,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.4235162998049596,
|
| 290 |
+
"eval_loss": 1.7204582691192627,
|
| 291 |
+
"eval_runtime": 63.2678,
|
| 292 |
+
"eval_samples_per_second": 211.292,
|
| 293 |
+
"eval_steps_per_second": 13.214,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.4458066313736417,
|
| 298 |
+
"grad_norm": 461049.8125,
|
| 299 |
+
"learning_rate": 2.652724185831147e-05,
|
| 300 |
+
"loss": 1.9519,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.4458066313736417,
|
| 305 |
+
"eval_loss": 1.7141714096069336,
|
| 306 |
+
"eval_runtime": 63.4578,
|
| 307 |
+
"eval_samples_per_second": 210.66,
|
| 308 |
+
"eval_steps_per_second": 13.174,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.4680969629423238,
|
| 313 |
+
"grad_norm": 470016.21875,
|
| 314 |
+
"learning_rate": 2.6295724648865566e-05,
|
| 315 |
+
"loss": 1.9391,
|
| 316 |
+
"step": 2100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.4680969629423238,
|
| 320 |
+
"eval_loss": 1.7201862335205078,
|
| 321 |
+
"eval_runtime": 63.3953,
|
| 322 |
+
"eval_samples_per_second": 210.867,
|
| 323 |
+
"eval_steps_per_second": 13.187,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4903872945110059,
|
| 328 |
+
"grad_norm": 485373.15625,
|
| 329 |
+
"learning_rate": 2.6064207439419662e-05,
|
| 330 |
+
"loss": 1.9352,
|
| 331 |
+
"step": 2200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.4903872945110059,
|
| 335 |
+
"eval_loss": 1.698974370956421,
|
| 336 |
+
"eval_runtime": 63.411,
|
| 337 |
+
"eval_samples_per_second": 210.815,
|
| 338 |
+
"eval_steps_per_second": 13.184,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5126776260796879,
|
| 343 |
+
"grad_norm": 472483.78125,
|
| 344 |
+
"learning_rate": 2.5832690229973762e-05,
|
| 345 |
+
"loss": 1.9412,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.5126776260796879,
|
| 350 |
+
"eval_loss": 1.7102808952331543,
|
| 351 |
+
"eval_runtime": 63.3414,
|
| 352 |
+
"eval_samples_per_second": 211.047,
|
| 353 |
+
"eval_steps_per_second": 13.198,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.53496795764837,
|
| 358 |
+
"grad_norm": 444579.25,
|
| 359 |
+
"learning_rate": 2.560117302052786e-05,
|
| 360 |
+
"loss": 1.9331,
|
| 361 |
+
"step": 2400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.53496795764837,
|
| 365 |
+
"eval_loss": 1.7026287317276,
|
| 366 |
+
"eval_runtime": 63.7826,
|
| 367 |
+
"eval_samples_per_second": 209.587,
|
| 368 |
+
"eval_steps_per_second": 13.107,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.5572582892170521,
|
| 373 |
+
"grad_norm": 544911.375,
|
| 374 |
+
"learning_rate": 2.5369655811081957e-05,
|
| 375 |
+
"loss": 1.933,
|
| 376 |
+
"step": 2500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.5572582892170521,
|
| 380 |
+
"eval_loss": 1.6917425394058228,
|
| 381 |
+
"eval_runtime": 63.6992,
|
| 382 |
+
"eval_samples_per_second": 209.861,
|
| 383 |
+
"eval_steps_per_second": 13.124,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.5795486207857342,
|
| 388 |
+
"grad_norm": 442399.9375,
|
| 389 |
+
"learning_rate": 2.5138138601636054e-05,
|
| 390 |
+
"loss": 1.9209,
|
| 391 |
+
"step": 2600
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.5795486207857342,
|
| 395 |
+
"eval_loss": 1.7024257183074951,
|
| 396 |
+
"eval_runtime": 63.6754,
|
| 397 |
+
"eval_samples_per_second": 209.94,
|
| 398 |
+
"eval_steps_per_second": 13.129,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.6018389523544163,
|
| 403 |
+
"grad_norm": 478748.46875,
|
| 404 |
+
"learning_rate": 2.4906621392190153e-05,
|
| 405 |
+
"loss": 1.9193,
|
| 406 |
+
"step": 2700
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.6018389523544163,
|
| 410 |
+
"eval_loss": 1.7053234577178955,
|
| 411 |
+
"eval_runtime": 63.8191,
|
| 412 |
+
"eval_samples_per_second": 209.467,
|
| 413 |
+
"eval_steps_per_second": 13.1,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.6241292839230984,
|
| 418 |
+
"grad_norm": 468540.28125,
|
| 419 |
+
"learning_rate": 2.4675104182744253e-05,
|
| 420 |
+
"loss": 1.8972,
|
| 421 |
+
"step": 2800
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.6241292839230984,
|
| 425 |
+
"eval_loss": 1.6971023082733154,
|
| 426 |
+
"eval_runtime": 63.3867,
|
| 427 |
+
"eval_samples_per_second": 210.896,
|
| 428 |
+
"eval_steps_per_second": 13.189,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6464196154917804,
|
| 433 |
+
"grad_norm": 447092.15625,
|
| 434 |
+
"learning_rate": 2.444358697329835e-05,
|
| 435 |
+
"loss": 1.9116,
|
| 436 |
+
"step": 2900
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6464196154917804,
|
| 440 |
+
"eval_loss": 1.6840194463729858,
|
| 441 |
+
"eval_runtime": 62.9634,
|
| 442 |
+
"eval_samples_per_second": 212.314,
|
| 443 |
+
"eval_steps_per_second": 13.278,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.6687099470604625,
|
| 448 |
+
"grad_norm": 498904.8125,
|
| 449 |
+
"learning_rate": 2.421206976385245e-05,
|
| 450 |
+
"loss": 1.908,
|
| 451 |
+
"step": 3000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.6687099470604625,
|
| 455 |
+
"eval_loss": 1.69094979763031,
|
| 456 |
+
"eval_runtime": 63.2731,
|
| 457 |
+
"eval_samples_per_second": 211.275,
|
| 458 |
+
"eval_steps_per_second": 13.213,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.6910002786291446,
|
| 463 |
+
"grad_norm": 462770.21875,
|
| 464 |
+
"learning_rate": 2.3980552554406545e-05,
|
| 465 |
+
"loss": 1.9074,
|
| 466 |
+
"step": 3100
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.6910002786291446,
|
| 470 |
+
"eval_loss": 1.6828372478485107,
|
| 471 |
+
"eval_runtime": 63.5905,
|
| 472 |
+
"eval_samples_per_second": 210.22,
|
| 473 |
+
"eval_steps_per_second": 13.147,
|
| 474 |
+
"step": 3100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.7132906101978267,
|
| 478 |
+
"grad_norm": 510012.96875,
|
| 479 |
+
"learning_rate": 2.374903534496064e-05,
|
| 480 |
+
"loss": 1.8977,
|
| 481 |
+
"step": 3200
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.7132906101978267,
|
| 485 |
+
"eval_loss": 1.6863964796066284,
|
| 486 |
+
"eval_runtime": 63.6806,
|
| 487 |
+
"eval_samples_per_second": 209.923,
|
| 488 |
+
"eval_steps_per_second": 13.128,
|
| 489 |
+
"step": 3200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.7355809417665088,
|
| 493 |
+
"grad_norm": 471075.21875,
|
| 494 |
+
"learning_rate": 2.351751813551474e-05,
|
| 495 |
+
"loss": 1.9154,
|
| 496 |
+
"step": 3300
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.7355809417665088,
|
| 500 |
+
"eval_loss": 1.6765246391296387,
|
| 501 |
+
"eval_runtime": 63.5227,
|
| 502 |
+
"eval_samples_per_second": 210.444,
|
| 503 |
+
"eval_steps_per_second": 13.161,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.7578712733351909,
|
| 508 |
+
"grad_norm": 459823.4375,
|
| 509 |
+
"learning_rate": 2.328600092606884e-05,
|
| 510 |
+
"loss": 1.8869,
|
| 511 |
+
"step": 3400
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.7578712733351909,
|
| 515 |
+
"eval_loss": 1.6767551898956299,
|
| 516 |
+
"eval_runtime": 62.9808,
|
| 517 |
+
"eval_samples_per_second": 212.255,
|
| 518 |
+
"eval_steps_per_second": 13.274,
|
| 519 |
+
"step": 3400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.780161604903873,
|
| 523 |
+
"grad_norm": 431094.84375,
|
| 524 |
+
"learning_rate": 2.3054483716622936e-05,
|
| 525 |
+
"loss": 1.8935,
|
| 526 |
+
"step": 3500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.780161604903873,
|
| 530 |
+
"eval_loss": 1.6749335527420044,
|
| 531 |
+
"eval_runtime": 62.9334,
|
| 532 |
+
"eval_samples_per_second": 212.415,
|
| 533 |
+
"eval_steps_per_second": 13.284,
|
| 534 |
+
"step": 3500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8024519364725551,
|
| 538 |
+
"grad_norm": 444868.96875,
|
| 539 |
+
"learning_rate": 2.2822966507177032e-05,
|
| 540 |
+
"loss": 1.8913,
|
| 541 |
+
"step": 3600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.8024519364725551,
|
| 545 |
+
"eval_loss": 1.6784425973892212,
|
| 546 |
+
"eval_runtime": 63.2429,
|
| 547 |
+
"eval_samples_per_second": 211.376,
|
| 548 |
+
"eval_steps_per_second": 13.219,
|
| 549 |
+
"step": 3600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.8247422680412371,
|
| 553 |
+
"grad_norm": 451189.40625,
|
| 554 |
+
"learning_rate": 2.259144929773113e-05,
|
| 555 |
+
"loss": 1.8878,
|
| 556 |
+
"step": 3700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.8247422680412371,
|
| 560 |
+
"eval_loss": 1.6754982471466064,
|
| 561 |
+
"eval_runtime": 63.7373,
|
| 562 |
+
"eval_samples_per_second": 209.736,
|
| 563 |
+
"eval_steps_per_second": 13.116,
|
| 564 |
+
"step": 3700
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.8470325996099192,
|
| 568 |
+
"grad_norm": 441200.9375,
|
| 569 |
+
"learning_rate": 2.235993208828523e-05,
|
| 570 |
+
"loss": 1.8948,
|
| 571 |
+
"step": 3800
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.8470325996099192,
|
| 575 |
+
"eval_loss": 1.6711094379425049,
|
| 576 |
+
"eval_runtime": 62.7885,
|
| 577 |
+
"eval_samples_per_second": 212.905,
|
| 578 |
+
"eval_steps_per_second": 13.315,
|
| 579 |
+
"step": 3800
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.8693229311786013,
|
| 583 |
+
"grad_norm": 467896.84375,
|
| 584 |
+
"learning_rate": 2.2128414878839327e-05,
|
| 585 |
+
"loss": 1.8816,
|
| 586 |
+
"step": 3900
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.8693229311786013,
|
| 590 |
+
"eval_loss": 1.671681523323059,
|
| 591 |
+
"eval_runtime": 63.1597,
|
| 592 |
+
"eval_samples_per_second": 211.654,
|
| 593 |
+
"eval_steps_per_second": 13.236,
|
| 594 |
+
"step": 3900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.8916132627472834,
|
| 598 |
+
"grad_norm": 456236.3125,
|
| 599 |
+
"learning_rate": 2.1896897669393427e-05,
|
| 600 |
+
"loss": 1.8864,
|
| 601 |
+
"step": 4000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.8916132627472834,
|
| 605 |
+
"eval_loss": 1.673299789428711,
|
| 606 |
+
"eval_runtime": 63.6594,
|
| 607 |
+
"eval_samples_per_second": 209.992,
|
| 608 |
+
"eval_steps_per_second": 13.132,
|
| 609 |
+
"step": 4000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.9139035943159655,
|
| 613 |
+
"grad_norm": 470346.40625,
|
| 614 |
+
"learning_rate": 2.1665380459947523e-05,
|
| 615 |
+
"loss": 1.879,
|
| 616 |
+
"step": 4100
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.9139035943159655,
|
| 620 |
+
"eval_loss": 1.6596086025238037,
|
| 621 |
+
"eval_runtime": 63.3568,
|
| 622 |
+
"eval_samples_per_second": 210.995,
|
| 623 |
+
"eval_steps_per_second": 13.195,
|
| 624 |
+
"step": 4100
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.9361939258846476,
|
| 628 |
+
"grad_norm": 468418.625,
|
| 629 |
+
"learning_rate": 2.143386325050162e-05,
|
| 630 |
+
"loss": 1.8862,
|
| 631 |
+
"step": 4200
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.9361939258846476,
|
| 635 |
+
"eval_loss": 1.6646808385849,
|
| 636 |
+
"eval_runtime": 63.5493,
|
| 637 |
+
"eval_samples_per_second": 210.356,
|
| 638 |
+
"eval_steps_per_second": 13.155,
|
| 639 |
+
"step": 4200
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9584842574533297,
|
| 643 |
+
"grad_norm": 454157.0,
|
| 644 |
+
"learning_rate": 2.120234604105572e-05,
|
| 645 |
+
"loss": 1.8722,
|
| 646 |
+
"step": 4300
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.9584842574533297,
|
| 650 |
+
"eval_loss": 1.667905330657959,
|
| 651 |
+
"eval_runtime": 62.7216,
|
| 652 |
+
"eval_samples_per_second": 213.132,
|
| 653 |
+
"eval_steps_per_second": 13.329,
|
| 654 |
+
"step": 4300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.9807745890220118,
|
| 658 |
+
"grad_norm": 462536.9375,
|
| 659 |
+
"learning_rate": 2.0970828831609818e-05,
|
| 660 |
+
"loss": 1.8669,
|
| 661 |
+
"step": 4400
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.9807745890220118,
|
| 665 |
+
"eval_loss": 1.65095853805542,
|
| 666 |
+
"eval_runtime": 62.9484,
|
| 667 |
+
"eval_samples_per_second": 212.364,
|
| 668 |
+
"eval_steps_per_second": 13.281,
|
| 669 |
+
"step": 4400
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.0030649205906939,
|
| 673 |
+
"grad_norm": 478586.0,
|
| 674 |
+
"learning_rate": 2.0739311622163914e-05,
|
| 675 |
+
"loss": 1.8636,
|
| 676 |
+
"step": 4500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.0030649205906939,
|
| 680 |
+
"eval_loss": 1.6621143817901611,
|
| 681 |
+
"eval_runtime": 63.2068,
|
| 682 |
+
"eval_samples_per_second": 211.496,
|
| 683 |
+
"eval_steps_per_second": 13.226,
|
| 684 |
+
"step": 4500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.0253552521593758,
|
| 688 |
+
"grad_norm": 539991.8125,
|
| 689 |
+
"learning_rate": 2.050779441271801e-05,
|
| 690 |
+
"loss": 1.8262,
|
| 691 |
+
"step": 4600
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.0253552521593758,
|
| 695 |
+
"eval_loss": 1.6551061868667603,
|
| 696 |
+
"eval_runtime": 63.124,
|
| 697 |
+
"eval_samples_per_second": 211.774,
|
| 698 |
+
"eval_steps_per_second": 13.244,
|
| 699 |
+
"step": 4600
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.047645583728058,
|
| 703 |
+
"grad_norm": 428922.53125,
|
| 704 |
+
"learning_rate": 2.027627720327211e-05,
|
| 705 |
+
"loss": 1.8142,
|
| 706 |
+
"step": 4700
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.047645583728058,
|
| 710 |
+
"eval_loss": 1.6545677185058594,
|
| 711 |
+
"eval_runtime": 63.0786,
|
| 712 |
+
"eval_samples_per_second": 211.926,
|
| 713 |
+
"eval_steps_per_second": 13.253,
|
| 714 |
+
"step": 4700
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.06993591529674,
|
| 718 |
+
"grad_norm": 438794.46875,
|
| 719 |
+
"learning_rate": 2.004475999382621e-05,
|
| 720 |
+
"loss": 1.8097,
|
| 721 |
+
"step": 4800
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 1.06993591529674,
|
| 725 |
+
"eval_loss": 1.6556122303009033,
|
| 726 |
+
"eval_runtime": 63.6203,
|
| 727 |
+
"eval_samples_per_second": 210.122,
|
| 728 |
+
"eval_steps_per_second": 13.14,
|
| 729 |
+
"step": 4800
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.092226246865422,
|
| 733 |
+
"grad_norm": 468837.34375,
|
| 734 |
+
"learning_rate": 1.9813242784380306e-05,
|
| 735 |
+
"loss": 1.8242,
|
| 736 |
+
"step": 4900
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.092226246865422,
|
| 740 |
+
"eval_loss": 1.657508134841919,
|
| 741 |
+
"eval_runtime": 63.2746,
|
| 742 |
+
"eval_samples_per_second": 211.27,
|
| 743 |
+
"eval_steps_per_second": 13.212,
|
| 744 |
+
"step": 4900
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.1145165784341042,
|
| 748 |
+
"grad_norm": 449878.40625,
|
| 749 |
+
"learning_rate": 1.9581725574934405e-05,
|
| 750 |
+
"loss": 1.8143,
|
| 751 |
+
"step": 5000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 1.1145165784341042,
|
| 755 |
+
"eval_loss": 1.6671580076217651,
|
| 756 |
+
"eval_runtime": 63.9114,
|
| 757 |
+
"eval_samples_per_second": 209.165,
|
| 758 |
+
"eval_steps_per_second": 13.081,
|
| 759 |
+
"step": 5000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.1368069100027862,
|
| 763 |
+
"grad_norm": 427682.84375,
|
| 764 |
+
"learning_rate": 1.93502083654885e-05,
|
| 765 |
+
"loss": 1.8242,
|
| 766 |
+
"step": 5100
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.1368069100027862,
|
| 770 |
+
"eval_loss": 1.6521689891815186,
|
| 771 |
+
"eval_runtime": 62.5274,
|
| 772 |
+
"eval_samples_per_second": 213.794,
|
| 773 |
+
"eval_steps_per_second": 13.37,
|
| 774 |
+
"step": 5100
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.1590972415714684,
|
| 778 |
+
"grad_norm": 441866.34375,
|
| 779 |
+
"learning_rate": 1.9118691156042597e-05,
|
| 780 |
+
"loss": 1.8105,
|
| 781 |
+
"step": 5200
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 1.1590972415714684,
|
| 785 |
+
"eval_loss": 1.6530238389968872,
|
| 786 |
+
"eval_runtime": 62.6567,
|
| 787 |
+
"eval_samples_per_second": 213.353,
|
| 788 |
+
"eval_steps_per_second": 13.343,
|
| 789 |
+
"step": 5200
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.1813875731401504,
|
| 793 |
+
"grad_norm": 455879.25,
|
| 794 |
+
"learning_rate": 1.8887173946596697e-05,
|
| 795 |
+
"loss": 1.813,
|
| 796 |
+
"step": 5300
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.1813875731401504,
|
| 800 |
+
"eval_loss": 1.654367208480835,
|
| 801 |
+
"eval_runtime": 63.6338,
|
| 802 |
+
"eval_samples_per_second": 210.077,
|
| 803 |
+
"eval_steps_per_second": 13.138,
|
| 804 |
+
"step": 5300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.2036779047088326,
|
| 808 |
+
"grad_norm": 410671.53125,
|
| 809 |
+
"learning_rate": 1.8655656737150796e-05,
|
| 810 |
+
"loss": 1.8201,
|
| 811 |
+
"step": 5400
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 1.2036779047088326,
|
| 815 |
+
"eval_loss": 1.6491619348526,
|
| 816 |
+
"eval_runtime": 63.5953,
|
| 817 |
+
"eval_samples_per_second": 210.204,
|
| 818 |
+
"eval_steps_per_second": 13.146,
|
| 819 |
+
"step": 5400
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.2259682362775146,
|
| 823 |
+
"grad_norm": 439893.84375,
|
| 824 |
+
"learning_rate": 1.8424139527704893e-05,
|
| 825 |
+
"loss": 1.8078,
|
| 826 |
+
"step": 5500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.2259682362775146,
|
| 830 |
+
"eval_loss": 1.6452112197875977,
|
| 831 |
+
"eval_runtime": 63.1345,
|
| 832 |
+
"eval_samples_per_second": 211.738,
|
| 833 |
+
"eval_steps_per_second": 13.242,
|
| 834 |
+
"step": 5500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.2482585678461966,
|
| 838 |
+
"grad_norm": 436707.84375,
|
| 839 |
+
"learning_rate": 1.819262231825899e-05,
|
| 840 |
+
"loss": 1.8081,
|
| 841 |
+
"step": 5600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.2482585678461966,
|
| 845 |
+
"eval_loss": 1.63877272605896,
|
| 846 |
+
"eval_runtime": 63.3151,
|
| 847 |
+
"eval_samples_per_second": 211.134,
|
| 848 |
+
"eval_steps_per_second": 13.204,
|
| 849 |
+
"step": 5600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.2705488994148788,
|
| 853 |
+
"grad_norm": 453170.34375,
|
| 854 |
+
"learning_rate": 1.7961105108813088e-05,
|
| 855 |
+
"loss": 1.809,
|
| 856 |
+
"step": 5700
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.2705488994148788,
|
| 860 |
+
"eval_loss": 1.6391615867614746,
|
| 861 |
+
"eval_runtime": 63.0066,
|
| 862 |
+
"eval_samples_per_second": 212.168,
|
| 863 |
+
"eval_steps_per_second": 13.268,
|
| 864 |
+
"step": 5700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.292839230983561,
|
| 868 |
+
"grad_norm": 419482.625,
|
| 869 |
+
"learning_rate": 1.7729587899367188e-05,
|
| 870 |
+
"loss": 1.7993,
|
| 871 |
+
"step": 5800
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.292839230983561,
|
| 875 |
+
"eval_loss": 1.6412807703018188,
|
| 876 |
+
"eval_runtime": 62.9872,
|
| 877 |
+
"eval_samples_per_second": 212.234,
|
| 878 |
+
"eval_steps_per_second": 13.273,
|
| 879 |
+
"step": 5800
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.315129562552243,
|
| 883 |
+
"grad_norm": 439712.59375,
|
| 884 |
+
"learning_rate": 1.7498070689921284e-05,
|
| 885 |
+
"loss": 1.806,
|
| 886 |
+
"step": 5900
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.315129562552243,
|
| 890 |
+
"eval_loss": 1.6369620561599731,
|
| 891 |
+
"eval_runtime": 62.9462,
|
| 892 |
+
"eval_samples_per_second": 212.372,
|
| 893 |
+
"eval_steps_per_second": 13.281,
|
| 894 |
+
"step": 5900
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.337419894120925,
|
| 898 |
+
"grad_norm": 433225.875,
|
| 899 |
+
"learning_rate": 1.7266553480475383e-05,
|
| 900 |
+
"loss": 1.8054,
|
| 901 |
+
"step": 6000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 1.337419894120925,
|
| 905 |
+
"eval_loss": 1.6376512050628662,
|
| 906 |
+
"eval_runtime": 63.3967,
|
| 907 |
+
"eval_samples_per_second": 210.863,
|
| 908 |
+
"eval_steps_per_second": 13.187,
|
| 909 |
+
"step": 6000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.3597102256896072,
|
| 913 |
+
"grad_norm": 442755.03125,
|
| 914 |
+
"learning_rate": 1.703503627102948e-05,
|
| 915 |
+
"loss": 1.7996,
|
| 916 |
+
"step": 6100
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.3597102256896072,
|
| 920 |
+
"eval_loss": 1.6386842727661133,
|
| 921 |
+
"eval_runtime": 64.1806,
|
| 922 |
+
"eval_samples_per_second": 208.287,
|
| 923 |
+
"eval_steps_per_second": 13.026,
|
| 924 |
+
"step": 6100
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.3820005572582892,
|
| 928 |
+
"grad_norm": 444388.1875,
|
| 929 |
+
"learning_rate": 1.6803519061583576e-05,
|
| 930 |
+
"loss": 1.7973,
|
| 931 |
+
"step": 6200
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 1.3820005572582892,
|
| 935 |
+
"eval_loss": 1.637714147567749,
|
| 936 |
+
"eval_runtime": 62.6809,
|
| 937 |
+
"eval_samples_per_second": 213.271,
|
| 938 |
+
"eval_steps_per_second": 13.337,
|
| 939 |
+
"step": 6200
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.4042908888269712,
|
| 943 |
+
"grad_norm": 457163.5625,
|
| 944 |
+
"learning_rate": 1.657200185213768e-05,
|
| 945 |
+
"loss": 1.8103,
|
| 946 |
+
"step": 6300
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.4042908888269712,
|
| 950 |
+
"eval_loss": 1.6353328227996826,
|
| 951 |
+
"eval_runtime": 63.7218,
|
| 952 |
+
"eval_samples_per_second": 209.787,
|
| 953 |
+
"eval_steps_per_second": 13.12,
|
| 954 |
+
"step": 6300
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.4265812203956534,
|
| 958 |
+
"grad_norm": 423063.71875,
|
| 959 |
+
"learning_rate": 1.6340484642691775e-05,
|
| 960 |
+
"loss": 1.8193,
|
| 961 |
+
"step": 6400
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 1.4265812203956534,
|
| 965 |
+
"eval_loss": 1.632241129875183,
|
| 966 |
+
"eval_runtime": 62.6795,
|
| 967 |
+
"eval_samples_per_second": 213.276,
|
| 968 |
+
"eval_steps_per_second": 13.338,
|
| 969 |
+
"step": 6400
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.4488715519643356,
|
| 973 |
+
"grad_norm": 450858.5625,
|
| 974 |
+
"learning_rate": 1.610896743324587e-05,
|
| 975 |
+
"loss": 1.8133,
|
| 976 |
+
"step": 6500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.4488715519643356,
|
| 980 |
+
"eval_loss": 1.642052412033081,
|
| 981 |
+
"eval_runtime": 64.1592,
|
| 982 |
+
"eval_samples_per_second": 208.357,
|
| 983 |
+
"eval_steps_per_second": 13.03,
|
| 984 |
+
"step": 6500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.4711618835330176,
|
| 988 |
+
"grad_norm": 424338.96875,
|
| 989 |
+
"learning_rate": 1.5877450223799967e-05,
|
| 990 |
+
"loss": 1.8016,
|
| 991 |
+
"step": 6600
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 1.4711618835330176,
|
| 995 |
+
"eval_loss": 1.6317675113677979,
|
| 996 |
+
"eval_runtime": 63.0019,
|
| 997 |
+
"eval_samples_per_second": 212.184,
|
| 998 |
+
"eval_steps_per_second": 13.269,
|
| 999 |
+
"step": 6600
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 1.4934522151016996,
|
| 1003 |
+
"grad_norm": 441573.03125,
|
| 1004 |
+
"learning_rate": 1.5645933014354067e-05,
|
| 1005 |
+
"loss": 1.7923,
|
| 1006 |
+
"step": 6700
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.4934522151016996,
|
| 1010 |
+
"eval_loss": 1.6302847862243652,
|
| 1011 |
+
"eval_runtime": 63.6702,
|
| 1012 |
+
"eval_samples_per_second": 209.957,
|
| 1013 |
+
"eval_steps_per_second": 13.13,
|
| 1014 |
+
"step": 6700
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 1.5157425466703818,
|
| 1018 |
+
"grad_norm": 460539.0625,
|
| 1019 |
+
"learning_rate": 1.5414415804908166e-05,
|
| 1020 |
+
"loss": 1.7969,
|
| 1021 |
+
"step": 6800
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.5157425466703818,
|
| 1025 |
+
"eval_loss": 1.6323357820510864,
|
| 1026 |
+
"eval_runtime": 62.8247,
|
| 1027 |
+
"eval_samples_per_second": 212.783,
|
| 1028 |
+
"eval_steps_per_second": 13.307,
|
| 1029 |
+
"step": 6800
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.5380328782390638,
|
| 1033 |
+
"grad_norm": 432685.96875,
|
| 1034 |
+
"learning_rate": 1.5182898595462264e-05,
|
| 1035 |
+
"loss": 1.7955,
|
| 1036 |
+
"step": 6900
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.5380328782390638,
|
| 1040 |
+
"eval_loss": 1.6306127309799194,
|
| 1041 |
+
"eval_runtime": 63.1442,
|
| 1042 |
+
"eval_samples_per_second": 211.706,
|
| 1043 |
+
"eval_steps_per_second": 13.24,
|
| 1044 |
+
"step": 6900
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.5603232098077457,
|
| 1048 |
+
"grad_norm": 414684.125,
|
| 1049 |
+
"learning_rate": 1.495138138601636e-05,
|
| 1050 |
+
"loss": 1.7933,
|
| 1051 |
+
"step": 7000
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.5603232098077457,
|
| 1055 |
+
"eval_loss": 1.6255934238433838,
|
| 1056 |
+
"eval_runtime": 63.4943,
|
| 1057 |
+
"eval_samples_per_second": 210.539,
|
| 1058 |
+
"eval_steps_per_second": 13.167,
|
| 1059 |
+
"step": 7000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 1.582613541376428,
|
| 1063 |
+
"grad_norm": 423529.65625,
|
| 1064 |
+
"learning_rate": 1.471986417657046e-05,
|
| 1065 |
+
"loss": 1.7951,
|
| 1066 |
+
"step": 7100
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.582613541376428,
|
| 1070 |
+
"eval_loss": 1.6387838125228882,
|
| 1071 |
+
"eval_runtime": 63.598,
|
| 1072 |
+
"eval_samples_per_second": 210.195,
|
| 1073 |
+
"eval_steps_per_second": 13.145,
|
| 1074 |
+
"step": 7100
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.6049038729451102,
|
| 1078 |
+
"grad_norm": 421001.21875,
|
| 1079 |
+
"learning_rate": 1.4488346967124556e-05,
|
| 1080 |
+
"loss": 1.8165,
|
| 1081 |
+
"step": 7200
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.6049038729451102,
|
| 1085 |
+
"eval_loss": 1.6351381540298462,
|
| 1086 |
+
"eval_runtime": 63.005,
|
| 1087 |
+
"eval_samples_per_second": 212.174,
|
| 1088 |
+
"eval_steps_per_second": 13.269,
|
| 1089 |
+
"step": 7200
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.6271942045137922,
|
| 1093 |
+
"grad_norm": 401336.375,
|
| 1094 |
+
"learning_rate": 1.4256829757678654e-05,
|
| 1095 |
+
"loss": 1.7934,
|
| 1096 |
+
"step": 7300
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.6271942045137922,
|
| 1100 |
+
"eval_loss": 1.630112886428833,
|
| 1101 |
+
"eval_runtime": 63.0665,
|
| 1102 |
+
"eval_samples_per_second": 211.967,
|
| 1103 |
+
"eval_steps_per_second": 13.256,
|
| 1104 |
+
"step": 7300
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 1.6494845360824741,
|
| 1108 |
+
"grad_norm": 439442.84375,
|
| 1109 |
+
"learning_rate": 1.4025312548232753e-05,
|
| 1110 |
+
"loss": 1.7809,
|
| 1111 |
+
"step": 7400
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 1.6494845360824741,
|
| 1115 |
+
"eval_loss": 1.6299716234207153,
|
| 1116 |
+
"eval_runtime": 63.6859,
|
| 1117 |
+
"eval_samples_per_second": 209.905,
|
| 1118 |
+
"eval_steps_per_second": 13.127,
|
| 1119 |
+
"step": 7400
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.6717748676511563,
|
| 1123 |
+
"grad_norm": 407261.71875,
|
| 1124 |
+
"learning_rate": 1.379379533878685e-05,
|
| 1125 |
+
"loss": 1.7899,
|
| 1126 |
+
"step": 7500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.6717748676511563,
|
| 1130 |
+
"eval_loss": 1.6285357475280762,
|
| 1131 |
+
"eval_runtime": 63.1642,
|
| 1132 |
+
"eval_samples_per_second": 211.639,
|
| 1133 |
+
"eval_steps_per_second": 13.235,
|
| 1134 |
+
"step": 7500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 1.6940651992198386,
|
| 1138 |
+
"grad_norm": 403575.21875,
|
| 1139 |
+
"learning_rate": 1.3562278129340949e-05,
|
| 1140 |
+
"loss": 1.7887,
|
| 1141 |
+
"step": 7600
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 1.6940651992198386,
|
| 1145 |
+
"eval_loss": 1.6282232999801636,
|
| 1146 |
+
"eval_runtime": 62.5905,
|
| 1147 |
+
"eval_samples_per_second": 213.579,
|
| 1148 |
+
"eval_steps_per_second": 13.357,
|
| 1149 |
+
"step": 7600
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.7163555307885203,
|
| 1153 |
+
"grad_norm": 440494.6875,
|
| 1154 |
+
"learning_rate": 1.3330760919895045e-05,
|
| 1155 |
+
"loss": 1.7859,
|
| 1156 |
+
"step": 7700
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 1.7163555307885203,
|
| 1160 |
+
"eval_loss": 1.622281551361084,
|
| 1161 |
+
"eval_runtime": 63.4527,
|
| 1162 |
+
"eval_samples_per_second": 210.677,
|
| 1163 |
+
"eval_steps_per_second": 13.175,
|
| 1164 |
+
"step": 7700
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.7386458623572025,
|
| 1168 |
+
"grad_norm": 414236.25,
|
| 1169 |
+
"learning_rate": 1.3099243710449143e-05,
|
| 1170 |
+
"loss": 1.8,
|
| 1171 |
+
"step": 7800
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.7386458623572025,
|
| 1175 |
+
"eval_loss": 1.623448371887207,
|
| 1176 |
+
"eval_runtime": 62.7927,
|
| 1177 |
+
"eval_samples_per_second": 212.891,
|
| 1178 |
+
"eval_steps_per_second": 13.314,
|
| 1179 |
+
"step": 7800
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.7609361939258847,
|
| 1183 |
+
"grad_norm": 438500.71875,
|
| 1184 |
+
"learning_rate": 1.2867726501003242e-05,
|
| 1185 |
+
"loss": 1.7907,
|
| 1186 |
+
"step": 7900
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.7609361939258847,
|
| 1190 |
+
"eval_loss": 1.6255710124969482,
|
| 1191 |
+
"eval_runtime": 63.6158,
|
| 1192 |
+
"eval_samples_per_second": 210.137,
|
| 1193 |
+
"eval_steps_per_second": 13.141,
|
| 1194 |
+
"step": 7900
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 1.7832265254945667,
|
| 1198 |
+
"grad_norm": 413099.34375,
|
| 1199 |
+
"learning_rate": 1.2636209291557339e-05,
|
| 1200 |
+
"loss": 1.8052,
|
| 1201 |
+
"step": 8000
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.7832265254945667,
|
| 1205 |
+
"eval_loss": 1.6219525337219238,
|
| 1206 |
+
"eval_runtime": 63.4015,
|
| 1207 |
+
"eval_samples_per_second": 210.847,
|
| 1208 |
+
"eval_steps_per_second": 13.186,
|
| 1209 |
+
"step": 8000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 1.8055168570632487,
|
| 1213 |
+
"grad_norm": 442402.25,
|
| 1214 |
+
"learning_rate": 1.2404692082111438e-05,
|
| 1215 |
+
"loss": 1.7881,
|
| 1216 |
+
"step": 8100
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 1.8055168570632487,
|
| 1220 |
+
"eval_loss": 1.6209757328033447,
|
| 1221 |
+
"eval_runtime": 62.8346,
|
| 1222 |
+
"eval_samples_per_second": 212.749,
|
| 1223 |
+
"eval_steps_per_second": 13.305,
|
| 1224 |
+
"step": 8100
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.827807188631931,
|
| 1228 |
+
"grad_norm": 482508.3125,
|
| 1229 |
+
"learning_rate": 1.2173174872665536e-05,
|
| 1230 |
+
"loss": 1.7967,
|
| 1231 |
+
"step": 8200
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 1.827807188631931,
|
| 1235 |
+
"eval_loss": 1.6282365322113037,
|
| 1236 |
+
"eval_runtime": 63.2359,
|
| 1237 |
+
"eval_samples_per_second": 211.399,
|
| 1238 |
+
"eval_steps_per_second": 13.22,
|
| 1239 |
+
"step": 8200
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 1.8500975202006131,
|
| 1243 |
+
"grad_norm": 443377.25,
|
| 1244 |
+
"learning_rate": 1.1941657663219632e-05,
|
| 1245 |
+
"loss": 1.7921,
|
| 1246 |
+
"step": 8300
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.8500975202006131,
|
| 1250 |
+
"eval_loss": 1.624315619468689,
|
| 1251 |
+
"eval_runtime": 63.0489,
|
| 1252 |
+
"eval_samples_per_second": 212.026,
|
| 1253 |
+
"eval_steps_per_second": 13.26,
|
| 1254 |
+
"step": 8300
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 1.8723878517692951,
|
| 1258 |
+
"grad_norm": 397804.8125,
|
| 1259 |
+
"learning_rate": 1.1710140453773732e-05,
|
| 1260 |
+
"loss": 1.7898,
|
| 1261 |
+
"step": 8400
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.8723878517692951,
|
| 1265 |
+
"eval_loss": 1.6195310354232788,
|
| 1266 |
+
"eval_runtime": 63.4127,
|
| 1267 |
+
"eval_samples_per_second": 210.81,
|
| 1268 |
+
"eval_steps_per_second": 13.183,
|
| 1269 |
+
"step": 8400
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.894678183337977,
|
| 1273 |
+
"grad_norm": 422386.96875,
|
| 1274 |
+
"learning_rate": 1.1478623244327828e-05,
|
| 1275 |
+
"loss": 1.779,
|
| 1276 |
+
"step": 8500
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.894678183337977,
|
| 1280 |
+
"eval_loss": 1.6192779541015625,
|
| 1281 |
+
"eval_runtime": 63.476,
|
| 1282 |
+
"eval_samples_per_second": 210.599,
|
| 1283 |
+
"eval_steps_per_second": 13.17,
|
| 1284 |
+
"step": 8500
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.9169685149066593,
|
| 1288 |
+
"grad_norm": 411348.03125,
|
| 1289 |
+
"learning_rate": 1.1247106034881927e-05,
|
| 1290 |
+
"loss": 1.7852,
|
| 1291 |
+
"step": 8600
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.9169685149066593,
|
| 1295 |
+
"eval_loss": 1.6169335842132568,
|
| 1296 |
+
"eval_runtime": 63.0679,
|
| 1297 |
+
"eval_samples_per_second": 211.962,
|
| 1298 |
+
"eval_steps_per_second": 13.256,
|
| 1299 |
+
"step": 8600
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.9392588464753413,
|
| 1303 |
+
"grad_norm": 444615.65625,
|
| 1304 |
+
"learning_rate": 1.1015588825436025e-05,
|
| 1305 |
+
"loss": 1.7813,
|
| 1306 |
+
"step": 8700
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.9392588464753413,
|
| 1310 |
+
"eval_loss": 1.6124924421310425,
|
| 1311 |
+
"eval_runtime": 63.9864,
|
| 1312 |
+
"eval_samples_per_second": 208.919,
|
| 1313 |
+
"eval_steps_per_second": 13.065,
|
| 1314 |
+
"step": 8700
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.9615491780440233,
|
| 1318 |
+
"grad_norm": 414404.125,
|
| 1319 |
+
"learning_rate": 1.0784071615990121e-05,
|
| 1320 |
+
"loss": 1.7893,
|
| 1321 |
+
"step": 8800
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 1.9615491780440233,
|
| 1325 |
+
"eval_loss": 1.6191661357879639,
|
| 1326 |
+
"eval_runtime": 63.6221,
|
| 1327 |
+
"eval_samples_per_second": 210.116,
|
| 1328 |
+
"eval_steps_per_second": 13.14,
|
| 1329 |
+
"step": 8800
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 1.9838395096127055,
|
| 1333 |
+
"grad_norm": 445457.1875,
|
| 1334 |
+
"learning_rate": 1.055255440654422e-05,
|
| 1335 |
+
"loss": 1.7905,
|
| 1336 |
+
"step": 8900
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 1.9838395096127055,
|
| 1340 |
+
"eval_loss": 1.6134953498840332,
|
| 1341 |
+
"eval_runtime": 63.3933,
|
| 1342 |
+
"eval_samples_per_second": 210.874,
|
| 1343 |
+
"eval_steps_per_second": 13.188,
|
| 1344 |
+
"step": 8900
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.0061298411813877,
|
| 1348 |
+
"grad_norm": 439959.25,
|
| 1349 |
+
"learning_rate": 1.0321037197098317e-05,
|
| 1350 |
+
"loss": 1.7873,
|
| 1351 |
+
"step": 9000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 2.0061298411813877,
|
| 1355 |
+
"eval_loss": 1.6150258779525757,
|
| 1356 |
+
"eval_runtime": 62.9808,
|
| 1357 |
+
"eval_samples_per_second": 212.255,
|
| 1358 |
+
"eval_steps_per_second": 13.274,
|
| 1359 |
+
"step": 9000
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 2.0284201727500695,
|
| 1363 |
+
"grad_norm": 399886.46875,
|
| 1364 |
+
"learning_rate": 1.0089519987652416e-05,
|
| 1365 |
+
"loss": 1.7304,
|
| 1366 |
+
"step": 9100
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 2.0284201727500695,
|
| 1370 |
+
"eval_loss": 1.615242600440979,
|
| 1371 |
+
"eval_runtime": 63.4005,
|
| 1372 |
+
"eval_samples_per_second": 210.85,
|
| 1373 |
+
"eval_steps_per_second": 13.186,
|
| 1374 |
+
"step": 9100
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.0507105043187517,
|
| 1378 |
+
"grad_norm": 432171.59375,
|
| 1379 |
+
"learning_rate": 9.858002778206514e-06,
|
| 1380 |
+
"loss": 1.748,
|
| 1381 |
+
"step": 9200
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 2.0507105043187517,
|
| 1385 |
+
"eval_loss": 1.6178884506225586,
|
| 1386 |
+
"eval_runtime": 63.1372,
|
| 1387 |
+
"eval_samples_per_second": 211.729,
|
| 1388 |
+
"eval_steps_per_second": 13.241,
|
| 1389 |
+
"step": 9200
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.073000835887434,
|
| 1393 |
+
"grad_norm": 438172.875,
|
| 1394 |
+
"learning_rate": 9.62648556876061e-06,
|
| 1395 |
+
"loss": 1.7488,
|
| 1396 |
+
"step": 9300
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.073000835887434,
|
| 1400 |
+
"eval_loss": 1.615029215812683,
|
| 1401 |
+
"eval_runtime": 63.7948,
|
| 1402 |
+
"eval_samples_per_second": 209.547,
|
| 1403 |
+
"eval_steps_per_second": 13.105,
|
| 1404 |
+
"step": 9300
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.095291167456116,
|
| 1408 |
+
"grad_norm": 422492.28125,
|
| 1409 |
+
"learning_rate": 9.39496835931471e-06,
|
| 1410 |
+
"loss": 1.7482,
|
| 1411 |
+
"step": 9400
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 2.095291167456116,
|
| 1415 |
+
"eval_loss": 1.6207051277160645,
|
| 1416 |
+
"eval_runtime": 63.458,
|
| 1417 |
+
"eval_samples_per_second": 210.659,
|
| 1418 |
+
"eval_steps_per_second": 13.174,
|
| 1419 |
+
"step": 9400
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 2.117581499024798,
|
| 1423 |
+
"grad_norm": 438706.75,
|
| 1424 |
+
"learning_rate": 9.163451149868806e-06,
|
| 1425 |
+
"loss": 1.739,
|
| 1426 |
+
"step": 9500
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 2.117581499024798,
|
| 1430 |
+
"eval_loss": 1.6097335815429688,
|
| 1431 |
+
"eval_runtime": 63.1577,
|
| 1432 |
+
"eval_samples_per_second": 211.66,
|
| 1433 |
+
"eval_steps_per_second": 13.237,
|
| 1434 |
+
"step": 9500
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.13987183059348,
|
| 1438 |
+
"grad_norm": 418132.5625,
|
| 1439 |
+
"learning_rate": 8.931933940422906e-06,
|
| 1440 |
+
"loss": 1.7599,
|
| 1441 |
+
"step": 9600
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.13987183059348,
|
| 1445 |
+
"eval_loss": 1.6131938695907593,
|
| 1446 |
+
"eval_runtime": 63.4093,
|
| 1447 |
+
"eval_samples_per_second": 210.821,
|
| 1448 |
+
"eval_steps_per_second": 13.184,
|
| 1449 |
+
"step": 9600
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 2.1621621621621623,
|
| 1453 |
+
"grad_norm": 430660.1875,
|
| 1454 |
+
"learning_rate": 8.700416730977003e-06,
|
| 1455 |
+
"loss": 1.7473,
|
| 1456 |
+
"step": 9700
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 2.1621621621621623,
|
| 1460 |
+
"eval_loss": 1.6116857528686523,
|
| 1461 |
+
"eval_runtime": 63.5141,
|
| 1462 |
+
"eval_samples_per_second": 210.473,
|
| 1463 |
+
"eval_steps_per_second": 13.162,
|
| 1464 |
+
"step": 9700
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 2.184452493730844,
|
| 1468 |
+
"grad_norm": 410735.0625,
|
| 1469 |
+
"learning_rate": 8.4688995215311e-06,
|
| 1470 |
+
"loss": 1.75,
|
| 1471 |
+
"step": 9800
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 2.184452493730844,
|
| 1475 |
+
"eval_loss": 1.611021876335144,
|
| 1476 |
+
"eval_runtime": 63.3479,
|
| 1477 |
+
"eval_samples_per_second": 211.025,
|
| 1478 |
+
"eval_steps_per_second": 13.197,
|
| 1479 |
+
"step": 9800
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 2.2067428252995263,
|
| 1483 |
+
"grad_norm": 437123.8125,
|
| 1484 |
+
"learning_rate": 8.237382312085199e-06,
|
| 1485 |
+
"loss": 1.7432,
|
| 1486 |
+
"step": 9900
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 2.2067428252995263,
|
| 1490 |
+
"eval_loss": 1.614385962486267,
|
| 1491 |
+
"eval_runtime": 63.4099,
|
| 1492 |
+
"eval_samples_per_second": 210.819,
|
| 1493 |
+
"eval_steps_per_second": 13.184,
|
| 1494 |
+
"step": 9900
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.2290331568682085,
|
| 1498 |
+
"grad_norm": 434528.1875,
|
| 1499 |
+
"learning_rate": 8.005865102639295e-06,
|
| 1500 |
+
"loss": 1.7491,
|
| 1501 |
+
"step": 10000
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.2290331568682085,
|
| 1505 |
+
"eval_loss": 1.6123193502426147,
|
| 1506 |
+
"eval_runtime": 63.2705,
|
| 1507 |
+
"eval_samples_per_second": 211.283,
|
| 1508 |
+
"eval_steps_per_second": 13.213,
|
| 1509 |
+
"step": 10000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 2.2513234884368907,
|
| 1513 |
+
"grad_norm": 394168.875,
|
| 1514 |
+
"learning_rate": 7.774347893193395e-06,
|
| 1515 |
+
"loss": 1.7377,
|
| 1516 |
+
"step": 10100
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 2.2513234884368907,
|
| 1520 |
+
"eval_loss": 1.6091859340667725,
|
| 1521 |
+
"eval_runtime": 63.9924,
|
| 1522 |
+
"eval_samples_per_second": 208.9,
|
| 1523 |
+
"eval_steps_per_second": 13.064,
|
| 1524 |
+
"step": 10100
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 2.2736138200055724,
|
| 1528 |
+
"grad_norm": 405977.28125,
|
| 1529 |
+
"learning_rate": 7.542830683747492e-06,
|
| 1530 |
+
"loss": 1.7439,
|
| 1531 |
+
"step": 10200
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 2.2736138200055724,
|
| 1535 |
+
"eval_loss": 1.6095374822616577,
|
| 1536 |
+
"eval_runtime": 63.1561,
|
| 1537 |
+
"eval_samples_per_second": 211.666,
|
| 1538 |
+
"eval_steps_per_second": 13.237,
|
| 1539 |
+
"step": 10200
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 2.2959041515742546,
|
| 1543 |
+
"grad_norm": 441095.4375,
|
| 1544 |
+
"learning_rate": 7.31131347430159e-06,
|
| 1545 |
+
"loss": 1.7417,
|
| 1546 |
+
"step": 10300
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 2.2959041515742546,
|
| 1550 |
+
"eval_loss": 1.6078873872756958,
|
| 1551 |
+
"eval_runtime": 62.9452,
|
| 1552 |
+
"eval_samples_per_second": 212.375,
|
| 1553 |
+
"eval_steps_per_second": 13.281,
|
| 1554 |
+
"step": 10300
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 2.318194483142937,
|
| 1558 |
+
"grad_norm": 450342.375,
|
| 1559 |
+
"learning_rate": 7.079796264855688e-06,
|
| 1560 |
+
"loss": 1.7482,
|
| 1561 |
+
"step": 10400
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 2.318194483142937,
|
| 1565 |
+
"eval_loss": 1.6116305589675903,
|
| 1566 |
+
"eval_runtime": 63.4969,
|
| 1567 |
+
"eval_samples_per_second": 210.53,
|
| 1568 |
+
"eval_steps_per_second": 13.166,
|
| 1569 |
+
"step": 10400
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 2.340484814711619,
|
| 1573 |
+
"grad_norm": 462851.03125,
|
| 1574 |
+
"learning_rate": 6.848279055409786e-06,
|
| 1575 |
+
"loss": 1.7391,
|
| 1576 |
+
"step": 10500
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 2.340484814711619,
|
| 1580 |
+
"eval_loss": 1.6078118085861206,
|
| 1581 |
+
"eval_runtime": 63.3093,
|
| 1582 |
+
"eval_samples_per_second": 211.154,
|
| 1583 |
+
"eval_steps_per_second": 13.205,
|
| 1584 |
+
"step": 10500
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.362775146280301,
|
| 1588 |
+
"grad_norm": 405519.75,
|
| 1589 |
+
"learning_rate": 6.616761845963883e-06,
|
| 1590 |
+
"loss": 1.7345,
|
| 1591 |
+
"step": 10600
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 2.362775146280301,
|
| 1595 |
+
"eval_loss": 1.6122682094573975,
|
| 1596 |
+
"eval_runtime": 63.3463,
|
| 1597 |
+
"eval_samples_per_second": 211.031,
|
| 1598 |
+
"eval_steps_per_second": 13.197,
|
| 1599 |
+
"step": 10600
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 2.385065477848983,
|
| 1603 |
+
"grad_norm": 471771.9375,
|
| 1604 |
+
"learning_rate": 6.385244636517981e-06,
|
| 1605 |
+
"loss": 1.7365,
|
| 1606 |
+
"step": 10700
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.385065477848983,
|
| 1610 |
+
"eval_loss": 1.6120107173919678,
|
| 1611 |
+
"eval_runtime": 63.2512,
|
| 1612 |
+
"eval_samples_per_second": 211.348,
|
| 1613 |
+
"eval_steps_per_second": 13.217,
|
| 1614 |
+
"step": 10700
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.4073558094176652,
|
| 1618 |
+
"grad_norm": 416676.4375,
|
| 1619 |
+
"learning_rate": 6.153727427072079e-06,
|
| 1620 |
+
"loss": 1.7446,
|
| 1621 |
+
"step": 10800
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.4073558094176652,
|
| 1625 |
+
"eval_loss": 1.6103585958480835,
|
| 1626 |
+
"eval_runtime": 63.4362,
|
| 1627 |
+
"eval_samples_per_second": 210.731,
|
| 1628 |
+
"eval_steps_per_second": 13.179,
|
| 1629 |
+
"step": 10800
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 2.429646140986347,
|
| 1633 |
+
"grad_norm": 409846.5,
|
| 1634 |
+
"learning_rate": 5.9222102176261775e-06,
|
| 1635 |
+
"loss": 1.7273,
|
| 1636 |
+
"step": 10900
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 2.429646140986347,
|
| 1640 |
+
"eval_loss": 1.6118780374526978,
|
| 1641 |
+
"eval_runtime": 63.3423,
|
| 1642 |
+
"eval_samples_per_second": 211.044,
|
| 1643 |
+
"eval_steps_per_second": 13.198,
|
| 1644 |
+
"step": 10900
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 2.4519364725550292,
|
| 1648 |
+
"grad_norm": 400530.59375,
|
| 1649 |
+
"learning_rate": 5.690693008180275e-06,
|
| 1650 |
+
"loss": 1.7494,
|
| 1651 |
+
"step": 11000
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 2.4519364725550292,
|
| 1655 |
+
"eval_loss": 1.6059410572052002,
|
| 1656 |
+
"eval_runtime": 63.1379,
|
| 1657 |
+
"eval_samples_per_second": 211.727,
|
| 1658 |
+
"eval_steps_per_second": 13.241,
|
| 1659 |
+
"step": 11000
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 2.4742268041237114,
|
| 1663 |
+
"grad_norm": 427720.5625,
|
| 1664 |
+
"learning_rate": 5.459175798734372e-06,
|
| 1665 |
+
"loss": 1.7332,
|
| 1666 |
+
"step": 11100
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 2.4742268041237114,
|
| 1670 |
+
"eval_loss": 1.6064603328704834,
|
| 1671 |
+
"eval_runtime": 63.7921,
|
| 1672 |
+
"eval_samples_per_second": 209.556,
|
| 1673 |
+
"eval_steps_per_second": 13.105,
|
| 1674 |
+
"step": 11100
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 2.496517135692393,
|
| 1678 |
+
"grad_norm": 450690.875,
|
| 1679 |
+
"learning_rate": 5.22765858928847e-06,
|
| 1680 |
+
"loss": 1.7285,
|
| 1681 |
+
"step": 11200
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 2.496517135692393,
|
| 1685 |
+
"eval_loss": 1.6082170009613037,
|
| 1686 |
+
"eval_runtime": 62.5222,
|
| 1687 |
+
"eval_samples_per_second": 213.812,
|
| 1688 |
+
"eval_steps_per_second": 13.371,
|
| 1689 |
+
"step": 11200
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 2.5188074672610754,
|
| 1693 |
+
"grad_norm": 412636.5,
|
| 1694 |
+
"learning_rate": 4.996141379842568e-06,
|
| 1695 |
+
"loss": 1.7319,
|
| 1696 |
+
"step": 11300
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 2.5188074672610754,
|
| 1700 |
+
"eval_loss": 1.6035947799682617,
|
| 1701 |
+
"eval_runtime": 63.3474,
|
| 1702 |
+
"eval_samples_per_second": 211.027,
|
| 1703 |
+
"eval_steps_per_second": 13.197,
|
| 1704 |
+
"step": 11300
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.5410977988297576,
|
| 1708 |
+
"grad_norm": 403399.875,
|
| 1709 |
+
"learning_rate": 4.764624170396667e-06,
|
| 1710 |
+
"loss": 1.7245,
|
| 1711 |
+
"step": 11400
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.5410977988297576,
|
| 1715 |
+
"eval_loss": 1.6081373691558838,
|
| 1716 |
+
"eval_runtime": 63.6595,
|
| 1717 |
+
"eval_samples_per_second": 209.992,
|
| 1718 |
+
"eval_steps_per_second": 13.132,
|
| 1719 |
+
"step": 11400
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 2.56338813039844,
|
| 1723 |
+
"grad_norm": 432179.4375,
|
| 1724 |
+
"learning_rate": 4.5331069609507645e-06,
|
| 1725 |
+
"loss": 1.7379,
|
| 1726 |
+
"step": 11500
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 2.56338813039844,
|
| 1730 |
+
"eval_loss": 1.6043556928634644,
|
| 1731 |
+
"eval_runtime": 63.1427,
|
| 1732 |
+
"eval_samples_per_second": 211.711,
|
| 1733 |
+
"eval_steps_per_second": 13.24,
|
| 1734 |
+
"step": 11500
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 2.585678461967122,
|
| 1738 |
+
"grad_norm": 398148.96875,
|
| 1739 |
+
"learning_rate": 4.3015897515048615e-06,
|
| 1740 |
+
"loss": 1.7349,
|
| 1741 |
+
"step": 11600
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 2.585678461967122,
|
| 1745 |
+
"eval_loss": 1.6080468893051147,
|
| 1746 |
+
"eval_runtime": 63.1768,
|
| 1747 |
+
"eval_samples_per_second": 211.597,
|
| 1748 |
+
"eval_steps_per_second": 13.233,
|
| 1749 |
+
"step": 11600
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 2.607968793535804,
|
| 1753 |
+
"grad_norm": 406493.65625,
|
| 1754 |
+
"learning_rate": 4.070072542058959e-06,
|
| 1755 |
+
"loss": 1.7408,
|
| 1756 |
+
"step": 11700
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 2.607968793535804,
|
| 1760 |
+
"eval_loss": 1.6043606996536255,
|
| 1761 |
+
"eval_runtime": 63.7306,
|
| 1762 |
+
"eval_samples_per_second": 209.758,
|
| 1763 |
+
"eval_steps_per_second": 13.118,
|
| 1764 |
+
"step": 11700
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 2.630259125104486,
|
| 1768 |
+
"grad_norm": 415316.5625,
|
| 1769 |
+
"learning_rate": 3.838555332613058e-06,
|
| 1770 |
+
"loss": 1.7317,
|
| 1771 |
+
"step": 11800
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 2.630259125104486,
|
| 1775 |
+
"eval_loss": 1.6045427322387695,
|
| 1776 |
+
"eval_runtime": 63.3899,
|
| 1777 |
+
"eval_samples_per_second": 210.885,
|
| 1778 |
+
"eval_steps_per_second": 13.188,
|
| 1779 |
+
"step": 11800
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 2.652549456673168,
|
| 1783 |
+
"grad_norm": 433577.84375,
|
| 1784 |
+
"learning_rate": 3.6070381231671554e-06,
|
| 1785 |
+
"loss": 1.7288,
|
| 1786 |
+
"step": 11900
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 2.652549456673168,
|
| 1790 |
+
"eval_loss": 1.603334903717041,
|
| 1791 |
+
"eval_runtime": 63.1008,
|
| 1792 |
+
"eval_samples_per_second": 211.851,
|
| 1793 |
+
"eval_steps_per_second": 13.249,
|
| 1794 |
+
"step": 11900
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 2.67483978824185,
|
| 1798 |
+
"grad_norm": 408270.8125,
|
| 1799 |
+
"learning_rate": 3.3755209137212533e-06,
|
| 1800 |
+
"loss": 1.7327,
|
| 1801 |
+
"step": 12000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 2.67483978824185,
|
| 1805 |
+
"eval_loss": 1.6032938957214355,
|
| 1806 |
+
"eval_runtime": 62.9232,
|
| 1807 |
+
"eval_samples_per_second": 212.45,
|
| 1808 |
+
"eval_steps_per_second": 13.286,
|
| 1809 |
+
"step": 12000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.697130119810532,
|
| 1813 |
+
"grad_norm": 412520.28125,
|
| 1814 |
+
"learning_rate": 3.144003704275351e-06,
|
| 1815 |
+
"loss": 1.7349,
|
| 1816 |
+
"step": 12100
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.697130119810532,
|
| 1820 |
+
"eval_loss": 1.6040232181549072,
|
| 1821 |
+
"eval_runtime": 63.2685,
|
| 1822 |
+
"eval_samples_per_second": 211.29,
|
| 1823 |
+
"eval_steps_per_second": 13.214,
|
| 1824 |
+
"step": 12100
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.7194204513792144,
|
| 1828 |
+
"grad_norm": 430910.1875,
|
| 1829 |
+
"learning_rate": 2.9124864948294494e-06,
|
| 1830 |
+
"loss": 1.7378,
|
| 1831 |
+
"step": 12200
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 2.7194204513792144,
|
| 1835 |
+
"eval_loss": 1.6026825904846191,
|
| 1836 |
+
"eval_runtime": 63.0275,
|
| 1837 |
+
"eval_samples_per_second": 212.098,
|
| 1838 |
+
"eval_steps_per_second": 13.264,
|
| 1839 |
+
"step": 12200
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 2.741710782947896,
|
| 1843 |
+
"grad_norm": 426524.9375,
|
| 1844 |
+
"learning_rate": 2.680969285383547e-06,
|
| 1845 |
+
"loss": 1.7438,
|
| 1846 |
+
"step": 12300
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 2.741710782947896,
|
| 1850 |
+
"eval_loss": 1.6039636135101318,
|
| 1851 |
+
"eval_runtime": 63.8654,
|
| 1852 |
+
"eval_samples_per_second": 209.315,
|
| 1853 |
+
"eval_steps_per_second": 13.09,
|
| 1854 |
+
"step": 12300
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 2.7640011145165784,
|
| 1858 |
+
"grad_norm": 439803.8125,
|
| 1859 |
+
"learning_rate": 2.449452075937645e-06,
|
| 1860 |
+
"loss": 1.7357,
|
| 1861 |
+
"step": 12400
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 2.7640011145165784,
|
| 1865 |
+
"eval_loss": 1.6037323474884033,
|
| 1866 |
+
"eval_runtime": 63.1113,
|
| 1867 |
+
"eval_samples_per_second": 211.816,
|
| 1868 |
+
"eval_steps_per_second": 13.246,
|
| 1869 |
+
"step": 12400
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 2.7862914460852606,
|
| 1873 |
+
"grad_norm": 442227.34375,
|
| 1874 |
+
"learning_rate": 2.2179348664917425e-06,
|
| 1875 |
+
"loss": 1.7333,
|
| 1876 |
+
"step": 12500
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 2.7862914460852606,
|
| 1880 |
+
"eval_loss": 1.6014666557312012,
|
| 1881 |
+
"eval_runtime": 63.3883,
|
| 1882 |
+
"eval_samples_per_second": 210.891,
|
| 1883 |
+
"eval_steps_per_second": 13.189,
|
| 1884 |
+
"step": 12500
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 2.8085817776539423,
|
| 1888 |
+
"grad_norm": 409348.65625,
|
| 1889 |
+
"learning_rate": 1.9864176570458403e-06,
|
| 1890 |
+
"loss": 1.7344,
|
| 1891 |
+
"step": 12600
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 2.8085817776539423,
|
| 1895 |
+
"eval_loss": 1.6025654077529907,
|
| 1896 |
+
"eval_runtime": 63.562,
|
| 1897 |
+
"eval_samples_per_second": 210.315,
|
| 1898 |
+
"eval_steps_per_second": 13.153,
|
| 1899 |
+
"step": 12600
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 2.8308721092226246,
|
| 1903 |
+
"grad_norm": 438774.5,
|
| 1904 |
+
"learning_rate": 1.7549004475999384e-06,
|
| 1905 |
+
"loss": 1.7356,
|
| 1906 |
+
"step": 12700
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 2.8308721092226246,
|
| 1910 |
+
"eval_loss": 1.6015514135360718,
|
| 1911 |
+
"eval_runtime": 63.4784,
|
| 1912 |
+
"eval_samples_per_second": 210.591,
|
| 1913 |
+
"eval_steps_per_second": 13.17,
|
| 1914 |
+
"step": 12700
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.8531624407913068,
|
| 1918 |
+
"grad_norm": 425528.09375,
|
| 1919 |
+
"learning_rate": 1.523383238154036e-06,
|
| 1920 |
+
"loss": 1.7494,
|
| 1921 |
+
"step": 12800
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.8531624407913068,
|
| 1925 |
+
"eval_loss": 1.602927565574646,
|
| 1926 |
+
"eval_runtime": 63.9753,
|
| 1927 |
+
"eval_samples_per_second": 208.956,
|
| 1928 |
+
"eval_steps_per_second": 13.068,
|
| 1929 |
+
"step": 12800
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 2.875452772359989,
|
| 1933 |
+
"grad_norm": 402082.0625,
|
| 1934 |
+
"learning_rate": 1.291866028708134e-06,
|
| 1935 |
+
"loss": 1.7414,
|
| 1936 |
+
"step": 12900
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 2.875452772359989,
|
| 1940 |
+
"eval_loss": 1.6020632982254028,
|
| 1941 |
+
"eval_runtime": 63.2754,
|
| 1942 |
+
"eval_samples_per_second": 211.267,
|
| 1943 |
+
"eval_steps_per_second": 13.212,
|
| 1944 |
+
"step": 12900
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 2.897743103928671,
|
| 1948 |
+
"grad_norm": 409632.125,
|
| 1949 |
+
"learning_rate": 1.0603488192622319e-06,
|
| 1950 |
+
"loss": 1.7337,
|
| 1951 |
+
"step": 13000
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 2.897743103928671,
|
| 1955 |
+
"eval_loss": 1.6021629571914673,
|
| 1956 |
+
"eval_runtime": 63.0484,
|
| 1957 |
+
"eval_samples_per_second": 212.028,
|
| 1958 |
+
"eval_steps_per_second": 13.26,
|
| 1959 |
+
"step": 13000
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 2.920033435497353,
|
| 1963 |
+
"grad_norm": 431921.65625,
|
| 1964 |
+
"learning_rate": 8.288316098163297e-07,
|
| 1965 |
+
"loss": 1.7239,
|
| 1966 |
+
"step": 13100
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 2.920033435497353,
|
| 1970 |
+
"eval_loss": 1.6020002365112305,
|
| 1971 |
+
"eval_runtime": 63.0873,
|
| 1972 |
+
"eval_samples_per_second": 211.897,
|
| 1973 |
+
"eval_steps_per_second": 13.251,
|
| 1974 |
+
"step": 13100
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 2.942323767066035,
|
| 1978 |
+
"grad_norm": 436490.65625,
|
| 1979 |
+
"learning_rate": 5.973144003704276e-07,
|
| 1980 |
+
"loss": 1.7461,
|
| 1981 |
+
"step": 13200
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 2.942323767066035,
|
| 1985 |
+
"eval_loss": 1.6018171310424805,
|
| 1986 |
+
"eval_runtime": 63.2016,
|
| 1987 |
+
"eval_samples_per_second": 211.514,
|
| 1988 |
+
"eval_steps_per_second": 13.228,
|
| 1989 |
+
"step": 13200
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 2.9646140986347174,
|
| 1993 |
+
"grad_norm": 396898.375,
|
| 1994 |
+
"learning_rate": 3.657971909245254e-07,
|
| 1995 |
+
"loss": 1.7358,
|
| 1996 |
+
"step": 13300
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 2.9646140986347174,
|
| 2000 |
+
"eval_loss": 1.601110577583313,
|
| 2001 |
+
"eval_runtime": 63.1463,
|
| 2002 |
+
"eval_samples_per_second": 211.699,
|
| 2003 |
+
"eval_steps_per_second": 13.239,
|
| 2004 |
+
"step": 13300
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 2.986904430203399,
|
| 2008 |
+
"grad_norm": 419936.46875,
|
| 2009 |
+
"learning_rate": 1.3427998147862324e-07,
|
| 2010 |
+
"loss": 1.7293,
|
| 2011 |
+
"step": 13400
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 2.986904430203399,
|
| 2015 |
+
"eval_loss": 1.6014801263809204,
|
| 2016 |
+
"eval_runtime": 63.6722,
|
| 2017 |
+
"eval_samples_per_second": 209.95,
|
| 2018 |
+
"eval_steps_per_second": 13.13,
|
| 2019 |
+
"step": 13400
|
| 2020 |
+
}
|
| 2021 |
+
],
|
| 2022 |
+
"logging_steps": 100,
|
| 2023 |
+
"max_steps": 13458,
|
| 2024 |
+
"num_input_tokens_seen": 0,
|
| 2025 |
+
"num_train_epochs": 3,
|
| 2026 |
+
"save_steps": 100,
|
| 2027 |
+
"stateful_callbacks": {
|
| 2028 |
+
"TrainerControl": {
|
| 2029 |
+
"args": {
|
| 2030 |
+
"should_epoch_stop": false,
|
| 2031 |
+
"should_evaluate": false,
|
| 2032 |
+
"should_log": false,
|
| 2033 |
+
"should_save": true,
|
| 2034 |
+
"should_training_stop": true
|
| 2035 |
+
},
|
| 2036 |
+
"attributes": {}
|
| 2037 |
+
}
|
| 2038 |
+
},
|
| 2039 |
+
"total_flos": 5.251647920091955e+17,
|
| 2040 |
+
"train_batch_size": 16,
|
| 2041 |
+
"trial_name": null,
|
| 2042 |
+
"trial_params": null
|
| 2043 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c06774a3300436e29902a6f2c3d79a1a82ab46088a613c1732e0a0aa94ede4da
|
| 3 |
+
size 5240
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|