Training in progress, step 38000, checkpoint
Browse files- checkpoint-38000/config.json +59 -0
- checkpoint-38000/generation_config.json +12 -0
- checkpoint-38000/model.safetensors +3 -0
- checkpoint-38000/optimizer.pt +3 -0
- checkpoint-38000/rng_state.pth +3 -0
- checkpoint-38000/scheduler.pt +3 -0
- checkpoint-38000/sentencepiece.bpe.model +3 -0
- checkpoint-38000/special_tokens_map.json +15 -0
- checkpoint-38000/tokenizer.json +0 -0
- checkpoint-38000/tokenizer_config.json +55 -0
- checkpoint-38000/trainer_state.json +664 -0
- checkpoint-38000/training_args.bin +3 -0
checkpoint-38000/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "moussakam/Arabart",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": true,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"MBartForConditionalGeneration"
|
| 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 |
+
"do_blenderbot_90_layernorm": false,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": true,
|
| 23 |
+
"encoder_attention_heads": 12,
|
| 24 |
+
"encoder_ffn_dim": 3072,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 6,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"extra_pos_embeddings": 2,
|
| 29 |
+
"force_bos_token_to_be_generated": false,
|
| 30 |
+
"forced_eos_token_id": 2,
|
| 31 |
+
"gradient_checkpointing": false,
|
| 32 |
+
"id2label": {
|
| 33 |
+
"0": "LABEL_0",
|
| 34 |
+
"1": "LABEL_1",
|
| 35 |
+
"2": "LABEL_2"
|
| 36 |
+
},
|
| 37 |
+
"init_std": 0.02,
|
| 38 |
+
"is_encoder_decoder": true,
|
| 39 |
+
"label2id": {
|
| 40 |
+
"LABEL_0": 0,
|
| 41 |
+
"LABEL_1": 1,
|
| 42 |
+
"LABEL_2": 2
|
| 43 |
+
},
|
| 44 |
+
"max_position_embeddings": 1024,
|
| 45 |
+
"model_type": "mbart",
|
| 46 |
+
"no_repeat_ngram_size": 3,
|
| 47 |
+
"normalize_before": true,
|
| 48 |
+
"normalize_embedding": true,
|
| 49 |
+
"num_beams": 4,
|
| 50 |
+
"num_hidden_layers": 6,
|
| 51 |
+
"pad_token_id": 1,
|
| 52 |
+
"scale_embedding": false,
|
| 53 |
+
"static_position_embeddings": false,
|
| 54 |
+
"tokenizer_class": "BarthezTokenizer",
|
| 55 |
+
"torch_dtype": "float32",
|
| 56 |
+
"transformers_version": "4.42.4",
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 50002
|
| 59 |
+
}
|
checkpoint-38000/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"max_new_tokens": 100,
|
| 8 |
+
"no_repeat_ngram_size": 3,
|
| 9 |
+
"num_beams": 3,
|
| 10 |
+
"pad_token_id": 1,
|
| 11 |
+
"transformers_version": "4.42.4"
|
| 12 |
+
}
|
checkpoint-38000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:554d1b35cd8b28161f7116ecdabe8451c7f3091deda340652fb4aeeabc7008a4
|
| 3 |
+
size 557116312
|
checkpoint-38000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0fb4abe100f8a5d5aeb25d863138a992a32861a5cee13db901a830a21c39249
|
| 3 |
+
size 1113991930
|
checkpoint-38000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:737ab921a0c766db437942a6c79858641ceb4694dc05d024aaaf20a0464ae7f6
|
| 3 |
+
size 14244
|
checkpoint-38000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff2d773c135b11db8f1e287d8fd6bc9052edf1ab829c8647dfba119421824bfa
|
| 3 |
+
size 1064
|
checkpoint-38000/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
|
| 3 |
+
size 1315170
|
checkpoint-38000/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": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-38000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-38000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"50001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"pad_token": "<pad>",
|
| 51 |
+
"sep_token": "</s>",
|
| 52 |
+
"sp_model_kwargs": {},
|
| 53 |
+
"tokenizer_class": "BarthezTokenizer",
|
| 54 |
+
"unk_token": "<unk>"
|
| 55 |
+
}
|
checkpoint-38000/trainer_state.json
ADDED
|
@@ -0,0 +1,664 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 28.5073,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/checkpoint-26201",
|
| 4 |
+
"epoch": 11.964735516372796,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 38000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1335826876836762,
|
| 13 |
+
"grad_norm": 5.345764636993408,
|
| 14 |
+
"learning_rate": 3.7102997922232118e-06,
|
| 15 |
+
"loss": 3.9988,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2671653753673524,
|
| 20 |
+
"grad_norm": 5.3753743171691895,
|
| 21 |
+
"learning_rate": 7.4205995844464235e-06,
|
| 22 |
+
"loss": 3.2671,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.4007480630510286,
|
| 27 |
+
"grad_norm": 3.7295212745666504,
|
| 28 |
+
"learning_rate": 1.1130899376669635e-05,
|
| 29 |
+
"loss": 3.1006,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5343307507347048,
|
| 34 |
+
"grad_norm": 4.027897834777832,
|
| 35 |
+
"learning_rate": 1.4841199168892847e-05,
|
| 36 |
+
"loss": 2.9767,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.667913438418381,
|
| 41 |
+
"grad_norm": 3.9697580337524414,
|
| 42 |
+
"learning_rate": 1.855149896111606e-05,
|
| 43 |
+
"loss": 2.8914,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8014961261020572,
|
| 48 |
+
"grad_norm": 3.5195724964141846,
|
| 49 |
+
"learning_rate": 2.226179875333927e-05,
|
| 50 |
+
"loss": 2.8273,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.9350788137857333,
|
| 55 |
+
"grad_norm": 3.447735071182251,
|
| 56 |
+
"learning_rate": 2.5972098545562486e-05,
|
| 57 |
+
"loss": 2.7964,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.0,
|
| 62 |
+
"eval_loss": 2.2515146732330322,
|
| 63 |
+
"eval_rouge1": 25.9968,
|
| 64 |
+
"eval_rouge2": 10.7383,
|
| 65 |
+
"eval_rougeL": 22.8305,
|
| 66 |
+
"eval_runtime": 801.3334,
|
| 67 |
+
"eval_samples_per_second": 5.851,
|
| 68 |
+
"eval_steps_per_second": 0.585,
|
| 69 |
+
"step": 3743
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.0686615014694096,
|
| 73 |
+
"grad_norm": 3.5466370582580566,
|
| 74 |
+
"learning_rate": 2.9682398337785694e-05,
|
| 75 |
+
"loss": 2.7258,
|
| 76 |
+
"step": 4000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.2022441891530857,
|
| 80 |
+
"grad_norm": 3.380523681640625,
|
| 81 |
+
"learning_rate": 3.33926981300089e-05,
|
| 82 |
+
"loss": 2.6799,
|
| 83 |
+
"step": 4500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.3358268768367618,
|
| 87 |
+
"grad_norm": 3.3388278484344482,
|
| 88 |
+
"learning_rate": 3.710299792223212e-05,
|
| 89 |
+
"loss": 2.6635,
|
| 90 |
+
"step": 5000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.4694095645204381,
|
| 94 |
+
"grad_norm": 4.365349292755127,
|
| 95 |
+
"learning_rate": 4.0813297714455326e-05,
|
| 96 |
+
"loss": 2.653,
|
| 97 |
+
"step": 5500
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.6029922522041145,
|
| 101 |
+
"grad_norm": 2.9895472526550293,
|
| 102 |
+
"learning_rate": 4.452359750667854e-05,
|
| 103 |
+
"loss": 2.6307,
|
| 104 |
+
"step": 6000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.7365749398877905,
|
| 108 |
+
"grad_norm": 3.2920846939086914,
|
| 109 |
+
"learning_rate": 4.8233897298901756e-05,
|
| 110 |
+
"loss": 2.6279,
|
| 111 |
+
"step": 6500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.8701576275714666,
|
| 115 |
+
"grad_norm": 2.7936699390411377,
|
| 116 |
+
"learning_rate": 4.708305499888667e-05,
|
| 117 |
+
"loss": 2.6157,
|
| 118 |
+
"step": 7000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.0,
|
| 122 |
+
"eval_loss": 2.2093820571899414,
|
| 123 |
+
"eval_rouge1": 27.1603,
|
| 124 |
+
"eval_rouge2": 11.6742,
|
| 125 |
+
"eval_rougeL": 23.9152,
|
| 126 |
+
"eval_runtime": 800.4224,
|
| 127 |
+
"eval_samples_per_second": 5.858,
|
| 128 |
+
"eval_steps_per_second": 0.586,
|
| 129 |
+
"step": 7486
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.003740315255143,
|
| 133 |
+
"grad_norm": 2.9695687294006348,
|
| 134 |
+
"learning_rate": 4.1516366065464264e-05,
|
| 135 |
+
"loss": 2.5275,
|
| 136 |
+
"step": 7500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.1373230029388193,
|
| 140 |
+
"grad_norm": 2.902341842651367,
|
| 141 |
+
"learning_rate": 3.594967713204186e-05,
|
| 142 |
+
"loss": 2.434,
|
| 143 |
+
"step": 8000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.270905690622495,
|
| 147 |
+
"grad_norm": 2.9437291622161865,
|
| 148 |
+
"learning_rate": 3.0382988198619462e-05,
|
| 149 |
+
"loss": 2.4224,
|
| 150 |
+
"step": 8500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.4044883783061715,
|
| 154 |
+
"grad_norm": 3.196054458618164,
|
| 155 |
+
"learning_rate": 2.4816299265197063e-05,
|
| 156 |
+
"loss": 2.4284,
|
| 157 |
+
"step": 9000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 2.5380710659898478,
|
| 161 |
+
"grad_norm": 2.9762144088745117,
|
| 162 |
+
"learning_rate": 1.924961033177466e-05,
|
| 163 |
+
"loss": 2.4025,
|
| 164 |
+
"step": 9500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.6716537536735236,
|
| 168 |
+
"grad_norm": 2.9706368446350098,
|
| 169 |
+
"learning_rate": 1.3682921398352261e-05,
|
| 170 |
+
"loss": 2.4134,
|
| 171 |
+
"step": 10000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.8052364413572,
|
| 175 |
+
"grad_norm": 3.00219464302063,
|
| 176 |
+
"learning_rate": 8.11623246492986e-06,
|
| 177 |
+
"loss": 2.393,
|
| 178 |
+
"step": 10500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.9388191290408763,
|
| 182 |
+
"grad_norm": 3.0556745529174805,
|
| 183 |
+
"learning_rate": 2.5495435315074595e-06,
|
| 184 |
+
"loss": 2.4,
|
| 185 |
+
"step": 11000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.0,
|
| 189 |
+
"eval_loss": 2.151719093322754,
|
| 190 |
+
"eval_rouge1": 28.0829,
|
| 191 |
+
"eval_rouge2": 12.389,
|
| 192 |
+
"eval_rougeL": 24.8018,
|
| 193 |
+
"eval_runtime": 828.6501,
|
| 194 |
+
"eval_samples_per_second": 5.659,
|
| 195 |
+
"eval_steps_per_second": 0.566,
|
| 196 |
+
"step": 11229
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.0724018167245526,
|
| 200 |
+
"grad_norm": 2.9094104766845703,
|
| 201 |
+
"learning_rate": 2.4396651527295397e-05,
|
| 202 |
+
"loss": 2.3046,
|
| 203 |
+
"step": 11500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.205984504408229,
|
| 207 |
+
"grad_norm": 3.2464346885681152,
|
| 208 |
+
"learning_rate": 2.3283462463264763e-05,
|
| 209 |
+
"loss": 2.3092,
|
| 210 |
+
"step": 12000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.339567192091905,
|
| 214 |
+
"grad_norm": 2.8669161796569824,
|
| 215 |
+
"learning_rate": 2.2170273399234126e-05,
|
| 216 |
+
"loss": 2.311,
|
| 217 |
+
"step": 12500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 3.473149879775581,
|
| 221 |
+
"grad_norm": 2.9395506381988525,
|
| 222 |
+
"learning_rate": 2.1057084335203492e-05,
|
| 223 |
+
"loss": 2.3464,
|
| 224 |
+
"step": 13000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.6067325674592574,
|
| 228 |
+
"grad_norm": 2.589228630065918,
|
| 229 |
+
"learning_rate": 1.994389527117286e-05,
|
| 230 |
+
"loss": 2.3138,
|
| 231 |
+
"step": 13500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 3.7403152551429333,
|
| 235 |
+
"grad_norm": 3.119093418121338,
|
| 236 |
+
"learning_rate": 1.883070620714222e-05,
|
| 237 |
+
"loss": 2.3379,
|
| 238 |
+
"step": 14000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.8738979428266096,
|
| 242 |
+
"grad_norm": 3.049482822418213,
|
| 243 |
+
"learning_rate": 1.7717517143111588e-05,
|
| 244 |
+
"loss": 2.3203,
|
| 245 |
+
"step": 14500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 4.0,
|
| 249 |
+
"eval_loss": 2.1520700454711914,
|
| 250 |
+
"eval_rouge1": 27.9025,
|
| 251 |
+
"eval_rouge2": 12.1745,
|
| 252 |
+
"eval_rougeL": 24.6421,
|
| 253 |
+
"eval_runtime": 806.5195,
|
| 254 |
+
"eval_samples_per_second": 5.814,
|
| 255 |
+
"eval_steps_per_second": 0.582,
|
| 256 |
+
"step": 14972
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.007480630510286,
|
| 260 |
+
"grad_norm": 2.8268468379974365,
|
| 261 |
+
"learning_rate": 1.6604328079080954e-05,
|
| 262 |
+
"loss": 2.3081,
|
| 263 |
+
"step": 15000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 4.141063318193962,
|
| 267 |
+
"grad_norm": 3.0538229942321777,
|
| 268 |
+
"learning_rate": 1.5491139015050317e-05,
|
| 269 |
+
"loss": 2.21,
|
| 270 |
+
"step": 15500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.2746460058776385,
|
| 274 |
+
"grad_norm": 2.8657615184783936,
|
| 275 |
+
"learning_rate": 1.4377949951019681e-05,
|
| 276 |
+
"loss": 2.2212,
|
| 277 |
+
"step": 16000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 4.408228693561314,
|
| 281 |
+
"grad_norm": 3.4228334426879883,
|
| 282 |
+
"learning_rate": 1.3264760886989048e-05,
|
| 283 |
+
"loss": 2.2211,
|
| 284 |
+
"step": 16500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.54181138124499,
|
| 288 |
+
"grad_norm": 2.928118944168091,
|
| 289 |
+
"learning_rate": 1.2151571822958412e-05,
|
| 290 |
+
"loss": 2.2231,
|
| 291 |
+
"step": 17000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 4.675394068928667,
|
| 295 |
+
"grad_norm": 3.1149392127990723,
|
| 296 |
+
"learning_rate": 1.1038382758927777e-05,
|
| 297 |
+
"loss": 2.2522,
|
| 298 |
+
"step": 17500
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 4.808976756612343,
|
| 302 |
+
"grad_norm": 3.263375759124756,
|
| 303 |
+
"learning_rate": 9.925193694897141e-06,
|
| 304 |
+
"loss": 2.2262,
|
| 305 |
+
"step": 18000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.94255944429602,
|
| 309 |
+
"grad_norm": 2.9795596599578857,
|
| 310 |
+
"learning_rate": 8.812004630866506e-06,
|
| 311 |
+
"loss": 2.2432,
|
| 312 |
+
"step": 18500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 5.0,
|
| 316 |
+
"eval_loss": 2.1519482135772705,
|
| 317 |
+
"eval_rouge1": 28.2114,
|
| 318 |
+
"eval_rouge2": 12.4638,
|
| 319 |
+
"eval_rougeL": 24.9195,
|
| 320 |
+
"eval_runtime": 801.5692,
|
| 321 |
+
"eval_samples_per_second": 5.85,
|
| 322 |
+
"eval_steps_per_second": 0.585,
|
| 323 |
+
"step": 18715
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 5.0761421319796955,
|
| 327 |
+
"grad_norm": 3.917699098587036,
|
| 328 |
+
"learning_rate": 2.4619289340101523e-05,
|
| 329 |
+
"loss": 2.1744,
|
| 330 |
+
"step": 19000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 5.209724819663371,
|
| 334 |
+
"grad_norm": 3.097011089324951,
|
| 335 |
+
"learning_rate": 2.3951375901683144e-05,
|
| 336 |
+
"loss": 2.187,
|
| 337 |
+
"step": 19500
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 5.343307507347048,
|
| 341 |
+
"grad_norm": 3.4347126483917236,
|
| 342 |
+
"learning_rate": 2.3283462463264763e-05,
|
| 343 |
+
"loss": 2.2042,
|
| 344 |
+
"step": 20000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 5.476890195030724,
|
| 348 |
+
"grad_norm": 3.750795364379883,
|
| 349 |
+
"learning_rate": 2.261554902484638e-05,
|
| 350 |
+
"loss": 2.2261,
|
| 351 |
+
"step": 20500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 5.6104728827144,
|
| 355 |
+
"grad_norm": 3.1423909664154053,
|
| 356 |
+
"learning_rate": 2.1947635586428e-05,
|
| 357 |
+
"loss": 2.1995,
|
| 358 |
+
"step": 21000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 5.744055570398077,
|
| 362 |
+
"grad_norm": 3.2796082496643066,
|
| 363 |
+
"learning_rate": 2.1279722148009618e-05,
|
| 364 |
+
"loss": 2.2165,
|
| 365 |
+
"step": 21500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 5.8776382580817526,
|
| 369 |
+
"grad_norm": 3.300898313522339,
|
| 370 |
+
"learning_rate": 2.0611808709591237e-05,
|
| 371 |
+
"loss": 2.2252,
|
| 372 |
+
"step": 22000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 6.0,
|
| 376 |
+
"eval_loss": 2.169365644454956,
|
| 377 |
+
"eval_rouge1": 28.1516,
|
| 378 |
+
"eval_rouge2": 12.3777,
|
| 379 |
+
"eval_rougeL": 24.7436,
|
| 380 |
+
"eval_runtime": 795.9208,
|
| 381 |
+
"eval_samples_per_second": 5.891,
|
| 382 |
+
"eval_steps_per_second": 0.589,
|
| 383 |
+
"step": 22458
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 6.011220945765428,
|
| 387 |
+
"grad_norm": 3.3653814792633057,
|
| 388 |
+
"learning_rate": 1.994389527117286e-05,
|
| 389 |
+
"loss": 2.044,
|
| 390 |
+
"step": 22500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 6.144803633449105,
|
| 394 |
+
"grad_norm": 3.162733554840088,
|
| 395 |
+
"learning_rate": 1.9275981832754473e-05,
|
| 396 |
+
"loss": 2.1435,
|
| 397 |
+
"step": 23000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 6.278386321132781,
|
| 401 |
+
"grad_norm": 2.9544992446899414,
|
| 402 |
+
"learning_rate": 1.8608068394336095e-05,
|
| 403 |
+
"loss": 2.1289,
|
| 404 |
+
"step": 23500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 6.411969008816458,
|
| 408 |
+
"grad_norm": 3.7476911544799805,
|
| 409 |
+
"learning_rate": 1.7940154955917714e-05,
|
| 410 |
+
"loss": 2.1454,
|
| 411 |
+
"step": 24000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 6.545551696500134,
|
| 415 |
+
"grad_norm": 3.191617727279663,
|
| 416 |
+
"learning_rate": 1.7272241517499332e-05,
|
| 417 |
+
"loss": 2.1435,
|
| 418 |
+
"step": 24500
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 6.67913438418381,
|
| 422 |
+
"grad_norm": 3.208509922027588,
|
| 423 |
+
"learning_rate": 1.6604328079080954e-05,
|
| 424 |
+
"loss": 2.1357,
|
| 425 |
+
"step": 25000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 6.812717071867486,
|
| 429 |
+
"grad_norm": 3.2755982875823975,
|
| 430 |
+
"learning_rate": 1.593641464066257e-05,
|
| 431 |
+
"loss": 2.1371,
|
| 432 |
+
"step": 25500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 6.946299759551162,
|
| 436 |
+
"grad_norm": 3.220367431640625,
|
| 437 |
+
"learning_rate": 1.526850120224419e-05,
|
| 438 |
+
"loss": 2.1313,
|
| 439 |
+
"step": 26000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 7.0,
|
| 443 |
+
"eval_loss": 2.18220853805542,
|
| 444 |
+
"eval_rouge1": 28.5073,
|
| 445 |
+
"eval_rouge2": 12.6157,
|
| 446 |
+
"eval_rougeL": 25.1244,
|
| 447 |
+
"eval_runtime": 795.4817,
|
| 448 |
+
"eval_samples_per_second": 5.895,
|
| 449 |
+
"eval_steps_per_second": 0.59,
|
| 450 |
+
"step": 26201
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 7.079882447234838,
|
| 454 |
+
"grad_norm": 3.261324167251587,
|
| 455 |
+
"learning_rate": 1.4600587763825809e-05,
|
| 456 |
+
"loss": 2.0706,
|
| 457 |
+
"step": 26500
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 7.213465134918515,
|
| 461 |
+
"grad_norm": 3.2409138679504395,
|
| 462 |
+
"learning_rate": 1.3932674325407427e-05,
|
| 463 |
+
"loss": 2.0684,
|
| 464 |
+
"step": 27000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 7.347047822602191,
|
| 468 |
+
"grad_norm": 3.02018666267395,
|
| 469 |
+
"learning_rate": 1.3264760886989048e-05,
|
| 470 |
+
"loss": 2.0621,
|
| 471 |
+
"step": 27500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 7.480630510285867,
|
| 475 |
+
"grad_norm": 3.306445598602295,
|
| 476 |
+
"learning_rate": 1.2596847448570668e-05,
|
| 477 |
+
"loss": 2.0637,
|
| 478 |
+
"step": 28000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 7.614213197969543,
|
| 482 |
+
"grad_norm": 3.3543508052825928,
|
| 483 |
+
"learning_rate": 1.1928934010152284e-05,
|
| 484 |
+
"loss": 2.0804,
|
| 485 |
+
"step": 28500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 7.747795885653219,
|
| 489 |
+
"grad_norm": 3.1137688159942627,
|
| 490 |
+
"learning_rate": 1.1261020571733903e-05,
|
| 491 |
+
"loss": 2.0845,
|
| 492 |
+
"step": 29000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 7.881378573336896,
|
| 496 |
+
"grad_norm": 3.7980918884277344,
|
| 497 |
+
"learning_rate": 1.0593107133315523e-05,
|
| 498 |
+
"loss": 2.0796,
|
| 499 |
+
"step": 29500
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 8.0,
|
| 503 |
+
"eval_loss": 2.18402361869812,
|
| 504 |
+
"eval_rouge1": 28.743,
|
| 505 |
+
"eval_rouge2": 12.8907,
|
| 506 |
+
"eval_rougeL": 25.4018,
|
| 507 |
+
"eval_runtime": 821.2111,
|
| 508 |
+
"eval_samples_per_second": 5.71,
|
| 509 |
+
"eval_steps_per_second": 0.571,
|
| 510 |
+
"step": 29944
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 8.014961261020572,
|
| 514 |
+
"grad_norm": 3.3595690727233887,
|
| 515 |
+
"learning_rate": 9.925193694897141e-06,
|
| 516 |
+
"loss": 2.1025,
|
| 517 |
+
"step": 30000
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 8.148543948704248,
|
| 521 |
+
"grad_norm": 3.24507737159729,
|
| 522 |
+
"learning_rate": 9.25728025647876e-06,
|
| 523 |
+
"loss": 2.0176,
|
| 524 |
+
"step": 30500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 8.282126636387924,
|
| 528 |
+
"grad_norm": 3.5450592041015625,
|
| 529 |
+
"learning_rate": 8.58936681806038e-06,
|
| 530 |
+
"loss": 2.0326,
|
| 531 |
+
"step": 31000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 8.4157093240716,
|
| 535 |
+
"grad_norm": 3.5833873748779297,
|
| 536 |
+
"learning_rate": 7.921453379642e-06,
|
| 537 |
+
"loss": 2.0427,
|
| 538 |
+
"step": 31500
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 8.549292011755277,
|
| 542 |
+
"grad_norm": 4.691043376922607,
|
| 543 |
+
"learning_rate": 7.2535399412236176e-06,
|
| 544 |
+
"loss": 2.0352,
|
| 545 |
+
"step": 32000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 10.232997481108312,
|
| 549 |
+
"grad_norm": 3.2953643798828125,
|
| 550 |
+
"learning_rate": 7.362510495382033e-06,
|
| 551 |
+
"loss": 1.8856,
|
| 552 |
+
"step": 32500
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 10.3904282115869,
|
| 556 |
+
"grad_norm": 3.4494450092315674,
|
| 557 |
+
"learning_rate": 6.70654911838791e-06,
|
| 558 |
+
"loss": 1.8634,
|
| 559 |
+
"step": 33000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 10.547858942065492,
|
| 563 |
+
"grad_norm": 2.9981698989868164,
|
| 564 |
+
"learning_rate": 6.050587741393787e-06,
|
| 565 |
+
"loss": 1.8751,
|
| 566 |
+
"step": 33500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 10.705289672544081,
|
| 570 |
+
"grad_norm": 3.224597454071045,
|
| 571 |
+
"learning_rate": 5.394626364399664e-06,
|
| 572 |
+
"loss": 1.8864,
|
| 573 |
+
"step": 34000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 10.86272040302267,
|
| 577 |
+
"grad_norm": 3.196687698364258,
|
| 578 |
+
"learning_rate": 4.738664987405542e-06,
|
| 579 |
+
"loss": 1.8653,
|
| 580 |
+
"step": 34500
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 11.0,
|
| 584 |
+
"eval_loss": 2.1366946697235107,
|
| 585 |
+
"eval_rouge1": 29.2809,
|
| 586 |
+
"eval_rouge2": 13.0769,
|
| 587 |
+
"eval_rougeL": 25.8435,
|
| 588 |
+
"eval_runtime": 656.6282,
|
| 589 |
+
"eval_samples_per_second": 6.468,
|
| 590 |
+
"eval_steps_per_second": 0.647,
|
| 591 |
+
"step": 34936
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 11.02015113350126,
|
| 595 |
+
"grad_norm": 3.253657341003418,
|
| 596 |
+
"learning_rate": 4.082703610411419e-06,
|
| 597 |
+
"loss": 1.8604,
|
| 598 |
+
"step": 35000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 11.17758186397985,
|
| 602 |
+
"grad_norm": 3.6433730125427246,
|
| 603 |
+
"learning_rate": 3.4267422334172966e-06,
|
| 604 |
+
"loss": 1.838,
|
| 605 |
+
"step": 35500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 11.335012594458439,
|
| 609 |
+
"grad_norm": 3.041062355041504,
|
| 610 |
+
"learning_rate": 2.770780856423174e-06,
|
| 611 |
+
"loss": 1.8356,
|
| 612 |
+
"step": 36000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 11.492443324937028,
|
| 616 |
+
"grad_norm": 2.9957120418548584,
|
| 617 |
+
"learning_rate": 2.114819479429051e-06,
|
| 618 |
+
"loss": 1.8549,
|
| 619 |
+
"step": 36500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 11.649874055415617,
|
| 623 |
+
"grad_norm": 3.1265900135040283,
|
| 624 |
+
"learning_rate": 1.4588581024349287e-06,
|
| 625 |
+
"loss": 1.8613,
|
| 626 |
+
"step": 37000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 11.807304785894207,
|
| 630 |
+
"grad_norm": 3.275404691696167,
|
| 631 |
+
"learning_rate": 8.028967254408061e-07,
|
| 632 |
+
"loss": 1.8527,
|
| 633 |
+
"step": 37500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 11.964735516372796,
|
| 637 |
+
"grad_norm": 3.625509023666382,
|
| 638 |
+
"learning_rate": 1.4693534844668346e-07,
|
| 639 |
+
"loss": 1.8359,
|
| 640 |
+
"step": 38000
|
| 641 |
+
}
|
| 642 |
+
],
|
| 643 |
+
"logging_steps": 500,
|
| 644 |
+
"max_steps": 38112,
|
| 645 |
+
"num_input_tokens_seen": 0,
|
| 646 |
+
"num_train_epochs": 12,
|
| 647 |
+
"save_steps": 500,
|
| 648 |
+
"stateful_callbacks": {
|
| 649 |
+
"TrainerControl": {
|
| 650 |
+
"args": {
|
| 651 |
+
"should_epoch_stop": false,
|
| 652 |
+
"should_evaluate": false,
|
| 653 |
+
"should_log": false,
|
| 654 |
+
"should_save": true,
|
| 655 |
+
"should_training_stop": false
|
| 656 |
+
},
|
| 657 |
+
"attributes": {}
|
| 658 |
+
}
|
| 659 |
+
},
|
| 660 |
+
"total_flos": 2.1748548304233677e+17,
|
| 661 |
+
"train_batch_size": 10,
|
| 662 |
+
"trial_name": null,
|
| 663 |
+
"trial_params": null
|
| 664 |
+
}
|
checkpoint-38000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39a626215cf2268e29ddd066c3dee70f82c637ce0a3bf5d79085c817c01b654c
|
| 3 |
+
size 7032
|