Upload folder using huggingface_hub
Browse files- config.json +25 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +71 -0
- trainer_state.json +1843 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 512,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 1024,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 8,
|
| 18 |
+
"num_hidden_layers": 4,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"transformers_version": "4.57.6",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:357b8e65d7d9b036190922ac184ca746274f953d347baeec8b626ff48e5486d8
|
| 3 |
+
size 133031496
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9ccd87af85a2958de00c3090ab85d6d5cdc1aefdeeaa8077a3a7270ac83f5af
|
| 3 |
+
size 266109515
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:344d546b52136b7b336b91a4db8709ac3ff3ac644fbaf7ae1ee9e638ac334fee
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9f025cb099f6a1c3c828b0e0495822252290f6b856f0800fe2bb140dc812b20
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[BOS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[EOS]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[PAD]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30001": {
|
| 44 |
+
"content": "[EOS]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"30002": {
|
| 52 |
+
"content": "[BOS]",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"bos_token": "[BOS]",
|
| 61 |
+
"clean_up_tokenization_spaces": false,
|
| 62 |
+
"cls_token": "[CLS]",
|
| 63 |
+
"eos_token": "[EOS]",
|
| 64 |
+
"extra_special_tokens": {},
|
| 65 |
+
"mask_token": "[MASK]",
|
| 66 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 67 |
+
"pad_token": "[PAD]",
|
| 68 |
+
"sep_token": "[SEP]",
|
| 69 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 70 |
+
"unk_token": "[UNK]"
|
| 71 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1843 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 6000,
|
| 3 |
+
"best_metric": 0.13940538465976715,
|
| 4 |
+
"best_model_checkpoint": "/data/alamparan/mattext_ckpt/results_2m/2026-02-06/03-23-25/pretrain/checkpoints/robocrys_rep_test-pretrain/checkpoint-6000",
|
| 5 |
+
"epoch": 0.5780903747952597,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 6000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004817419789960497,
|
| 14 |
+
"grad_norm": 1.3140820264816284,
|
| 15 |
+
"learning_rate": 0.00019998111571442338,
|
| 16 |
+
"loss": 5.9543,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.004817419789960497,
|
| 21 |
+
"eval_loss": 4.040468692779541,
|
| 22 |
+
"eval_runtime": 85.9858,
|
| 23 |
+
"eval_samples_per_second": 221.013,
|
| 24 |
+
"eval_steps_per_second": 4.605,
|
| 25 |
+
"step": 50
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.009634839579920994,
|
| 29 |
+
"grad_norm": 0.8951072692871094,
|
| 30 |
+
"learning_rate": 0.0001999618460352635,
|
| 31 |
+
"loss": 3.7958,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.009634839579920994,
|
| 36 |
+
"eval_loss": 3.572112798690796,
|
| 37 |
+
"eval_runtime": 87.5351,
|
| 38 |
+
"eval_samples_per_second": 217.102,
|
| 39 |
+
"eval_steps_per_second": 4.524,
|
| 40 |
+
"step": 100
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.014452259369881492,
|
| 44 |
+
"grad_norm": 1.1552037000656128,
|
| 45 |
+
"learning_rate": 0.00019994257635610368,
|
| 46 |
+
"loss": 3.4955,
|
| 47 |
+
"step": 150
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.014452259369881492,
|
| 51 |
+
"eval_loss": 3.365239381790161,
|
| 52 |
+
"eval_runtime": 86.7746,
|
| 53 |
+
"eval_samples_per_second": 219.004,
|
| 54 |
+
"eval_steps_per_second": 4.564,
|
| 55 |
+
"step": 150
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.019269679159841988,
|
| 59 |
+
"grad_norm": 1.1728101968765259,
|
| 60 |
+
"learning_rate": 0.00019992330667694384,
|
| 61 |
+
"loss": 3.3176,
|
| 62 |
+
"step": 200
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.019269679159841988,
|
| 66 |
+
"eval_loss": 3.2046337127685547,
|
| 67 |
+
"eval_runtime": 86.8432,
|
| 68 |
+
"eval_samples_per_second": 218.831,
|
| 69 |
+
"eval_steps_per_second": 4.56,
|
| 70 |
+
"step": 200
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.024087098949802484,
|
| 74 |
+
"grad_norm": 0.8054835200309753,
|
| 75 |
+
"learning_rate": 0.000199904036997784,
|
| 76 |
+
"loss": 3.1815,
|
| 77 |
+
"step": 250
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.024087098949802484,
|
| 81 |
+
"eval_loss": 3.065305709838867,
|
| 82 |
+
"eval_runtime": 85.5782,
|
| 83 |
+
"eval_samples_per_second": 222.066,
|
| 84 |
+
"eval_steps_per_second": 4.627,
|
| 85 |
+
"step": 250
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.028904518739762984,
|
| 89 |
+
"grad_norm": 1.2382686138153076,
|
| 90 |
+
"learning_rate": 0.00019988476731862417,
|
| 91 |
+
"loss": 3.0462,
|
| 92 |
+
"step": 300
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.028904518739762984,
|
| 96 |
+
"eval_loss": 2.937901020050049,
|
| 97 |
+
"eval_runtime": 86.036,
|
| 98 |
+
"eval_samples_per_second": 220.884,
|
| 99 |
+
"eval_steps_per_second": 4.603,
|
| 100 |
+
"step": 300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.03372193852972348,
|
| 104 |
+
"grad_norm": 1.245282530784607,
|
| 105 |
+
"learning_rate": 0.00019986549763946433,
|
| 106 |
+
"loss": 2.9173,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.03372193852972348,
|
| 111 |
+
"eval_loss": 2.7557334899902344,
|
| 112 |
+
"eval_runtime": 88.8138,
|
| 113 |
+
"eval_samples_per_second": 213.976,
|
| 114 |
+
"eval_steps_per_second": 4.459,
|
| 115 |
+
"step": 350
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.038539358319683976,
|
| 119 |
+
"grad_norm": 1.2060555219650269,
|
| 120 |
+
"learning_rate": 0.00019984622796030447,
|
| 121 |
+
"loss": 2.7187,
|
| 122 |
+
"step": 400
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.038539358319683976,
|
| 126 |
+
"eval_loss": 2.480039119720459,
|
| 127 |
+
"eval_runtime": 88.2775,
|
| 128 |
+
"eval_samples_per_second": 215.276,
|
| 129 |
+
"eval_steps_per_second": 4.486,
|
| 130 |
+
"step": 400
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.04335677810964447,
|
| 134 |
+
"grad_norm": 1.9137617349624634,
|
| 135 |
+
"learning_rate": 0.00019982695828114463,
|
| 136 |
+
"loss": 2.3768,
|
| 137 |
+
"step": 450
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.04335677810964447,
|
| 141 |
+
"eval_loss": 1.9087786674499512,
|
| 142 |
+
"eval_runtime": 88.071,
|
| 143 |
+
"eval_samples_per_second": 215.78,
|
| 144 |
+
"eval_steps_per_second": 4.496,
|
| 145 |
+
"step": 450
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.04817419789960497,
|
| 149 |
+
"grad_norm": 1.4742215871810913,
|
| 150 |
+
"learning_rate": 0.00019980768860198477,
|
| 151 |
+
"loss": 1.7234,
|
| 152 |
+
"step": 500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.04817419789960497,
|
| 156 |
+
"eval_loss": 1.158734679222107,
|
| 157 |
+
"eval_runtime": 88.5849,
|
| 158 |
+
"eval_samples_per_second": 214.529,
|
| 159 |
+
"eval_steps_per_second": 4.47,
|
| 160 |
+
"step": 500
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.05299161768956547,
|
| 164 |
+
"grad_norm": 1.0141704082489014,
|
| 165 |
+
"learning_rate": 0.00019978841892282493,
|
| 166 |
+
"loss": 1.1418,
|
| 167 |
+
"step": 550
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.05299161768956547,
|
| 171 |
+
"eval_loss": 0.8516036868095398,
|
| 172 |
+
"eval_runtime": 87.5002,
|
| 173 |
+
"eval_samples_per_second": 217.188,
|
| 174 |
+
"eval_steps_per_second": 4.526,
|
| 175 |
+
"step": 550
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.05780903747952597,
|
| 179 |
+
"grad_norm": 0.8414612412452698,
|
| 180 |
+
"learning_rate": 0.0001997691492436651,
|
| 181 |
+
"loss": 0.881,
|
| 182 |
+
"step": 600
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.05780903747952597,
|
| 186 |
+
"eval_loss": 0.7400951385498047,
|
| 187 |
+
"eval_runtime": 88.6088,
|
| 188 |
+
"eval_samples_per_second": 214.471,
|
| 189 |
+
"eval_steps_per_second": 4.469,
|
| 190 |
+
"step": 600
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.06262645726948646,
|
| 194 |
+
"grad_norm": 0.694267213344574,
|
| 195 |
+
"learning_rate": 0.00019974987956450526,
|
| 196 |
+
"loss": 0.813,
|
| 197 |
+
"step": 650
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.06262645726948646,
|
| 201 |
+
"eval_loss": 0.6765585541725159,
|
| 202 |
+
"eval_runtime": 90.0063,
|
| 203 |
+
"eval_samples_per_second": 211.141,
|
| 204 |
+
"eval_steps_per_second": 4.4,
|
| 205 |
+
"step": 650
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.06744387705944696,
|
| 209 |
+
"grad_norm": 0.6236635446548462,
|
| 210 |
+
"learning_rate": 0.00019973060988534542,
|
| 211 |
+
"loss": 0.7301,
|
| 212 |
+
"step": 700
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.06744387705944696,
|
| 216 |
+
"eval_loss": 0.6367717981338501,
|
| 217 |
+
"eval_runtime": 90.1272,
|
| 218 |
+
"eval_samples_per_second": 210.857,
|
| 219 |
+
"eval_steps_per_second": 4.394,
|
| 220 |
+
"step": 700
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.07226129684940746,
|
| 224 |
+
"grad_norm": 0.663361132144928,
|
| 225 |
+
"learning_rate": 0.00019971134020618558,
|
| 226 |
+
"loss": 0.6936,
|
| 227 |
+
"step": 750
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.07226129684940746,
|
| 231 |
+
"eval_loss": 0.603342592716217,
|
| 232 |
+
"eval_runtime": 88.3855,
|
| 233 |
+
"eval_samples_per_second": 215.013,
|
| 234 |
+
"eval_steps_per_second": 4.48,
|
| 235 |
+
"step": 750
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.07707871663936795,
|
| 239 |
+
"grad_norm": 0.584972083568573,
|
| 240 |
+
"learning_rate": 0.00019969207052702575,
|
| 241 |
+
"loss": 0.6492,
|
| 242 |
+
"step": 800
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.07707871663936795,
|
| 246 |
+
"eval_loss": 0.5670896768569946,
|
| 247 |
+
"eval_runtime": 88.8592,
|
| 248 |
+
"eval_samples_per_second": 213.867,
|
| 249 |
+
"eval_steps_per_second": 4.456,
|
| 250 |
+
"step": 800
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.08189613642932846,
|
| 254 |
+
"grad_norm": 0.6252435445785522,
|
| 255 |
+
"learning_rate": 0.00019967280084786588,
|
| 256 |
+
"loss": 0.6554,
|
| 257 |
+
"step": 850
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.08189613642932846,
|
| 261 |
+
"eval_loss": 0.5390716791152954,
|
| 262 |
+
"eval_runtime": 88.7469,
|
| 263 |
+
"eval_samples_per_second": 214.137,
|
| 264 |
+
"eval_steps_per_second": 4.462,
|
| 265 |
+
"step": 850
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.08671355621928895,
|
| 269 |
+
"grad_norm": 0.5381043553352356,
|
| 270 |
+
"learning_rate": 0.00019965353116870605,
|
| 271 |
+
"loss": 0.5847,
|
| 272 |
+
"step": 900
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.08671355621928895,
|
| 276 |
+
"eval_loss": 0.5227247476577759,
|
| 277 |
+
"eval_runtime": 87.1283,
|
| 278 |
+
"eval_samples_per_second": 218.115,
|
| 279 |
+
"eval_steps_per_second": 4.545,
|
| 280 |
+
"step": 900
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.09153097600924945,
|
| 284 |
+
"grad_norm": 0.4695926308631897,
|
| 285 |
+
"learning_rate": 0.0001996342614895462,
|
| 286 |
+
"loss": 0.5787,
|
| 287 |
+
"step": 950
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.09153097600924945,
|
| 291 |
+
"eval_loss": 0.5046476721763611,
|
| 292 |
+
"eval_runtime": 88.0204,
|
| 293 |
+
"eval_samples_per_second": 215.905,
|
| 294 |
+
"eval_steps_per_second": 4.499,
|
| 295 |
+
"step": 950
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.09634839579920994,
|
| 299 |
+
"grad_norm": 0.49100059270858765,
|
| 300 |
+
"learning_rate": 0.00019961499181038637,
|
| 301 |
+
"loss": 0.5795,
|
| 302 |
+
"step": 1000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.09634839579920994,
|
| 306 |
+
"eval_loss": 0.4904717803001404,
|
| 307 |
+
"eval_runtime": 87.871,
|
| 308 |
+
"eval_samples_per_second": 216.272,
|
| 309 |
+
"eval_steps_per_second": 4.507,
|
| 310 |
+
"step": 1000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.10116581558917044,
|
| 314 |
+
"grad_norm": 0.48738670349121094,
|
| 315 |
+
"learning_rate": 0.00019959572213122654,
|
| 316 |
+
"loss": 0.5372,
|
| 317 |
+
"step": 1050
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.10116581558917044,
|
| 321 |
+
"eval_loss": 0.4725087285041809,
|
| 322 |
+
"eval_runtime": 87.3641,
|
| 323 |
+
"eval_samples_per_second": 217.526,
|
| 324 |
+
"eval_steps_per_second": 4.533,
|
| 325 |
+
"step": 1050
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.10598323537913094,
|
| 329 |
+
"grad_norm": 0.5932963490486145,
|
| 330 |
+
"learning_rate": 0.0001995764524520667,
|
| 331 |
+
"loss": 0.5074,
|
| 332 |
+
"step": 1100
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.10598323537913094,
|
| 336 |
+
"eval_loss": 0.4346506893634796,
|
| 337 |
+
"eval_runtime": 87.5476,
|
| 338 |
+
"eval_samples_per_second": 217.07,
|
| 339 |
+
"eval_steps_per_second": 4.523,
|
| 340 |
+
"step": 1100
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.11080065516909143,
|
| 344 |
+
"grad_norm": 0.5904502272605896,
|
| 345 |
+
"learning_rate": 0.00019955718277290684,
|
| 346 |
+
"loss": 0.4764,
|
| 347 |
+
"step": 1150
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.11080065516909143,
|
| 351 |
+
"eval_loss": 0.4015448987483978,
|
| 352 |
+
"eval_runtime": 88.5379,
|
| 353 |
+
"eval_samples_per_second": 214.642,
|
| 354 |
+
"eval_steps_per_second": 4.473,
|
| 355 |
+
"step": 1150
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.11561807495905194,
|
| 359 |
+
"grad_norm": 0.46411070227622986,
|
| 360 |
+
"learning_rate": 0.000199537913093747,
|
| 361 |
+
"loss": 0.4346,
|
| 362 |
+
"step": 1200
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.11561807495905194,
|
| 366 |
+
"eval_loss": 0.38101693987846375,
|
| 367 |
+
"eval_runtime": 87.5237,
|
| 368 |
+
"eval_samples_per_second": 217.13,
|
| 369 |
+
"eval_steps_per_second": 4.524,
|
| 370 |
+
"step": 1200
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.12043549474901243,
|
| 374 |
+
"grad_norm": 0.49205589294433594,
|
| 375 |
+
"learning_rate": 0.00019951864341458714,
|
| 376 |
+
"loss": 0.4151,
|
| 377 |
+
"step": 1250
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.12043549474901243,
|
| 381 |
+
"eval_loss": 0.3670279085636139,
|
| 382 |
+
"eval_runtime": 87.1762,
|
| 383 |
+
"eval_samples_per_second": 217.995,
|
| 384 |
+
"eval_steps_per_second": 4.543,
|
| 385 |
+
"step": 1250
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.12525291453897291,
|
| 389 |
+
"grad_norm": 0.5221843123435974,
|
| 390 |
+
"learning_rate": 0.0001994993737354273,
|
| 391 |
+
"loss": 0.3951,
|
| 392 |
+
"step": 1300
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.12525291453897291,
|
| 396 |
+
"eval_loss": 0.3488354980945587,
|
| 397 |
+
"eval_runtime": 87.8499,
|
| 398 |
+
"eval_samples_per_second": 216.324,
|
| 399 |
+
"eval_steps_per_second": 4.508,
|
| 400 |
+
"step": 1300
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.13007033432893342,
|
| 404 |
+
"grad_norm": 0.5032587647438049,
|
| 405 |
+
"learning_rate": 0.00019948010405626746,
|
| 406 |
+
"loss": 0.3593,
|
| 407 |
+
"step": 1350
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.13007033432893342,
|
| 411 |
+
"eval_loss": 0.33173102140426636,
|
| 412 |
+
"eval_runtime": 86.3749,
|
| 413 |
+
"eval_samples_per_second": 220.018,
|
| 414 |
+
"eval_steps_per_second": 4.585,
|
| 415 |
+
"step": 1350
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.13488775411889392,
|
| 419 |
+
"grad_norm": 0.5051923394203186,
|
| 420 |
+
"learning_rate": 0.00019946083437710763,
|
| 421 |
+
"loss": 0.3526,
|
| 422 |
+
"step": 1400
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.13488775411889392,
|
| 426 |
+
"eval_loss": 0.30538395047187805,
|
| 427 |
+
"eval_runtime": 89.1978,
|
| 428 |
+
"eval_samples_per_second": 213.055,
|
| 429 |
+
"eval_steps_per_second": 4.44,
|
| 430 |
+
"step": 1400
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.13970517390885442,
|
| 434 |
+
"grad_norm": 0.46636977791786194,
|
| 435 |
+
"learning_rate": 0.0001994415646979478,
|
| 436 |
+
"loss": 0.3299,
|
| 437 |
+
"step": 1450
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.13970517390885442,
|
| 441 |
+
"eval_loss": 0.28566229343414307,
|
| 442 |
+
"eval_runtime": 87.6248,
|
| 443 |
+
"eval_samples_per_second": 216.879,
|
| 444 |
+
"eval_steps_per_second": 4.519,
|
| 445 |
+
"step": 1450
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.14452259369881493,
|
| 449 |
+
"grad_norm": 0.4614977240562439,
|
| 450 |
+
"learning_rate": 0.00019942229501878795,
|
| 451 |
+
"loss": 0.2968,
|
| 452 |
+
"step": 1500
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.14452259369881493,
|
| 456 |
+
"eval_loss": 0.2682988941669464,
|
| 457 |
+
"eval_runtime": 88.341,
|
| 458 |
+
"eval_samples_per_second": 215.121,
|
| 459 |
+
"eval_steps_per_second": 4.483,
|
| 460 |
+
"step": 1500
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.1493400134887754,
|
| 464 |
+
"grad_norm": 0.40138185024261475,
|
| 465 |
+
"learning_rate": 0.00019940302533962812,
|
| 466 |
+
"loss": 0.2822,
|
| 467 |
+
"step": 1550
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.1493400134887754,
|
| 471 |
+
"eval_loss": 0.2586437165737152,
|
| 472 |
+
"eval_runtime": 87.7499,
|
| 473 |
+
"eval_samples_per_second": 216.57,
|
| 474 |
+
"eval_steps_per_second": 4.513,
|
| 475 |
+
"step": 1550
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.1541574332787359,
|
| 479 |
+
"grad_norm": 0.4057703912258148,
|
| 480 |
+
"learning_rate": 0.00019938375566046825,
|
| 481 |
+
"loss": 0.271,
|
| 482 |
+
"step": 1600
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.1541574332787359,
|
| 486 |
+
"eval_loss": 0.25495249032974243,
|
| 487 |
+
"eval_runtime": 87.2931,
|
| 488 |
+
"eval_samples_per_second": 217.703,
|
| 489 |
+
"eval_steps_per_second": 4.536,
|
| 490 |
+
"step": 1600
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.1589748530686964,
|
| 494 |
+
"grad_norm": 0.32808950543403625,
|
| 495 |
+
"learning_rate": 0.00019936448598130842,
|
| 496 |
+
"loss": 0.2547,
|
| 497 |
+
"step": 1650
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.1589748530686964,
|
| 501 |
+
"eval_loss": 0.243699312210083,
|
| 502 |
+
"eval_runtime": 86.1589,
|
| 503 |
+
"eval_samples_per_second": 220.569,
|
| 504 |
+
"eval_steps_per_second": 4.596,
|
| 505 |
+
"step": 1650
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.1637922728586569,
|
| 509 |
+
"grad_norm": 0.40255042910575867,
|
| 510 |
+
"learning_rate": 0.00019934521630214858,
|
| 511 |
+
"loss": 0.2549,
|
| 512 |
+
"step": 1700
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.1637922728586569,
|
| 516 |
+
"eval_loss": 0.24029429256916046,
|
| 517 |
+
"eval_runtime": 88.882,
|
| 518 |
+
"eval_samples_per_second": 213.812,
|
| 519 |
+
"eval_steps_per_second": 4.455,
|
| 520 |
+
"step": 1700
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.1686096926486174,
|
| 524 |
+
"grad_norm": 0.4509395956993103,
|
| 525 |
+
"learning_rate": 0.00019932594662298874,
|
| 526 |
+
"loss": 0.2541,
|
| 527 |
+
"step": 1750
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.1686096926486174,
|
| 531 |
+
"eval_loss": 0.23613183200359344,
|
| 532 |
+
"eval_runtime": 87.9005,
|
| 533 |
+
"eval_samples_per_second": 216.199,
|
| 534 |
+
"eval_steps_per_second": 4.505,
|
| 535 |
+
"step": 1750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.1734271124385779,
|
| 539 |
+
"grad_norm": 0.3515077531337738,
|
| 540 |
+
"learning_rate": 0.0001993066769438289,
|
| 541 |
+
"loss": 0.2385,
|
| 542 |
+
"step": 1800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.1734271124385779,
|
| 546 |
+
"eval_loss": 0.2291395217180252,
|
| 547 |
+
"eval_runtime": 87.3005,
|
| 548 |
+
"eval_samples_per_second": 217.685,
|
| 549 |
+
"eval_steps_per_second": 4.536,
|
| 550 |
+
"step": 1800
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.1782445322285384,
|
| 554 |
+
"grad_norm": 0.3758944272994995,
|
| 555 |
+
"learning_rate": 0.00019928740726466907,
|
| 556 |
+
"loss": 0.2406,
|
| 557 |
+
"step": 1850
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.1782445322285384,
|
| 561 |
+
"eval_loss": 0.22721637785434723,
|
| 562 |
+
"eval_runtime": 87.3928,
|
| 563 |
+
"eval_samples_per_second": 217.455,
|
| 564 |
+
"eval_steps_per_second": 4.531,
|
| 565 |
+
"step": 1850
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 0.1830619520184989,
|
| 569 |
+
"grad_norm": 0.33480963110923767,
|
| 570 |
+
"learning_rate": 0.0001992681375855092,
|
| 571 |
+
"loss": 0.2327,
|
| 572 |
+
"step": 1900
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.1830619520184989,
|
| 576 |
+
"eval_loss": 0.22441919147968292,
|
| 577 |
+
"eval_runtime": 87.7197,
|
| 578 |
+
"eval_samples_per_second": 216.645,
|
| 579 |
+
"eval_steps_per_second": 4.514,
|
| 580 |
+
"step": 1900
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.1878793718084594,
|
| 584 |
+
"grad_norm": 0.44033002853393555,
|
| 585 |
+
"learning_rate": 0.00019924886790634937,
|
| 586 |
+
"loss": 0.2327,
|
| 587 |
+
"step": 1950
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.1878793718084594,
|
| 591 |
+
"eval_loss": 0.21973223984241486,
|
| 592 |
+
"eval_runtime": 86.9627,
|
| 593 |
+
"eval_samples_per_second": 218.53,
|
| 594 |
+
"eval_steps_per_second": 4.554,
|
| 595 |
+
"step": 1950
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.19269679159841988,
|
| 599 |
+
"grad_norm": 0.36066603660583496,
|
| 600 |
+
"learning_rate": 0.0001992295982271895,
|
| 601 |
+
"loss": 0.2204,
|
| 602 |
+
"step": 2000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.19269679159841988,
|
| 606 |
+
"eval_loss": 0.21755366027355194,
|
| 607 |
+
"eval_runtime": 85.9832,
|
| 608 |
+
"eval_samples_per_second": 221.02,
|
| 609 |
+
"eval_steps_per_second": 4.606,
|
| 610 |
+
"step": 2000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.19751421138838038,
|
| 614 |
+
"grad_norm": 0.3927019536495209,
|
| 615 |
+
"learning_rate": 0.00019921032854802967,
|
| 616 |
+
"loss": 0.2227,
|
| 617 |
+
"step": 2050
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.19751421138838038,
|
| 621 |
+
"eval_loss": 0.21245667338371277,
|
| 622 |
+
"eval_runtime": 88.7726,
|
| 623 |
+
"eval_samples_per_second": 214.075,
|
| 624 |
+
"eval_steps_per_second": 4.461,
|
| 625 |
+
"step": 2050
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.20233163117834088,
|
| 629 |
+
"grad_norm": 0.33693307638168335,
|
| 630 |
+
"learning_rate": 0.00019919105886886983,
|
| 631 |
+
"loss": 0.2193,
|
| 632 |
+
"step": 2100
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.20233163117834088,
|
| 636 |
+
"eval_loss": 0.21231026947498322,
|
| 637 |
+
"eval_runtime": 86.8589,
|
| 638 |
+
"eval_samples_per_second": 218.792,
|
| 639 |
+
"eval_steps_per_second": 4.559,
|
| 640 |
+
"step": 2100
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.20714905096830138,
|
| 644 |
+
"grad_norm": 0.32883742451667786,
|
| 645 |
+
"learning_rate": 0.00019917178918971,
|
| 646 |
+
"loss": 0.2163,
|
| 647 |
+
"step": 2150
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.20714905096830138,
|
| 651 |
+
"eval_loss": 0.20846392214298248,
|
| 652 |
+
"eval_runtime": 86.2766,
|
| 653 |
+
"eval_samples_per_second": 220.268,
|
| 654 |
+
"eval_steps_per_second": 4.59,
|
| 655 |
+
"step": 2150
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.2119664707582619,
|
| 659 |
+
"grad_norm": 0.3935041129589081,
|
| 660 |
+
"learning_rate": 0.00019915251951055016,
|
| 661 |
+
"loss": 0.216,
|
| 662 |
+
"step": 2200
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.2119664707582619,
|
| 666 |
+
"eval_loss": 0.206617072224617,
|
| 667 |
+
"eval_runtime": 87.55,
|
| 668 |
+
"eval_samples_per_second": 217.065,
|
| 669 |
+
"eval_steps_per_second": 4.523,
|
| 670 |
+
"step": 2200
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.21678389054822236,
|
| 674 |
+
"grad_norm": 0.41742655634880066,
|
| 675 |
+
"learning_rate": 0.00019913324983139032,
|
| 676 |
+
"loss": 0.2046,
|
| 677 |
+
"step": 2250
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.21678389054822236,
|
| 681 |
+
"eval_loss": 0.2045588344335556,
|
| 682 |
+
"eval_runtime": 86.8857,
|
| 683 |
+
"eval_samples_per_second": 218.724,
|
| 684 |
+
"eval_steps_per_second": 4.558,
|
| 685 |
+
"step": 2250
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.22160131033818287,
|
| 689 |
+
"grad_norm": 0.3324650526046753,
|
| 690 |
+
"learning_rate": 0.00019911398015223049,
|
| 691 |
+
"loss": 0.206,
|
| 692 |
+
"step": 2300
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.22160131033818287,
|
| 696 |
+
"eval_loss": 0.2034013867378235,
|
| 697 |
+
"eval_runtime": 88.0292,
|
| 698 |
+
"eval_samples_per_second": 215.883,
|
| 699 |
+
"eval_steps_per_second": 4.499,
|
| 700 |
+
"step": 2300
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.22641873012814337,
|
| 704 |
+
"grad_norm": 0.3411875367164612,
|
| 705 |
+
"learning_rate": 0.00019909471047307062,
|
| 706 |
+
"loss": 0.2021,
|
| 707 |
+
"step": 2350
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.22641873012814337,
|
| 711 |
+
"eval_loss": 0.19746768474578857,
|
| 712 |
+
"eval_runtime": 88.0101,
|
| 713 |
+
"eval_samples_per_second": 215.93,
|
| 714 |
+
"eval_steps_per_second": 4.499,
|
| 715 |
+
"step": 2350
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.23123614991810387,
|
| 719 |
+
"grad_norm": 0.3764231503009796,
|
| 720 |
+
"learning_rate": 0.00019907544079391079,
|
| 721 |
+
"loss": 0.2028,
|
| 722 |
+
"step": 2400
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.23123614991810387,
|
| 726 |
+
"eval_loss": 0.19666016101837158,
|
| 727 |
+
"eval_runtime": 87.9384,
|
| 728 |
+
"eval_samples_per_second": 216.106,
|
| 729 |
+
"eval_steps_per_second": 4.503,
|
| 730 |
+
"step": 2400
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.23605356970806435,
|
| 734 |
+
"grad_norm": 0.377541720867157,
|
| 735 |
+
"learning_rate": 0.00019905617111475095,
|
| 736 |
+
"loss": 0.1995,
|
| 737 |
+
"step": 2450
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.23605356970806435,
|
| 741 |
+
"eval_loss": 0.19164888560771942,
|
| 742 |
+
"eval_runtime": 88.6219,
|
| 743 |
+
"eval_samples_per_second": 214.439,
|
| 744 |
+
"eval_steps_per_second": 4.468,
|
| 745 |
+
"step": 2450
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.24087098949802485,
|
| 749 |
+
"grad_norm": 0.38512399792671204,
|
| 750 |
+
"learning_rate": 0.0001990369014355911,
|
| 751 |
+
"loss": 0.1947,
|
| 752 |
+
"step": 2500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.24087098949802485,
|
| 756 |
+
"eval_loss": 0.1909172534942627,
|
| 757 |
+
"eval_runtime": 86.7278,
|
| 758 |
+
"eval_samples_per_second": 219.122,
|
| 759 |
+
"eval_steps_per_second": 4.566,
|
| 760 |
+
"step": 2500
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.24568840928798535,
|
| 764 |
+
"grad_norm": 0.29089486598968506,
|
| 765 |
+
"learning_rate": 0.00019901763175643128,
|
| 766 |
+
"loss": 0.1934,
|
| 767 |
+
"step": 2550
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.24568840928798535,
|
| 771 |
+
"eval_loss": 0.19215822219848633,
|
| 772 |
+
"eval_runtime": 87.4982,
|
| 773 |
+
"eval_samples_per_second": 217.193,
|
| 774 |
+
"eval_steps_per_second": 4.526,
|
| 775 |
+
"step": 2550
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.25050582907794583,
|
| 779 |
+
"grad_norm": 0.34340256452560425,
|
| 780 |
+
"learning_rate": 0.00019899836207727144,
|
| 781 |
+
"loss": 0.1893,
|
| 782 |
+
"step": 2600
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.25050582907794583,
|
| 786 |
+
"eval_loss": 0.18751804530620575,
|
| 787 |
+
"eval_runtime": 89.0572,
|
| 788 |
+
"eval_samples_per_second": 213.391,
|
| 789 |
+
"eval_steps_per_second": 4.447,
|
| 790 |
+
"step": 2600
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.25532324886790636,
|
| 794 |
+
"grad_norm": 0.31367331743240356,
|
| 795 |
+
"learning_rate": 0.00019897909239811158,
|
| 796 |
+
"loss": 0.1831,
|
| 797 |
+
"step": 2650
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.25532324886790636,
|
| 801 |
+
"eval_loss": 0.1869846135377884,
|
| 802 |
+
"eval_runtime": 88.3755,
|
| 803 |
+
"eval_samples_per_second": 215.037,
|
| 804 |
+
"eval_steps_per_second": 4.481,
|
| 805 |
+
"step": 2650
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.26014066865786684,
|
| 809 |
+
"grad_norm": 0.35607218742370605,
|
| 810 |
+
"learning_rate": 0.00019895982271895174,
|
| 811 |
+
"loss": 0.1906,
|
| 812 |
+
"step": 2700
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.26014066865786684,
|
| 816 |
+
"eval_loss": 0.1840076744556427,
|
| 817 |
+
"eval_runtime": 88.0613,
|
| 818 |
+
"eval_samples_per_second": 215.804,
|
| 819 |
+
"eval_steps_per_second": 4.497,
|
| 820 |
+
"step": 2700
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.26495808844782737,
|
| 824 |
+
"grad_norm": 0.29454657435417175,
|
| 825 |
+
"learning_rate": 0.00019894055303979188,
|
| 826 |
+
"loss": 0.1878,
|
| 827 |
+
"step": 2750
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.26495808844782737,
|
| 831 |
+
"eval_loss": 0.1864839792251587,
|
| 832 |
+
"eval_runtime": 87.4663,
|
| 833 |
+
"eval_samples_per_second": 217.272,
|
| 834 |
+
"eval_steps_per_second": 4.527,
|
| 835 |
+
"step": 2750
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.26977550823778784,
|
| 839 |
+
"grad_norm": 0.33838963508605957,
|
| 840 |
+
"learning_rate": 0.00019892128336063204,
|
| 841 |
+
"loss": 0.1821,
|
| 842 |
+
"step": 2800
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.26977550823778784,
|
| 846 |
+
"eval_loss": 0.1847812533378601,
|
| 847 |
+
"eval_runtime": 88.0891,
|
| 848 |
+
"eval_samples_per_second": 215.736,
|
| 849 |
+
"eval_steps_per_second": 4.495,
|
| 850 |
+
"step": 2800
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.2745929280277483,
|
| 854 |
+
"grad_norm": 0.2440441995859146,
|
| 855 |
+
"learning_rate": 0.0001989020136814722,
|
| 856 |
+
"loss": 0.1783,
|
| 857 |
+
"step": 2850
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.2745929280277483,
|
| 861 |
+
"eval_loss": 0.18052709102630615,
|
| 862 |
+
"eval_runtime": 85.9682,
|
| 863 |
+
"eval_samples_per_second": 221.059,
|
| 864 |
+
"eval_steps_per_second": 4.606,
|
| 865 |
+
"step": 2850
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.27941034781770885,
|
| 869 |
+
"grad_norm": 0.33384960889816284,
|
| 870 |
+
"learning_rate": 0.00019888274400231237,
|
| 871 |
+
"loss": 0.1796,
|
| 872 |
+
"step": 2900
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.27941034781770885,
|
| 876 |
+
"eval_loss": 0.17909078299999237,
|
| 877 |
+
"eval_runtime": 87.5176,
|
| 878 |
+
"eval_samples_per_second": 217.145,
|
| 879 |
+
"eval_steps_per_second": 4.525,
|
| 880 |
+
"step": 2900
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.2842277676076693,
|
| 884 |
+
"grad_norm": 0.29702430963516235,
|
| 885 |
+
"learning_rate": 0.00019886347432315253,
|
| 886 |
+
"loss": 0.1785,
|
| 887 |
+
"step": 2950
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.2842277676076693,
|
| 891 |
+
"eval_loss": 0.17997683584690094,
|
| 892 |
+
"eval_runtime": 87.9757,
|
| 893 |
+
"eval_samples_per_second": 216.014,
|
| 894 |
+
"eval_steps_per_second": 4.501,
|
| 895 |
+
"step": 2950
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 0.28904518739762985,
|
| 899 |
+
"grad_norm": 0.3510948121547699,
|
| 900 |
+
"learning_rate": 0.0001988442046439927,
|
| 901 |
+
"loss": 0.1765,
|
| 902 |
+
"step": 3000
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.28904518739762985,
|
| 906 |
+
"eval_loss": 0.1761734038591385,
|
| 907 |
+
"eval_runtime": 88.1258,
|
| 908 |
+
"eval_samples_per_second": 215.646,
|
| 909 |
+
"eval_steps_per_second": 4.494,
|
| 910 |
+
"step": 3000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.29386260718759033,
|
| 914 |
+
"grad_norm": 0.37029772996902466,
|
| 915 |
+
"learning_rate": 0.00019882493496483286,
|
| 916 |
+
"loss": 0.1737,
|
| 917 |
+
"step": 3050
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.29386260718759033,
|
| 921 |
+
"eval_loss": 0.17449568212032318,
|
| 922 |
+
"eval_runtime": 88.3713,
|
| 923 |
+
"eval_samples_per_second": 215.047,
|
| 924 |
+
"eval_steps_per_second": 4.481,
|
| 925 |
+
"step": 3050
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.2986800269775508,
|
| 929 |
+
"grad_norm": 0.2771267592906952,
|
| 930 |
+
"learning_rate": 0.000198805665285673,
|
| 931 |
+
"loss": 0.1761,
|
| 932 |
+
"step": 3100
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.2986800269775508,
|
| 936 |
+
"eval_loss": 0.1765695959329605,
|
| 937 |
+
"eval_runtime": 87.9476,
|
| 938 |
+
"eval_samples_per_second": 216.083,
|
| 939 |
+
"eval_steps_per_second": 4.503,
|
| 940 |
+
"step": 3100
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.30349744676751134,
|
| 944 |
+
"grad_norm": 0.338558167219162,
|
| 945 |
+
"learning_rate": 0.00019878639560651316,
|
| 946 |
+
"loss": 0.1766,
|
| 947 |
+
"step": 3150
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.30349744676751134,
|
| 951 |
+
"eval_loss": 0.17348217964172363,
|
| 952 |
+
"eval_runtime": 86.4764,
|
| 953 |
+
"eval_samples_per_second": 219.759,
|
| 954 |
+
"eval_steps_per_second": 4.579,
|
| 955 |
+
"step": 3150
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.3083148665574718,
|
| 959 |
+
"grad_norm": 0.36884650588035583,
|
| 960 |
+
"learning_rate": 0.00019876712592735332,
|
| 961 |
+
"loss": 0.1697,
|
| 962 |
+
"step": 3200
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.3083148665574718,
|
| 966 |
+
"eval_loss": 0.1715058535337448,
|
| 967 |
+
"eval_runtime": 88.0269,
|
| 968 |
+
"eval_samples_per_second": 215.888,
|
| 969 |
+
"eval_steps_per_second": 4.499,
|
| 970 |
+
"step": 3200
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.31313228634743234,
|
| 974 |
+
"grad_norm": 0.2907465994358063,
|
| 975 |
+
"learning_rate": 0.00019874785624819348,
|
| 976 |
+
"loss": 0.1747,
|
| 977 |
+
"step": 3250
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.31313228634743234,
|
| 981 |
+
"eval_loss": 0.17374737560749054,
|
| 982 |
+
"eval_runtime": 87.3911,
|
| 983 |
+
"eval_samples_per_second": 217.459,
|
| 984 |
+
"eval_steps_per_second": 4.531,
|
| 985 |
+
"step": 3250
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.3179497061373928,
|
| 989 |
+
"grad_norm": 0.3033406734466553,
|
| 990 |
+
"learning_rate": 0.00019872858656903365,
|
| 991 |
+
"loss": 0.1706,
|
| 992 |
+
"step": 3300
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.3179497061373928,
|
| 996 |
+
"eval_loss": 0.17150533199310303,
|
| 997 |
+
"eval_runtime": 88.1112,
|
| 998 |
+
"eval_samples_per_second": 215.682,
|
| 999 |
+
"eval_steps_per_second": 4.494,
|
| 1000 |
+
"step": 3300
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 0.3227671259273533,
|
| 1004 |
+
"grad_norm": 0.3115890324115753,
|
| 1005 |
+
"learning_rate": 0.0001987093168898738,
|
| 1006 |
+
"loss": 0.1665,
|
| 1007 |
+
"step": 3350
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 0.3227671259273533,
|
| 1011 |
+
"eval_loss": 0.16980254650115967,
|
| 1012 |
+
"eval_runtime": 87.4444,
|
| 1013 |
+
"eval_samples_per_second": 217.327,
|
| 1014 |
+
"eval_steps_per_second": 4.529,
|
| 1015 |
+
"step": 3350
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 0.3275845457173138,
|
| 1019 |
+
"grad_norm": 0.25616976618766785,
|
| 1020 |
+
"learning_rate": 0.00019869004721071395,
|
| 1021 |
+
"loss": 0.1655,
|
| 1022 |
+
"step": 3400
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 0.3275845457173138,
|
| 1026 |
+
"eval_loss": 0.17015036940574646,
|
| 1027 |
+
"eval_runtime": 88.3575,
|
| 1028 |
+
"eval_samples_per_second": 215.081,
|
| 1029 |
+
"eval_steps_per_second": 4.482,
|
| 1030 |
+
"step": 3400
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 0.3324019655072743,
|
| 1034 |
+
"grad_norm": 0.23346827924251556,
|
| 1035 |
+
"learning_rate": 0.0001986707775315541,
|
| 1036 |
+
"loss": 0.1673,
|
| 1037 |
+
"step": 3450
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.3324019655072743,
|
| 1041 |
+
"eval_loss": 0.1687326282262802,
|
| 1042 |
+
"eval_runtime": 90.3569,
|
| 1043 |
+
"eval_samples_per_second": 210.321,
|
| 1044 |
+
"eval_steps_per_second": 4.383,
|
| 1045 |
+
"step": 3450
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.3372193852972348,
|
| 1049 |
+
"grad_norm": 0.3347044289112091,
|
| 1050 |
+
"learning_rate": 0.00019865150785239425,
|
| 1051 |
+
"loss": 0.163,
|
| 1052 |
+
"step": 3500
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.3372193852972348,
|
| 1056 |
+
"eval_loss": 0.17024628818035126,
|
| 1057 |
+
"eval_runtime": 88.9183,
|
| 1058 |
+
"eval_samples_per_second": 213.724,
|
| 1059 |
+
"eval_steps_per_second": 4.454,
|
| 1060 |
+
"step": 3500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.3420368050871953,
|
| 1064 |
+
"grad_norm": 0.34929919242858887,
|
| 1065 |
+
"learning_rate": 0.0001986322381732344,
|
| 1066 |
+
"loss": 0.1624,
|
| 1067 |
+
"step": 3550
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.3420368050871953,
|
| 1071 |
+
"eval_loss": 0.16716831922531128,
|
| 1072 |
+
"eval_runtime": 89.8228,
|
| 1073 |
+
"eval_samples_per_second": 211.572,
|
| 1074 |
+
"eval_steps_per_second": 4.409,
|
| 1075 |
+
"step": 3550
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.3468542248771558,
|
| 1079 |
+
"grad_norm": 0.2455097734928131,
|
| 1080 |
+
"learning_rate": 0.00019861296849407457,
|
| 1081 |
+
"loss": 0.1633,
|
| 1082 |
+
"step": 3600
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.3468542248771558,
|
| 1086 |
+
"eval_loss": 0.16651391983032227,
|
| 1087 |
+
"eval_runtime": 86.8189,
|
| 1088 |
+
"eval_samples_per_second": 218.892,
|
| 1089 |
+
"eval_steps_per_second": 4.561,
|
| 1090 |
+
"step": 3600
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.3516716446671163,
|
| 1094 |
+
"grad_norm": 0.28978198766708374,
|
| 1095 |
+
"learning_rate": 0.00019859369881491474,
|
| 1096 |
+
"loss": 0.1646,
|
| 1097 |
+
"step": 3650
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.3516716446671163,
|
| 1101 |
+
"eval_loss": 0.16727794706821442,
|
| 1102 |
+
"eval_runtime": 87.7801,
|
| 1103 |
+
"eval_samples_per_second": 216.496,
|
| 1104 |
+
"eval_steps_per_second": 4.511,
|
| 1105 |
+
"step": 3650
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.3564890644570768,
|
| 1109 |
+
"grad_norm": 0.292510062456131,
|
| 1110 |
+
"learning_rate": 0.0001985744291357549,
|
| 1111 |
+
"loss": 0.1625,
|
| 1112 |
+
"step": 3700
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.3564890644570768,
|
| 1116 |
+
"eval_loss": 0.16462790966033936,
|
| 1117 |
+
"eval_runtime": 87.2466,
|
| 1118 |
+
"eval_samples_per_second": 217.819,
|
| 1119 |
+
"eval_steps_per_second": 4.539,
|
| 1120 |
+
"step": 3700
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 0.36130648424703726,
|
| 1124 |
+
"grad_norm": 0.26186755299568176,
|
| 1125 |
+
"learning_rate": 0.00019855515945659506,
|
| 1126 |
+
"loss": 0.1583,
|
| 1127 |
+
"step": 3750
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.36130648424703726,
|
| 1131 |
+
"eval_loss": 0.16536560654640198,
|
| 1132 |
+
"eval_runtime": 85.6294,
|
| 1133 |
+
"eval_samples_per_second": 221.933,
|
| 1134 |
+
"eval_steps_per_second": 4.625,
|
| 1135 |
+
"step": 3750
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 0.3661239040369978,
|
| 1139 |
+
"grad_norm": 0.25864389538764954,
|
| 1140 |
+
"learning_rate": 0.00019853588977743523,
|
| 1141 |
+
"loss": 0.163,
|
| 1142 |
+
"step": 3800
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 0.3661239040369978,
|
| 1146 |
+
"eval_loss": 0.16156961023807526,
|
| 1147 |
+
"eval_runtime": 88.8605,
|
| 1148 |
+
"eval_samples_per_second": 213.863,
|
| 1149 |
+
"eval_steps_per_second": 4.456,
|
| 1150 |
+
"step": 3800
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.37094132382695827,
|
| 1154 |
+
"grad_norm": 0.298779159784317,
|
| 1155 |
+
"learning_rate": 0.00019851662009827536,
|
| 1156 |
+
"loss": 0.1582,
|
| 1157 |
+
"step": 3850
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.37094132382695827,
|
| 1161 |
+
"eval_loss": 0.16503678262233734,
|
| 1162 |
+
"eval_runtime": 90.0855,
|
| 1163 |
+
"eval_samples_per_second": 210.955,
|
| 1164 |
+
"eval_steps_per_second": 4.396,
|
| 1165 |
+
"step": 3850
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.3757587436169188,
|
| 1169 |
+
"grad_norm": 0.30580171942710876,
|
| 1170 |
+
"learning_rate": 0.00019849735041911553,
|
| 1171 |
+
"loss": 0.1568,
|
| 1172 |
+
"step": 3900
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.3757587436169188,
|
| 1176 |
+
"eval_loss": 0.16093286871910095,
|
| 1177 |
+
"eval_runtime": 87.9051,
|
| 1178 |
+
"eval_samples_per_second": 216.188,
|
| 1179 |
+
"eval_steps_per_second": 4.505,
|
| 1180 |
+
"step": 3900
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.3805761634068793,
|
| 1184 |
+
"grad_norm": 0.26903071999549866,
|
| 1185 |
+
"learning_rate": 0.0001984780807399557,
|
| 1186 |
+
"loss": 0.156,
|
| 1187 |
+
"step": 3950
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.3805761634068793,
|
| 1191 |
+
"eval_loss": 0.16180996596813202,
|
| 1192 |
+
"eval_runtime": 87.2728,
|
| 1193 |
+
"eval_samples_per_second": 217.754,
|
| 1194 |
+
"eval_steps_per_second": 4.537,
|
| 1195 |
+
"step": 3950
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.38539358319683975,
|
| 1199 |
+
"grad_norm": 0.25209519267082214,
|
| 1200 |
+
"learning_rate": 0.00019845881106079585,
|
| 1201 |
+
"loss": 0.1559,
|
| 1202 |
+
"step": 4000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.38539358319683975,
|
| 1206 |
+
"eval_loss": 0.15961618721485138,
|
| 1207 |
+
"eval_runtime": 89.2611,
|
| 1208 |
+
"eval_samples_per_second": 212.903,
|
| 1209 |
+
"eval_steps_per_second": 4.436,
|
| 1210 |
+
"step": 4000
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.3902110029868003,
|
| 1214 |
+
"grad_norm": 0.29754438996315,
|
| 1215 |
+
"learning_rate": 0.00019843954138163602,
|
| 1216 |
+
"loss": 0.1546,
|
| 1217 |
+
"step": 4050
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.3902110029868003,
|
| 1221 |
+
"eval_loss": 0.16072513163089752,
|
| 1222 |
+
"eval_runtime": 87.9158,
|
| 1223 |
+
"eval_samples_per_second": 216.161,
|
| 1224 |
+
"eval_steps_per_second": 4.504,
|
| 1225 |
+
"step": 4050
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 0.39502842277676076,
|
| 1229 |
+
"grad_norm": 0.259056031703949,
|
| 1230 |
+
"learning_rate": 0.00019842027170247618,
|
| 1231 |
+
"loss": 0.1576,
|
| 1232 |
+
"step": 4100
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.39502842277676076,
|
| 1236 |
+
"eval_loss": 0.16210326552391052,
|
| 1237 |
+
"eval_runtime": 87.5661,
|
| 1238 |
+
"eval_samples_per_second": 217.025,
|
| 1239 |
+
"eval_steps_per_second": 4.522,
|
| 1240 |
+
"step": 4100
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"epoch": 0.3998458425667213,
|
| 1244 |
+
"grad_norm": 0.2900582253932953,
|
| 1245 |
+
"learning_rate": 0.00019840100202331634,
|
| 1246 |
+
"loss": 0.1557,
|
| 1247 |
+
"step": 4150
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 0.3998458425667213,
|
| 1251 |
+
"eval_loss": 0.16127543151378632,
|
| 1252 |
+
"eval_runtime": 87.2874,
|
| 1253 |
+
"eval_samples_per_second": 217.718,
|
| 1254 |
+
"eval_steps_per_second": 4.537,
|
| 1255 |
+
"step": 4150
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.40466326235668176,
|
| 1259 |
+
"grad_norm": 0.3155025243759155,
|
| 1260 |
+
"learning_rate": 0.00019838173234415648,
|
| 1261 |
+
"loss": 0.151,
|
| 1262 |
+
"step": 4200
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.40466326235668176,
|
| 1266 |
+
"eval_loss": 0.15659989416599274,
|
| 1267 |
+
"eval_runtime": 87.5007,
|
| 1268 |
+
"eval_samples_per_second": 217.187,
|
| 1269 |
+
"eval_steps_per_second": 4.526,
|
| 1270 |
+
"step": 4200
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.40948068214664224,
|
| 1274 |
+
"grad_norm": 0.20887872576713562,
|
| 1275 |
+
"learning_rate": 0.00019836246266499664,
|
| 1276 |
+
"loss": 0.149,
|
| 1277 |
+
"step": 4250
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.40948068214664224,
|
| 1281 |
+
"eval_loss": 0.1579655408859253,
|
| 1282 |
+
"eval_runtime": 88.1039,
|
| 1283 |
+
"eval_samples_per_second": 215.7,
|
| 1284 |
+
"eval_steps_per_second": 4.495,
|
| 1285 |
+
"step": 4250
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 0.41429810193660277,
|
| 1289 |
+
"grad_norm": 0.2782476544380188,
|
| 1290 |
+
"learning_rate": 0.00019834319298583678,
|
| 1291 |
+
"loss": 0.1519,
|
| 1292 |
+
"step": 4300
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 0.41429810193660277,
|
| 1296 |
+
"eval_loss": 0.15905822813510895,
|
| 1297 |
+
"eval_runtime": 89.4392,
|
| 1298 |
+
"eval_samples_per_second": 212.479,
|
| 1299 |
+
"eval_steps_per_second": 4.428,
|
| 1300 |
+
"step": 4300
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.41911552172656324,
|
| 1304 |
+
"grad_norm": 0.2640698254108429,
|
| 1305 |
+
"learning_rate": 0.00019832392330667694,
|
| 1306 |
+
"loss": 0.1499,
|
| 1307 |
+
"step": 4350
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.41911552172656324,
|
| 1311 |
+
"eval_loss": 0.15701065957546234,
|
| 1312 |
+
"eval_runtime": 88.5724,
|
| 1313 |
+
"eval_samples_per_second": 214.559,
|
| 1314 |
+
"eval_steps_per_second": 4.471,
|
| 1315 |
+
"step": 4350
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.4239329415165238,
|
| 1319 |
+
"grad_norm": 0.2606890797615051,
|
| 1320 |
+
"learning_rate": 0.0001983046536275171,
|
| 1321 |
+
"loss": 0.1509,
|
| 1322 |
+
"step": 4400
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.4239329415165238,
|
| 1326 |
+
"eval_loss": 0.1540563404560089,
|
| 1327 |
+
"eval_runtime": 87.9838,
|
| 1328 |
+
"eval_samples_per_second": 215.994,
|
| 1329 |
+
"eval_steps_per_second": 4.501,
|
| 1330 |
+
"step": 4400
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.42875036130648425,
|
| 1334 |
+
"grad_norm": 0.32414618134498596,
|
| 1335 |
+
"learning_rate": 0.00019828538394835727,
|
| 1336 |
+
"loss": 0.1476,
|
| 1337 |
+
"step": 4450
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 0.42875036130648425,
|
| 1341 |
+
"eval_loss": 0.15688583254814148,
|
| 1342 |
+
"eval_runtime": 85.8129,
|
| 1343 |
+
"eval_samples_per_second": 221.459,
|
| 1344 |
+
"eval_steps_per_second": 4.615,
|
| 1345 |
+
"step": 4450
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 0.4335677810964447,
|
| 1349 |
+
"grad_norm": 0.31708353757858276,
|
| 1350 |
+
"learning_rate": 0.00019826611426919743,
|
| 1351 |
+
"loss": 0.1477,
|
| 1352 |
+
"step": 4500
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 0.4335677810964447,
|
| 1356 |
+
"eval_loss": 0.15801727771759033,
|
| 1357 |
+
"eval_runtime": 89.5976,
|
| 1358 |
+
"eval_samples_per_second": 212.104,
|
| 1359 |
+
"eval_steps_per_second": 4.42,
|
| 1360 |
+
"step": 4500
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.43838520088640526,
|
| 1364 |
+
"grad_norm": 0.23212596774101257,
|
| 1365 |
+
"learning_rate": 0.0001982468445900376,
|
| 1366 |
+
"loss": 0.146,
|
| 1367 |
+
"step": 4550
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.43838520088640526,
|
| 1371 |
+
"eval_loss": 0.15200358629226685,
|
| 1372 |
+
"eval_runtime": 87.3248,
|
| 1373 |
+
"eval_samples_per_second": 217.624,
|
| 1374 |
+
"eval_steps_per_second": 4.535,
|
| 1375 |
+
"step": 4550
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.44320262067636573,
|
| 1379 |
+
"grad_norm": 0.2829053997993469,
|
| 1380 |
+
"learning_rate": 0.00019822757491087773,
|
| 1381 |
+
"loss": 0.1465,
|
| 1382 |
+
"step": 4600
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.44320262067636573,
|
| 1386 |
+
"eval_loss": 0.1542133092880249,
|
| 1387 |
+
"eval_runtime": 85.3408,
|
| 1388 |
+
"eval_samples_per_second": 222.684,
|
| 1389 |
+
"eval_steps_per_second": 4.64,
|
| 1390 |
+
"step": 4600
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 0.4480200404663262,
|
| 1394 |
+
"grad_norm": 0.26959696412086487,
|
| 1395 |
+
"learning_rate": 0.0001982083052317179,
|
| 1396 |
+
"loss": 0.1494,
|
| 1397 |
+
"step": 4650
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 0.4480200404663262,
|
| 1401 |
+
"eval_loss": 0.15412269532680511,
|
| 1402 |
+
"eval_runtime": 87.9426,
|
| 1403 |
+
"eval_samples_per_second": 216.095,
|
| 1404 |
+
"eval_steps_per_second": 4.503,
|
| 1405 |
+
"step": 4650
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.45283746025628674,
|
| 1409 |
+
"grad_norm": 0.2577558755874634,
|
| 1410 |
+
"learning_rate": 0.00019818903555255806,
|
| 1411 |
+
"loss": 0.1465,
|
| 1412 |
+
"step": 4700
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.45283746025628674,
|
| 1416 |
+
"eval_loss": 0.15427736937999725,
|
| 1417 |
+
"eval_runtime": 88.297,
|
| 1418 |
+
"eval_samples_per_second": 215.228,
|
| 1419 |
+
"eval_steps_per_second": 4.485,
|
| 1420 |
+
"step": 4700
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.4576548800462472,
|
| 1424 |
+
"grad_norm": 0.23728205263614655,
|
| 1425 |
+
"learning_rate": 0.00019816976587339822,
|
| 1426 |
+
"loss": 0.1425,
|
| 1427 |
+
"step": 4750
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.4576548800462472,
|
| 1431 |
+
"eval_loss": 0.15123674273490906,
|
| 1432 |
+
"eval_runtime": 87.7725,
|
| 1433 |
+
"eval_samples_per_second": 216.514,
|
| 1434 |
+
"eval_steps_per_second": 4.512,
|
| 1435 |
+
"step": 4750
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.46247229983620775,
|
| 1439 |
+
"grad_norm": 0.2485925406217575,
|
| 1440 |
+
"learning_rate": 0.00019815049619423839,
|
| 1441 |
+
"loss": 0.1422,
|
| 1442 |
+
"step": 4800
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.46247229983620775,
|
| 1446 |
+
"eval_loss": 0.15153329074382782,
|
| 1447 |
+
"eval_runtime": 87.8581,
|
| 1448 |
+
"eval_samples_per_second": 216.303,
|
| 1449 |
+
"eval_steps_per_second": 4.507,
|
| 1450 |
+
"step": 4800
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 0.4672897196261682,
|
| 1454 |
+
"grad_norm": 0.22593127191066742,
|
| 1455 |
+
"learning_rate": 0.00019813122651507855,
|
| 1456 |
+
"loss": 0.1452,
|
| 1457 |
+
"step": 4850
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 0.4672897196261682,
|
| 1461 |
+
"eval_loss": 0.15019385516643524,
|
| 1462 |
+
"eval_runtime": 88.2356,
|
| 1463 |
+
"eval_samples_per_second": 215.378,
|
| 1464 |
+
"eval_steps_per_second": 4.488,
|
| 1465 |
+
"step": 4850
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.4721071394161287,
|
| 1469 |
+
"grad_norm": 0.2340419441461563,
|
| 1470 |
+
"learning_rate": 0.0001981119568359187,
|
| 1471 |
+
"loss": 0.1409,
|
| 1472 |
+
"step": 4900
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.4721071394161287,
|
| 1476 |
+
"eval_loss": 0.14823836088180542,
|
| 1477 |
+
"eval_runtime": 87.0907,
|
| 1478 |
+
"eval_samples_per_second": 218.209,
|
| 1479 |
+
"eval_steps_per_second": 4.547,
|
| 1480 |
+
"step": 4900
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.4769245592060892,
|
| 1484 |
+
"grad_norm": 0.24335741996765137,
|
| 1485 |
+
"learning_rate": 0.00019809268715675885,
|
| 1486 |
+
"loss": 0.1442,
|
| 1487 |
+
"step": 4950
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.4769245592060892,
|
| 1491 |
+
"eval_loss": 0.14839066565036774,
|
| 1492 |
+
"eval_runtime": 88.1982,
|
| 1493 |
+
"eval_samples_per_second": 215.469,
|
| 1494 |
+
"eval_steps_per_second": 4.49,
|
| 1495 |
+
"step": 4950
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.4817419789960497,
|
| 1499 |
+
"grad_norm": 0.2178025096654892,
|
| 1500 |
+
"learning_rate": 0.000198073417477599,
|
| 1501 |
+
"loss": 0.1397,
|
| 1502 |
+
"step": 5000
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 0.4817419789960497,
|
| 1506 |
+
"eval_loss": 0.14846083521842957,
|
| 1507 |
+
"eval_runtime": 88.7021,
|
| 1508 |
+
"eval_samples_per_second": 214.245,
|
| 1509 |
+
"eval_steps_per_second": 4.464,
|
| 1510 |
+
"step": 5000
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 0.48655939878601023,
|
| 1514 |
+
"grad_norm": 0.2502117156982422,
|
| 1515 |
+
"learning_rate": 0.00019805414779843915,
|
| 1516 |
+
"loss": 0.1412,
|
| 1517 |
+
"step": 5050
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.48655939878601023,
|
| 1521 |
+
"eval_loss": 0.14794325828552246,
|
| 1522 |
+
"eval_runtime": 87.2101,
|
| 1523 |
+
"eval_samples_per_second": 217.911,
|
| 1524 |
+
"eval_steps_per_second": 4.541,
|
| 1525 |
+
"step": 5050
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 0.4913768185759707,
|
| 1529 |
+
"grad_norm": 0.26042014360427856,
|
| 1530 |
+
"learning_rate": 0.0001980348781192793,
|
| 1531 |
+
"loss": 0.1407,
|
| 1532 |
+
"step": 5100
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 0.4913768185759707,
|
| 1536 |
+
"eval_loss": 0.14844238758087158,
|
| 1537 |
+
"eval_runtime": 87.5921,
|
| 1538 |
+
"eval_samples_per_second": 216.96,
|
| 1539 |
+
"eval_steps_per_second": 4.521,
|
| 1540 |
+
"step": 5100
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.4961942383659312,
|
| 1544 |
+
"grad_norm": 0.27736595273017883,
|
| 1545 |
+
"learning_rate": 0.00019801560844011948,
|
| 1546 |
+
"loss": 0.1392,
|
| 1547 |
+
"step": 5150
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.4961942383659312,
|
| 1551 |
+
"eval_loss": 0.1466793715953827,
|
| 1552 |
+
"eval_runtime": 87.8863,
|
| 1553 |
+
"eval_samples_per_second": 216.234,
|
| 1554 |
+
"eval_steps_per_second": 4.506,
|
| 1555 |
+
"step": 5150
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.5010116581558917,
|
| 1559 |
+
"grad_norm": 0.26440733671188354,
|
| 1560 |
+
"learning_rate": 0.00019799633876095964,
|
| 1561 |
+
"loss": 0.1362,
|
| 1562 |
+
"step": 5200
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 0.5010116581558917,
|
| 1566 |
+
"eval_loss": 0.1452549546957016,
|
| 1567 |
+
"eval_runtime": 87.8213,
|
| 1568 |
+
"eval_samples_per_second": 216.394,
|
| 1569 |
+
"eval_steps_per_second": 4.509,
|
| 1570 |
+
"step": 5200
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.5058290779458522,
|
| 1574 |
+
"grad_norm": 0.2524762749671936,
|
| 1575 |
+
"learning_rate": 0.0001979770690817998,
|
| 1576 |
+
"loss": 0.1411,
|
| 1577 |
+
"step": 5250
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.5058290779458522,
|
| 1581 |
+
"eval_loss": 0.14888718724250793,
|
| 1582 |
+
"eval_runtime": 87.8648,
|
| 1583 |
+
"eval_samples_per_second": 216.287,
|
| 1584 |
+
"eval_steps_per_second": 4.507,
|
| 1585 |
+
"step": 5250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.5106464977358127,
|
| 1589 |
+
"grad_norm": 0.2830604612827301,
|
| 1590 |
+
"learning_rate": 0.00019795779940263997,
|
| 1591 |
+
"loss": 0.1373,
|
| 1592 |
+
"step": 5300
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.5106464977358127,
|
| 1596 |
+
"eval_loss": 0.14802096784114838,
|
| 1597 |
+
"eval_runtime": 86.7846,
|
| 1598 |
+
"eval_samples_per_second": 218.979,
|
| 1599 |
+
"eval_steps_per_second": 4.563,
|
| 1600 |
+
"step": 5300
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.5154639175257731,
|
| 1604 |
+
"grad_norm": 0.23933689296245575,
|
| 1605 |
+
"learning_rate": 0.0001979385297234801,
|
| 1606 |
+
"loss": 0.1356,
|
| 1607 |
+
"step": 5350
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.5154639175257731,
|
| 1611 |
+
"eval_loss": 0.14858801662921906,
|
| 1612 |
+
"eval_runtime": 86.8659,
|
| 1613 |
+
"eval_samples_per_second": 218.774,
|
| 1614 |
+
"eval_steps_per_second": 4.559,
|
| 1615 |
+
"step": 5350
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 0.5202813373157337,
|
| 1619 |
+
"grad_norm": 0.23482471704483032,
|
| 1620 |
+
"learning_rate": 0.00019791926004432027,
|
| 1621 |
+
"loss": 0.1375,
|
| 1622 |
+
"step": 5400
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 0.5202813373157337,
|
| 1626 |
+
"eval_loss": 0.14439742267131805,
|
| 1627 |
+
"eval_runtime": 86.5083,
|
| 1628 |
+
"eval_samples_per_second": 219.678,
|
| 1629 |
+
"eval_steps_per_second": 4.578,
|
| 1630 |
+
"step": 5400
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 0.5250987571056942,
|
| 1634 |
+
"grad_norm": 0.2511419653892517,
|
| 1635 |
+
"learning_rate": 0.00019789999036516043,
|
| 1636 |
+
"loss": 0.1338,
|
| 1637 |
+
"step": 5450
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 0.5250987571056942,
|
| 1641 |
+
"eval_loss": 0.14546434581279755,
|
| 1642 |
+
"eval_runtime": 88.2612,
|
| 1643 |
+
"eval_samples_per_second": 215.316,
|
| 1644 |
+
"eval_steps_per_second": 4.487,
|
| 1645 |
+
"step": 5450
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.5299161768956547,
|
| 1649 |
+
"grad_norm": 0.2835318148136139,
|
| 1650 |
+
"learning_rate": 0.0001978807206860006,
|
| 1651 |
+
"loss": 0.1373,
|
| 1652 |
+
"step": 5500
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.5299161768956547,
|
| 1656 |
+
"eval_loss": 0.14437447488307953,
|
| 1657 |
+
"eval_runtime": 87.9924,
|
| 1658 |
+
"eval_samples_per_second": 215.973,
|
| 1659 |
+
"eval_steps_per_second": 4.5,
|
| 1660 |
+
"step": 5500
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 0.5347335966856152,
|
| 1664 |
+
"grad_norm": 0.2739470899105072,
|
| 1665 |
+
"learning_rate": 0.00019786145100684076,
|
| 1666 |
+
"loss": 0.1377,
|
| 1667 |
+
"step": 5550
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 0.5347335966856152,
|
| 1671 |
+
"eval_loss": 0.14675094187259674,
|
| 1672 |
+
"eval_runtime": 88.4052,
|
| 1673 |
+
"eval_samples_per_second": 214.965,
|
| 1674 |
+
"eval_steps_per_second": 4.479,
|
| 1675 |
+
"step": 5550
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.5395510164755757,
|
| 1679 |
+
"grad_norm": 0.23613734543323517,
|
| 1680 |
+
"learning_rate": 0.00019784218132768092,
|
| 1681 |
+
"loss": 0.1375,
|
| 1682 |
+
"step": 5600
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.5395510164755757,
|
| 1686 |
+
"eval_loss": 0.14566753804683685,
|
| 1687 |
+
"eval_runtime": 87.4914,
|
| 1688 |
+
"eval_samples_per_second": 217.21,
|
| 1689 |
+
"eval_steps_per_second": 4.526,
|
| 1690 |
+
"step": 5600
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.5443684362655362,
|
| 1694 |
+
"grad_norm": 0.2323722243309021,
|
| 1695 |
+
"learning_rate": 0.00019782291164852108,
|
| 1696 |
+
"loss": 0.1321,
|
| 1697 |
+
"step": 5650
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.5443684362655362,
|
| 1701 |
+
"eval_loss": 0.1452152580022812,
|
| 1702 |
+
"eval_runtime": 89.1135,
|
| 1703 |
+
"eval_samples_per_second": 213.256,
|
| 1704 |
+
"eval_steps_per_second": 4.444,
|
| 1705 |
+
"step": 5650
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.5491858560554966,
|
| 1709 |
+
"grad_norm": 0.29475587606430054,
|
| 1710 |
+
"learning_rate": 0.00019780364196936122,
|
| 1711 |
+
"loss": 0.1335,
|
| 1712 |
+
"step": 5700
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 0.5491858560554966,
|
| 1716 |
+
"eval_loss": 0.142301544547081,
|
| 1717 |
+
"eval_runtime": 85.457,
|
| 1718 |
+
"eval_samples_per_second": 222.381,
|
| 1719 |
+
"eval_steps_per_second": 4.634,
|
| 1720 |
+
"step": 5700
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 0.5540032758454572,
|
| 1724 |
+
"grad_norm": 0.29040685296058655,
|
| 1725 |
+
"learning_rate": 0.00019778437229020138,
|
| 1726 |
+
"loss": 0.1339,
|
| 1727 |
+
"step": 5750
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 0.5540032758454572,
|
| 1731 |
+
"eval_loss": 0.14422039687633514,
|
| 1732 |
+
"eval_runtime": 88.9367,
|
| 1733 |
+
"eval_samples_per_second": 213.68,
|
| 1734 |
+
"eval_steps_per_second": 4.453,
|
| 1735 |
+
"step": 5750
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.5588206956354177,
|
| 1739 |
+
"grad_norm": 0.28566643595695496,
|
| 1740 |
+
"learning_rate": 0.00019776510261104152,
|
| 1741 |
+
"loss": 0.1334,
|
| 1742 |
+
"step": 5800
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.5588206956354177,
|
| 1746 |
+
"eval_loss": 0.14271041750907898,
|
| 1747 |
+
"eval_runtime": 87.7795,
|
| 1748 |
+
"eval_samples_per_second": 216.497,
|
| 1749 |
+
"eval_steps_per_second": 4.511,
|
| 1750 |
+
"step": 5800
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 0.5636381154253781,
|
| 1754 |
+
"grad_norm": 0.2813100218772888,
|
| 1755 |
+
"learning_rate": 0.00019774583293188168,
|
| 1756 |
+
"loss": 0.1347,
|
| 1757 |
+
"step": 5850
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 0.5636381154253781,
|
| 1761 |
+
"eval_loss": 0.14340683817863464,
|
| 1762 |
+
"eval_runtime": 87.6902,
|
| 1763 |
+
"eval_samples_per_second": 216.717,
|
| 1764 |
+
"eval_steps_per_second": 4.516,
|
| 1765 |
+
"step": 5850
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 0.5684555352153386,
|
| 1769 |
+
"grad_norm": 0.2560277581214905,
|
| 1770 |
+
"learning_rate": 0.00019772656325272185,
|
| 1771 |
+
"loss": 0.1335,
|
| 1772 |
+
"step": 5900
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 0.5684555352153386,
|
| 1776 |
+
"eval_loss": 0.1437900960445404,
|
| 1777 |
+
"eval_runtime": 88.7352,
|
| 1778 |
+
"eval_samples_per_second": 214.165,
|
| 1779 |
+
"eval_steps_per_second": 4.463,
|
| 1780 |
+
"step": 5900
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.5732729550052992,
|
| 1784 |
+
"grad_norm": 0.2642715275287628,
|
| 1785 |
+
"learning_rate": 0.000197707293573562,
|
| 1786 |
+
"loss": 0.1313,
|
| 1787 |
+
"step": 5950
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.5732729550052992,
|
| 1791 |
+
"eval_loss": 0.14153434336185455,
|
| 1792 |
+
"eval_runtime": 89.9067,
|
| 1793 |
+
"eval_samples_per_second": 211.375,
|
| 1794 |
+
"eval_steps_per_second": 4.405,
|
| 1795 |
+
"step": 5950
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.5780903747952597,
|
| 1799 |
+
"grad_norm": 0.2073492407798767,
|
| 1800 |
+
"learning_rate": 0.00019768802389440217,
|
| 1801 |
+
"loss": 0.1323,
|
| 1802 |
+
"step": 6000
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.5780903747952597,
|
| 1806 |
+
"eval_loss": 0.13940538465976715,
|
| 1807 |
+
"eval_runtime": 89.7245,
|
| 1808 |
+
"eval_samples_per_second": 211.804,
|
| 1809 |
+
"eval_steps_per_second": 4.414,
|
| 1810 |
+
"step": 6000
|
| 1811 |
+
}
|
| 1812 |
+
],
|
| 1813 |
+
"logging_steps": 50,
|
| 1814 |
+
"max_steps": 518950,
|
| 1815 |
+
"num_input_tokens_seen": 0,
|
| 1816 |
+
"num_train_epochs": 50,
|
| 1817 |
+
"save_steps": 1000,
|
| 1818 |
+
"stateful_callbacks": {
|
| 1819 |
+
"EarlyStoppingCallback": {
|
| 1820 |
+
"args": {
|
| 1821 |
+
"early_stopping_patience": 10,
|
| 1822 |
+
"early_stopping_threshold": 0.001
|
| 1823 |
+
},
|
| 1824 |
+
"attributes": {
|
| 1825 |
+
"early_stopping_patience_counter": 0
|
| 1826 |
+
}
|
| 1827 |
+
},
|
| 1828 |
+
"TrainerControl": {
|
| 1829 |
+
"args": {
|
| 1830 |
+
"should_epoch_stop": false,
|
| 1831 |
+
"should_evaluate": false,
|
| 1832 |
+
"should_log": false,
|
| 1833 |
+
"should_save": true,
|
| 1834 |
+
"should_training_stop": false
|
| 1835 |
+
},
|
| 1836 |
+
"attributes": {}
|
| 1837 |
+
}
|
| 1838 |
+
},
|
| 1839 |
+
"total_flos": 1.21054265081856e+17,
|
| 1840 |
+
"train_batch_size": 192,
|
| 1841 |
+
"trial_name": null,
|
| 1842 |
+
"trial_params": null
|
| 1843 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a527f086366d366847d11f10c57e6cc777a7a700779f165accea7b1f13ea243
|
| 3 |
+
size 15761
|