Initial upload: BERT Hindi pretrained 1 epoch
Browse files- config.json +24 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- trainer_state.json +1318 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 312,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 1200,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"model_type": "bert",
|
| 15 |
+
"num_attention_heads": 12,
|
| 16 |
+
"num_hidden_layers": 4,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"position_embedding_type": "absolute",
|
| 19 |
+
"torch_dtype": "float32",
|
| 20 |
+
"transformers_version": "4.52.4",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 64000
|
| 24 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2dec62f7fac34fb39b664faeda710a164b01ab85510bc13d58463bc23cca488
|
| 3 |
+
size 99448512
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3c492d68655cc385f44691a8908d02658b57224ac70684a329959ac7b312beb
|
| 3 |
+
size 198939642
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50d5b29546e75091c3f7e6c0e063fb2f2b6ba4e2c846ad670e85631b25e5954f
|
| 3 |
+
size 14244
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ba2d9861718463ff7bd6d73f6b23628ebc78b5e0f737da9d01a6bf436bebb71
|
| 3 |
+
size 988
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79bae0715819b1b77abf40ca1f738a8fab27c31b60cfb1939fa909b01bc244d1
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1318 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 15000,
|
| 7 |
+
"global_step": 140625,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0035555555555555557,
|
| 14 |
+
"eval_loss": 10.192023277282715,
|
| 15 |
+
"eval_runtime": 3606.549,
|
| 16 |
+
"eval_samples_per_second": 138.637,
|
| 17 |
+
"eval_steps_per_second": 4.332,
|
| 18 |
+
"step": 500
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.0071111111111111115,
|
| 22 |
+
"grad_norm": 2.387178421020508,
|
| 23 |
+
"learning_rate": 7.103242320819113e-06,
|
| 24 |
+
"loss": 10.1288,
|
| 25 |
+
"step": 1000
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.0071111111111111115,
|
| 29 |
+
"eval_loss": 9.418336868286133,
|
| 30 |
+
"eval_runtime": 3608.5139,
|
| 31 |
+
"eval_samples_per_second": 138.561,
|
| 32 |
+
"eval_steps_per_second": 4.33,
|
| 33 |
+
"step": 1000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.010666666666666666,
|
| 37 |
+
"eval_loss": 8.553510665893555,
|
| 38 |
+
"eval_runtime": 3626.6638,
|
| 39 |
+
"eval_samples_per_second": 137.868,
|
| 40 |
+
"eval_steps_per_second": 4.308,
|
| 41 |
+
"step": 1500
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.014222222222222223,
|
| 45 |
+
"grad_norm": 1.6770904064178467,
|
| 46 |
+
"learning_rate": 1.4213594994311718e-05,
|
| 47 |
+
"loss": 8.5935,
|
| 48 |
+
"step": 2000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.014222222222222223,
|
| 52 |
+
"eval_loss": 7.8756632804870605,
|
| 53 |
+
"eval_runtime": 3629.9225,
|
| 54 |
+
"eval_samples_per_second": 137.744,
|
| 55 |
+
"eval_steps_per_second": 4.304,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.017777777777777778,
|
| 60 |
+
"eval_loss": 7.625248432159424,
|
| 61 |
+
"eval_runtime": 3637.2635,
|
| 62 |
+
"eval_samples_per_second": 137.466,
|
| 63 |
+
"eval_steps_per_second": 4.296,
|
| 64 |
+
"step": 2500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.021333333333333333,
|
| 68 |
+
"grad_norm": 1.6508774757385254,
|
| 69 |
+
"learning_rate": 2.1323947667804326e-05,
|
| 70 |
+
"loss": 7.6525,
|
| 71 |
+
"step": 3000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.021333333333333333,
|
| 75 |
+
"eval_loss": 7.534073829650879,
|
| 76 |
+
"eval_runtime": 3654.9087,
|
| 77 |
+
"eval_samples_per_second": 136.802,
|
| 78 |
+
"eval_steps_per_second": 4.275,
|
| 79 |
+
"step": 3000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.024888888888888887,
|
| 83 |
+
"eval_loss": 7.45560884475708,
|
| 84 |
+
"eval_runtime": 3671.4513,
|
| 85 |
+
"eval_samples_per_second": 136.186,
|
| 86 |
+
"eval_steps_per_second": 4.256,
|
| 87 |
+
"step": 3500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.028444444444444446,
|
| 91 |
+
"grad_norm": 2.0226364135742188,
|
| 92 |
+
"learning_rate": 2.8434300341296933e-05,
|
| 93 |
+
"loss": 7.4767,
|
| 94 |
+
"step": 4000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.028444444444444446,
|
| 98 |
+
"eval_loss": 7.391005992889404,
|
| 99 |
+
"eval_runtime": 3680.5941,
|
| 100 |
+
"eval_samples_per_second": 135.848,
|
| 101 |
+
"eval_steps_per_second": 4.245,
|
| 102 |
+
"step": 4000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.032,
|
| 106 |
+
"eval_loss": 7.328425407409668,
|
| 107 |
+
"eval_runtime": 3685.0206,
|
| 108 |
+
"eval_samples_per_second": 135.684,
|
| 109 |
+
"eval_steps_per_second": 4.24,
|
| 110 |
+
"step": 4500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.035555555555555556,
|
| 114 |
+
"grad_norm": 1.980565071105957,
|
| 115 |
+
"learning_rate": 3.554465301478954e-05,
|
| 116 |
+
"loss": 7.3497,
|
| 117 |
+
"step": 5000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.035555555555555556,
|
| 121 |
+
"eval_loss": 7.287872314453125,
|
| 122 |
+
"eval_runtime": 3698.5108,
|
| 123 |
+
"eval_samples_per_second": 135.19,
|
| 124 |
+
"eval_steps_per_second": 4.225,
|
| 125 |
+
"step": 5000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.03911111111111111,
|
| 129 |
+
"eval_loss": 7.240482807159424,
|
| 130 |
+
"eval_runtime": 3709.8586,
|
| 131 |
+
"eval_samples_per_second": 134.776,
|
| 132 |
+
"eval_steps_per_second": 4.212,
|
| 133 |
+
"step": 5500
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.042666666666666665,
|
| 137 |
+
"grad_norm": 2.800004720687866,
|
| 138 |
+
"learning_rate": 4.265500568828214e-05,
|
| 139 |
+
"loss": 7.2465,
|
| 140 |
+
"step": 6000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.042666666666666665,
|
| 144 |
+
"eval_loss": 7.197748184204102,
|
| 145 |
+
"eval_runtime": 3735.3694,
|
| 146 |
+
"eval_samples_per_second": 133.856,
|
| 147 |
+
"eval_steps_per_second": 4.183,
|
| 148 |
+
"step": 6000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.04622222222222222,
|
| 152 |
+
"eval_loss": 7.154662132263184,
|
| 153 |
+
"eval_runtime": 3742.7005,
|
| 154 |
+
"eval_samples_per_second": 133.593,
|
| 155 |
+
"eval_steps_per_second": 4.175,
|
| 156 |
+
"step": 6500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.049777777777777775,
|
| 160 |
+
"grad_norm": 3.009158134460449,
|
| 161 |
+
"learning_rate": 4.9765358361774746e-05,
|
| 162 |
+
"loss": 7.1859,
|
| 163 |
+
"step": 7000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.049777777777777775,
|
| 167 |
+
"eval_loss": 7.120786190032959,
|
| 168 |
+
"eval_runtime": 3747.8473,
|
| 169 |
+
"eval_samples_per_second": 133.41,
|
| 170 |
+
"eval_steps_per_second": 4.169,
|
| 171 |
+
"step": 7000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.05333333333333334,
|
| 175 |
+
"eval_loss": 7.0815510749816895,
|
| 176 |
+
"eval_runtime": 3748.6541,
|
| 177 |
+
"eval_samples_per_second": 133.381,
|
| 178 |
+
"eval_steps_per_second": 4.168,
|
| 179 |
+
"step": 7500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.05688888888888889,
|
| 183 |
+
"grad_norm": 3.3026907444000244,
|
| 184 |
+
"learning_rate": 4.963807983951255e-05,
|
| 185 |
+
"loss": 7.1209,
|
| 186 |
+
"step": 8000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.05688888888888889,
|
| 190 |
+
"eval_loss": 7.053798675537109,
|
| 191 |
+
"eval_runtime": 3748.7994,
|
| 192 |
+
"eval_samples_per_second": 133.376,
|
| 193 |
+
"eval_steps_per_second": 4.168,
|
| 194 |
+
"step": 8000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.060444444444444446,
|
| 198 |
+
"eval_loss": 7.023181438446045,
|
| 199 |
+
"eval_runtime": 3634.6666,
|
| 200 |
+
"eval_samples_per_second": 137.564,
|
| 201 |
+
"eval_steps_per_second": 4.299,
|
| 202 |
+
"step": 8500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.064,
|
| 206 |
+
"grad_norm": 3.314805030822754,
|
| 207 |
+
"learning_rate": 4.926380873249347e-05,
|
| 208 |
+
"loss": 7.0348,
|
| 209 |
+
"step": 9000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.07111111111111111,
|
| 213 |
+
"grad_norm": 2.875911235809326,
|
| 214 |
+
"learning_rate": 4.888953762547439e-05,
|
| 215 |
+
"loss": 7.0072,
|
| 216 |
+
"step": 10000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.07111111111111111,
|
| 220 |
+
"eval_loss": 6.941441535949707,
|
| 221 |
+
"eval_runtime": 3748.7055,
|
| 222 |
+
"eval_samples_per_second": 133.379,
|
| 223 |
+
"eval_steps_per_second": 4.168,
|
| 224 |
+
"step": 10000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.07822222222222222,
|
| 228 |
+
"grad_norm": 2.914552688598633,
|
| 229 |
+
"learning_rate": 4.851526651845531e-05,
|
| 230 |
+
"loss": 6.947,
|
| 231 |
+
"step": 11000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.08533333333333333,
|
| 235 |
+
"grad_norm": 2.964020252227783,
|
| 236 |
+
"learning_rate": 4.814099541143623e-05,
|
| 237 |
+
"loss": 6.8917,
|
| 238 |
+
"step": 12000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.08533333333333333,
|
| 242 |
+
"eval_loss": 6.830844402313232,
|
| 243 |
+
"eval_runtime": 3577.7662,
|
| 244 |
+
"eval_samples_per_second": 139.752,
|
| 245 |
+
"eval_steps_per_second": 4.367,
|
| 246 |
+
"step": 12000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.09244444444444444,
|
| 250 |
+
"grad_norm": 3.0612735748291016,
|
| 251 |
+
"learning_rate": 4.7766724304417146e-05,
|
| 252 |
+
"loss": 6.8343,
|
| 253 |
+
"step": 13000
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.09955555555555555,
|
| 257 |
+
"grad_norm": 2.7895731925964355,
|
| 258 |
+
"learning_rate": 4.739245319739807e-05,
|
| 259 |
+
"loss": 6.8006,
|
| 260 |
+
"step": 14000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.09955555555555555,
|
| 264 |
+
"eval_loss": 6.7523064613342285,
|
| 265 |
+
"eval_runtime": 3593.4585,
|
| 266 |
+
"eval_samples_per_second": 139.142,
|
| 267 |
+
"eval_steps_per_second": 4.348,
|
| 268 |
+
"step": 14000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.10666666666666667,
|
| 272 |
+
"grad_norm": 4.3099260330200195,
|
| 273 |
+
"learning_rate": 4.7018182090378985e-05,
|
| 274 |
+
"loss": 6.7552,
|
| 275 |
+
"step": 15000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.11377777777777778,
|
| 279 |
+
"grad_norm": 4.26462459564209,
|
| 280 |
+
"learning_rate": 4.664391098335991e-05,
|
| 281 |
+
"loss": 6.716,
|
| 282 |
+
"step": 16000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.11377777777777778,
|
| 286 |
+
"eval_loss": 6.662391185760498,
|
| 287 |
+
"eval_runtime": 3610.0752,
|
| 288 |
+
"eval_samples_per_second": 138.501,
|
| 289 |
+
"eval_steps_per_second": 4.328,
|
| 290 |
+
"step": 16000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.12088888888888889,
|
| 294 |
+
"grad_norm": 4.591431140899658,
|
| 295 |
+
"learning_rate": 4.626963987634083e-05,
|
| 296 |
+
"loss": 6.6886,
|
| 297 |
+
"step": 17000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.128,
|
| 301 |
+
"grad_norm": 3.8068220615386963,
|
| 302 |
+
"learning_rate": 4.589536876932175e-05,
|
| 303 |
+
"loss": 6.6432,
|
| 304 |
+
"step": 18000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.128,
|
| 308 |
+
"eval_loss": 6.585519313812256,
|
| 309 |
+
"eval_runtime": 3618.075,
|
| 310 |
+
"eval_samples_per_second": 138.195,
|
| 311 |
+
"eval_steps_per_second": 4.319,
|
| 312 |
+
"step": 18000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.1351111111111111,
|
| 316 |
+
"grad_norm": 4.0343523025512695,
|
| 317 |
+
"learning_rate": 4.552109766230267e-05,
|
| 318 |
+
"loss": 6.6323,
|
| 319 |
+
"step": 19000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.14222222222222222,
|
| 323 |
+
"grad_norm": 4.53961181640625,
|
| 324 |
+
"learning_rate": 4.5146826555283586e-05,
|
| 325 |
+
"loss": 6.5772,
|
| 326 |
+
"step": 20000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.14222222222222222,
|
| 330 |
+
"eval_loss": 6.517657279968262,
|
| 331 |
+
"eval_runtime": 3623.0508,
|
| 332 |
+
"eval_samples_per_second": 138.005,
|
| 333 |
+
"eval_steps_per_second": 4.313,
|
| 334 |
+
"step": 20000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.14933333333333335,
|
| 338 |
+
"grad_norm": 4.860204219818115,
|
| 339 |
+
"learning_rate": 4.477255544826451e-05,
|
| 340 |
+
"loss": 6.5456,
|
| 341 |
+
"step": 21000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.15644444444444444,
|
| 345 |
+
"grad_norm": 4.892744541168213,
|
| 346 |
+
"learning_rate": 4.4398284341245425e-05,
|
| 347 |
+
"loss": 6.4887,
|
| 348 |
+
"step": 22000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.15644444444444444,
|
| 352 |
+
"eval_loss": 6.45619010925293,
|
| 353 |
+
"eval_runtime": 3632.2999,
|
| 354 |
+
"eval_samples_per_second": 137.654,
|
| 355 |
+
"eval_steps_per_second": 4.302,
|
| 356 |
+
"step": 22000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.16355555555555557,
|
| 360 |
+
"grad_norm": 4.8081135749816895,
|
| 361 |
+
"learning_rate": 4.402401323422635e-05,
|
| 362 |
+
"loss": 6.4871,
|
| 363 |
+
"step": 23000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.17066666666666666,
|
| 367 |
+
"grad_norm": 6.334560871124268,
|
| 368 |
+
"learning_rate": 4.3649742127207264e-05,
|
| 369 |
+
"loss": 6.4517,
|
| 370 |
+
"step": 24000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.17066666666666666,
|
| 374 |
+
"eval_loss": 6.385794639587402,
|
| 375 |
+
"eval_runtime": 3643.4203,
|
| 376 |
+
"eval_samples_per_second": 137.234,
|
| 377 |
+
"eval_steps_per_second": 4.289,
|
| 378 |
+
"step": 24000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.17777777777777778,
|
| 382 |
+
"grad_norm": 6.487077713012695,
|
| 383 |
+
"learning_rate": 4.3275471020188187e-05,
|
| 384 |
+
"loss": 6.4336,
|
| 385 |
+
"step": 25000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.18488888888888888,
|
| 389 |
+
"grad_norm": 6.764550685882568,
|
| 390 |
+
"learning_rate": 4.29011999131691e-05,
|
| 391 |
+
"loss": 6.3861,
|
| 392 |
+
"step": 26000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.18488888888888888,
|
| 396 |
+
"eval_loss": 6.320189476013184,
|
| 397 |
+
"eval_runtime": 3651.5073,
|
| 398 |
+
"eval_samples_per_second": 136.93,
|
| 399 |
+
"eval_steps_per_second": 4.279,
|
| 400 |
+
"step": 26000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 0.192,
|
| 404 |
+
"grad_norm": 6.320560932159424,
|
| 405 |
+
"learning_rate": 4.2526928806150026e-05,
|
| 406 |
+
"loss": 6.3545,
|
| 407 |
+
"step": 27000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.1991111111111111,
|
| 411 |
+
"grad_norm": 7.219266414642334,
|
| 412 |
+
"learning_rate": 4.215265769913094e-05,
|
| 413 |
+
"loss": 6.3368,
|
| 414 |
+
"step": 28000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.1991111111111111,
|
| 418 |
+
"eval_loss": 6.245439052581787,
|
| 419 |
+
"eval_runtime": 3691.7383,
|
| 420 |
+
"eval_samples_per_second": 135.438,
|
| 421 |
+
"eval_steps_per_second": 4.232,
|
| 422 |
+
"step": 28000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.20622222222222222,
|
| 426 |
+
"grad_norm": 7.970364570617676,
|
| 427 |
+
"learning_rate": 4.1778386592111864e-05,
|
| 428 |
+
"loss": 6.2752,
|
| 429 |
+
"step": 29000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.21333333333333335,
|
| 433 |
+
"grad_norm": 4.8507232666015625,
|
| 434 |
+
"learning_rate": 4.140411548509278e-05,
|
| 435 |
+
"loss": 6.2344,
|
| 436 |
+
"step": 30000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.21333333333333335,
|
| 440 |
+
"eval_loss": 6.119101524353027,
|
| 441 |
+
"eval_runtime": 3746.4316,
|
| 442 |
+
"eval_samples_per_second": 133.46,
|
| 443 |
+
"eval_steps_per_second": 4.171,
|
| 444 |
+
"step": 30000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.22044444444444444,
|
| 448 |
+
"grad_norm": 4.850826740264893,
|
| 449 |
+
"learning_rate": 4.10298443780737e-05,
|
| 450 |
+
"loss": 6.1825,
|
| 451 |
+
"step": 31000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.22755555555555557,
|
| 455 |
+
"grad_norm": 6.614843368530273,
|
| 456 |
+
"learning_rate": 4.0655573271054626e-05,
|
| 457 |
+
"loss": 6.1117,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.22755555555555557,
|
| 462 |
+
"eval_loss": 5.977404594421387,
|
| 463 |
+
"eval_runtime": 3748.1526,
|
| 464 |
+
"eval_samples_per_second": 133.399,
|
| 465 |
+
"eval_steps_per_second": 4.169,
|
| 466 |
+
"step": 32000
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.23466666666666666,
|
| 470 |
+
"grad_norm": 7.195309162139893,
|
| 471 |
+
"learning_rate": 4.028130216403554e-05,
|
| 472 |
+
"loss": 6.0633,
|
| 473 |
+
"step": 33000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.24177777777777779,
|
| 477 |
+
"grad_norm": 6.1979522705078125,
|
| 478 |
+
"learning_rate": 3.9907031057016465e-05,
|
| 479 |
+
"loss": 5.9906,
|
| 480 |
+
"step": 34000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.24177777777777779,
|
| 484 |
+
"eval_loss": 5.844593524932861,
|
| 485 |
+
"eval_runtime": 3748.7753,
|
| 486 |
+
"eval_samples_per_second": 133.377,
|
| 487 |
+
"eval_steps_per_second": 4.168,
|
| 488 |
+
"step": 34000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.24888888888888888,
|
| 492 |
+
"grad_norm": 5.907817840576172,
|
| 493 |
+
"learning_rate": 3.953275994999738e-05,
|
| 494 |
+
"loss": 5.9681,
|
| 495 |
+
"step": 35000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.256,
|
| 499 |
+
"grad_norm": 10.167774200439453,
|
| 500 |
+
"learning_rate": 3.9158488842978304e-05,
|
| 501 |
+
"loss": 5.8877,
|
| 502 |
+
"step": 36000
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.26311111111111113,
|
| 506 |
+
"grad_norm": 6.226233005523682,
|
| 507 |
+
"learning_rate": 3.878421773595922e-05,
|
| 508 |
+
"loss": 5.8555,
|
| 509 |
+
"step": 37000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.2702222222222222,
|
| 513 |
+
"grad_norm": 8.957833290100098,
|
| 514 |
+
"learning_rate": 3.840994662894014e-05,
|
| 515 |
+
"loss": 5.7746,
|
| 516 |
+
"step": 38000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.2773333333333333,
|
| 520 |
+
"grad_norm": 5.283188819885254,
|
| 521 |
+
"learning_rate": 3.803567552192106e-05,
|
| 522 |
+
"loss": 5.7368,
|
| 523 |
+
"step": 39000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.28444444444444444,
|
| 527 |
+
"grad_norm": 8.641979217529297,
|
| 528 |
+
"learning_rate": 3.766140441490198e-05,
|
| 529 |
+
"loss": 5.684,
|
| 530 |
+
"step": 40000
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.28444444444444444,
|
| 534 |
+
"eval_loss": 5.490408420562744,
|
| 535 |
+
"eval_runtime": 3560.4593,
|
| 536 |
+
"eval_samples_per_second": 140.431,
|
| 537 |
+
"eval_steps_per_second": 4.388,
|
| 538 |
+
"step": 40000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.29155555555555557,
|
| 542 |
+
"grad_norm": 7.102558135986328,
|
| 543 |
+
"learning_rate": 3.72871333078829e-05,
|
| 544 |
+
"loss": 5.6058,
|
| 545 |
+
"step": 41000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.2986666666666667,
|
| 549 |
+
"grad_norm": 10.386979103088379,
|
| 550 |
+
"learning_rate": 3.691286220086382e-05,
|
| 551 |
+
"loss": 5.5434,
|
| 552 |
+
"step": 42000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.30577777777777776,
|
| 556 |
+
"grad_norm": 8.64822006225586,
|
| 557 |
+
"learning_rate": 3.653859109384474e-05,
|
| 558 |
+
"loss": 5.5001,
|
| 559 |
+
"step": 43000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.3128888888888889,
|
| 563 |
+
"grad_norm": 5.785928249359131,
|
| 564 |
+
"learning_rate": 3.616431998682566e-05,
|
| 565 |
+
"loss": 5.4771,
|
| 566 |
+
"step": 44000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.32,
|
| 570 |
+
"grad_norm": 5.5996294021606445,
|
| 571 |
+
"learning_rate": 3.5790048879806576e-05,
|
| 572 |
+
"loss": 5.4112,
|
| 573 |
+
"step": 45000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.32,
|
| 577 |
+
"eval_loss": 5.232267379760742,
|
| 578 |
+
"eval_runtime": 3637.4962,
|
| 579 |
+
"eval_samples_per_second": 137.457,
|
| 580 |
+
"eval_steps_per_second": 4.296,
|
| 581 |
+
"step": 45000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.32711111111111113,
|
| 585 |
+
"grad_norm": 6.475677967071533,
|
| 586 |
+
"learning_rate": 3.54157777727875e-05,
|
| 587 |
+
"loss": 5.3516,
|
| 588 |
+
"step": 46000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.3342222222222222,
|
| 592 |
+
"grad_norm": 8.867932319641113,
|
| 593 |
+
"learning_rate": 3.504150666576842e-05,
|
| 594 |
+
"loss": 5.3162,
|
| 595 |
+
"step": 47000
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.3413333333333333,
|
| 599 |
+
"grad_norm": 6.978850364685059,
|
| 600 |
+
"learning_rate": 3.466723555874934e-05,
|
| 601 |
+
"loss": 5.2946,
|
| 602 |
+
"step": 48000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.34844444444444445,
|
| 606 |
+
"grad_norm": 8.528263092041016,
|
| 607 |
+
"learning_rate": 3.429296445173026e-05,
|
| 608 |
+
"loss": 5.263,
|
| 609 |
+
"step": 49000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.35555555555555557,
|
| 613 |
+
"grad_norm": 8.980386734008789,
|
| 614 |
+
"learning_rate": 3.3919067615818196e-05,
|
| 615 |
+
"loss": 5.2126,
|
| 616 |
+
"step": 50000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.3626666666666667,
|
| 620 |
+
"grad_norm": 6.648774147033691,
|
| 621 |
+
"learning_rate": 3.354479650879911e-05,
|
| 622 |
+
"loss": 5.1586,
|
| 623 |
+
"step": 51000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.36977777777777776,
|
| 627 |
+
"grad_norm": 7.404205322265625,
|
| 628 |
+
"learning_rate": 3.3170899672887054e-05,
|
| 629 |
+
"loss": 5.1437,
|
| 630 |
+
"step": 52000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.3768888888888889,
|
| 634 |
+
"grad_norm": 8.521736145019531,
|
| 635 |
+
"learning_rate": 3.279662856586798e-05,
|
| 636 |
+
"loss": 5.1017,
|
| 637 |
+
"step": 53000
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.384,
|
| 641 |
+
"grad_norm": 8.535130500793457,
|
| 642 |
+
"learning_rate": 3.242273172995591e-05,
|
| 643 |
+
"loss": 5.0448,
|
| 644 |
+
"step": 54000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.39111111111111113,
|
| 648 |
+
"grad_norm": 8.199433326721191,
|
| 649 |
+
"learning_rate": 3.204846062293683e-05,
|
| 650 |
+
"loss": 5.0525,
|
| 651 |
+
"step": 55000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.3982222222222222,
|
| 655 |
+
"grad_norm": 6.0434651374816895,
|
| 656 |
+
"learning_rate": 3.167456378702477e-05,
|
| 657 |
+
"loss": 5.028,
|
| 658 |
+
"step": 56000
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.4053333333333333,
|
| 662 |
+
"grad_norm": 9.137014389038086,
|
| 663 |
+
"learning_rate": 3.130029268000569e-05,
|
| 664 |
+
"loss": 4.9989,
|
| 665 |
+
"step": 57000
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.41244444444444445,
|
| 669 |
+
"grad_norm": 8.472779273986816,
|
| 670 |
+
"learning_rate": 3.092639584409363e-05,
|
| 671 |
+
"loss": 4.9428,
|
| 672 |
+
"step": 58000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.41955555555555557,
|
| 676 |
+
"grad_norm": 8.970288276672363,
|
| 677 |
+
"learning_rate": 3.055212473707455e-05,
|
| 678 |
+
"loss": 4.9541,
|
| 679 |
+
"step": 59000
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.4266666666666667,
|
| 683 |
+
"grad_norm": 8.8677339553833,
|
| 684 |
+
"learning_rate": 3.017785363005547e-05,
|
| 685 |
+
"loss": 4.9165,
|
| 686 |
+
"step": 60000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.4266666666666667,
|
| 690 |
+
"eval_loss": 4.728287220001221,
|
| 691 |
+
"eval_runtime": 1065.1935,
|
| 692 |
+
"eval_samples_per_second": 469.398,
|
| 693 |
+
"eval_steps_per_second": 14.669,
|
| 694 |
+
"step": 60000
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.43377777777777776,
|
| 698 |
+
"grad_norm": 7.122616767883301,
|
| 699 |
+
"learning_rate": 2.980358252303639e-05,
|
| 700 |
+
"loss": 4.8869,
|
| 701 |
+
"step": 61000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.4408888888888889,
|
| 705 |
+
"grad_norm": 8.567378044128418,
|
| 706 |
+
"learning_rate": 2.9429685687124324e-05,
|
| 707 |
+
"loss": 4.87,
|
| 708 |
+
"step": 62000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.448,
|
| 712 |
+
"grad_norm": 6.809515953063965,
|
| 713 |
+
"learning_rate": 2.9055788851212266e-05,
|
| 714 |
+
"loss": 4.8423,
|
| 715 |
+
"step": 63000
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.45511111111111113,
|
| 719 |
+
"grad_norm": 8.371034622192383,
|
| 720 |
+
"learning_rate": 2.8681517744193186e-05,
|
| 721 |
+
"loss": 4.8137,
|
| 722 |
+
"step": 64000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.4622222222222222,
|
| 726 |
+
"grad_norm": 11.026784896850586,
|
| 727 |
+
"learning_rate": 2.8307246637174105e-05,
|
| 728 |
+
"loss": 4.7887,
|
| 729 |
+
"step": 65000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.4693333333333333,
|
| 733 |
+
"grad_norm": 7.04138708114624,
|
| 734 |
+
"learning_rate": 2.7933349801262044e-05,
|
| 735 |
+
"loss": 4.7642,
|
| 736 |
+
"step": 66000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.47644444444444445,
|
| 740 |
+
"grad_norm": 6.654124736785889,
|
| 741 |
+
"learning_rate": 2.7559078694242964e-05,
|
| 742 |
+
"loss": 4.7682,
|
| 743 |
+
"step": 67000
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.48355555555555557,
|
| 747 |
+
"grad_norm": 9.198745727539062,
|
| 748 |
+
"learning_rate": 2.718480758722388e-05,
|
| 749 |
+
"loss": 4.7505,
|
| 750 |
+
"step": 68000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.49066666666666664,
|
| 754 |
+
"grad_norm": 7.339107036590576,
|
| 755 |
+
"learning_rate": 2.68105364802048e-05,
|
| 756 |
+
"loss": 4.695,
|
| 757 |
+
"step": 69000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.49777777777777776,
|
| 761 |
+
"grad_norm": 7.021571636199951,
|
| 762 |
+
"learning_rate": 2.6436639644292742e-05,
|
| 763 |
+
"loss": 4.6952,
|
| 764 |
+
"step": 70000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.5048888888888889,
|
| 768 |
+
"grad_norm": 6.531971454620361,
|
| 769 |
+
"learning_rate": 2.606236853727366e-05,
|
| 770 |
+
"loss": 4.7041,
|
| 771 |
+
"step": 71000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.512,
|
| 775 |
+
"grad_norm": 8.730067253112793,
|
| 776 |
+
"learning_rate": 2.56884717013616e-05,
|
| 777 |
+
"loss": 4.6792,
|
| 778 |
+
"step": 72000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.5191111111111111,
|
| 782 |
+
"grad_norm": 6.701645374298096,
|
| 783 |
+
"learning_rate": 2.531420059434252e-05,
|
| 784 |
+
"loss": 4.6603,
|
| 785 |
+
"step": 73000
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.5262222222222223,
|
| 789 |
+
"grad_norm": 8.028661727905273,
|
| 790 |
+
"learning_rate": 2.493992948732344e-05,
|
| 791 |
+
"loss": 4.6216,
|
| 792 |
+
"step": 74000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.5333333333333333,
|
| 796 |
+
"grad_norm": 8.593280792236328,
|
| 797 |
+
"learning_rate": 2.456565838030436e-05,
|
| 798 |
+
"loss": 4.5962,
|
| 799 |
+
"step": 75000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.5333333333333333,
|
| 803 |
+
"eval_loss": 4.437507152557373,
|
| 804 |
+
"eval_runtime": 1115.0836,
|
| 805 |
+
"eval_samples_per_second": 448.397,
|
| 806 |
+
"eval_steps_per_second": 14.012,
|
| 807 |
+
"step": 75000
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.5404444444444444,
|
| 811 |
+
"grad_norm": 7.844559192657471,
|
| 812 |
+
"learning_rate": 2.4191761544392298e-05,
|
| 813 |
+
"loss": 4.5922,
|
| 814 |
+
"step": 76000
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.5475555555555556,
|
| 818 |
+
"grad_norm": 8.809325218200684,
|
| 819 |
+
"learning_rate": 2.3817490437373217e-05,
|
| 820 |
+
"loss": 4.5741,
|
| 821 |
+
"step": 77000
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.5546666666666666,
|
| 825 |
+
"grad_norm": 8.746879577636719,
|
| 826 |
+
"learning_rate": 2.3443593601461156e-05,
|
| 827 |
+
"loss": 4.5682,
|
| 828 |
+
"step": 78000
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.5617777777777778,
|
| 832 |
+
"grad_norm": 6.95306921005249,
|
| 833 |
+
"learning_rate": 2.3069322494442076e-05,
|
| 834 |
+
"loss": 4.5368,
|
| 835 |
+
"step": 79000
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.5688888888888889,
|
| 839 |
+
"grad_norm": 6.743412494659424,
|
| 840 |
+
"learning_rate": 2.2695425658530015e-05,
|
| 841 |
+
"loss": 4.533,
|
| 842 |
+
"step": 80000
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.576,
|
| 846 |
+
"grad_norm": 7.390259742736816,
|
| 847 |
+
"learning_rate": 2.2321154551510934e-05,
|
| 848 |
+
"loss": 4.4858,
|
| 849 |
+
"step": 81000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.5831111111111111,
|
| 853 |
+
"grad_norm": 6.666167736053467,
|
| 854 |
+
"learning_rate": 2.1947257715598873e-05,
|
| 855 |
+
"loss": 4.4989,
|
| 856 |
+
"step": 82000
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.5902222222222222,
|
| 860 |
+
"grad_norm": 11.42460823059082,
|
| 861 |
+
"learning_rate": 2.1572986608579793e-05,
|
| 862 |
+
"loss": 4.4954,
|
| 863 |
+
"step": 83000
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.5973333333333334,
|
| 867 |
+
"grad_norm": 8.539606094360352,
|
| 868 |
+
"learning_rate": 2.1198715501560712e-05,
|
| 869 |
+
"loss": 4.4719,
|
| 870 |
+
"step": 84000
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.6044444444444445,
|
| 874 |
+
"grad_norm": 7.553934097290039,
|
| 875 |
+
"learning_rate": 2.082481866564865e-05,
|
| 876 |
+
"loss": 4.4676,
|
| 877 |
+
"step": 85000
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.6115555555555555,
|
| 881 |
+
"grad_norm": 6.772820949554443,
|
| 882 |
+
"learning_rate": 2.045054755862957e-05,
|
| 883 |
+
"loss": 4.4472,
|
| 884 |
+
"step": 86000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.6186666666666667,
|
| 888 |
+
"grad_norm": 7.853897571563721,
|
| 889 |
+
"learning_rate": 2.0076650722717507e-05,
|
| 890 |
+
"loss": 4.4265,
|
| 891 |
+
"step": 87000
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.6257777777777778,
|
| 895 |
+
"grad_norm": 9.26160717010498,
|
| 896 |
+
"learning_rate": 1.9702379615698426e-05,
|
| 897 |
+
"loss": 4.4468,
|
| 898 |
+
"step": 88000
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.6328888888888888,
|
| 902 |
+
"grad_norm": 7.147493362426758,
|
| 903 |
+
"learning_rate": 1.932810850867935e-05,
|
| 904 |
+
"loss": 4.4117,
|
| 905 |
+
"step": 89000
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.64,
|
| 909 |
+
"grad_norm": 7.0213446617126465,
|
| 910 |
+
"learning_rate": 1.8954211672767285e-05,
|
| 911 |
+
"loss": 4.4131,
|
| 912 |
+
"step": 90000
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.64,
|
| 916 |
+
"eval_loss": 4.241979122161865,
|
| 917 |
+
"eval_runtime": 1150.9235,
|
| 918 |
+
"eval_samples_per_second": 434.434,
|
| 919 |
+
"eval_steps_per_second": 13.576,
|
| 920 |
+
"step": 90000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.6471111111111111,
|
| 924 |
+
"grad_norm": 8.582975387573242,
|
| 925 |
+
"learning_rate": 1.8580314836855227e-05,
|
| 926 |
+
"loss": 4.4139,
|
| 927 |
+
"step": 91000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.6542222222222223,
|
| 931 |
+
"grad_norm": 8.507649421691895,
|
| 932 |
+
"learning_rate": 1.8206043729836143e-05,
|
| 933 |
+
"loss": 4.3542,
|
| 934 |
+
"step": 92000
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.6613333333333333,
|
| 938 |
+
"grad_norm": 6.707493305206299,
|
| 939 |
+
"learning_rate": 1.7832146893924085e-05,
|
| 940 |
+
"loss": 4.3797,
|
| 941 |
+
"step": 93000
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.6684444444444444,
|
| 945 |
+
"grad_norm": 7.590912818908691,
|
| 946 |
+
"learning_rate": 1.7457875786905005e-05,
|
| 947 |
+
"loss": 4.3638,
|
| 948 |
+
"step": 94000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.6755555555555556,
|
| 952 |
+
"grad_norm": 10.533121109008789,
|
| 953 |
+
"learning_rate": 1.7083604679885924e-05,
|
| 954 |
+
"loss": 4.3663,
|
| 955 |
+
"step": 95000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.6826666666666666,
|
| 959 |
+
"grad_norm": 9.008646965026855,
|
| 960 |
+
"learning_rate": 1.670933357286684e-05,
|
| 961 |
+
"loss": 4.3485,
|
| 962 |
+
"step": 96000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.6897777777777778,
|
| 966 |
+
"grad_norm": 5.894834518432617,
|
| 967 |
+
"learning_rate": 1.6335436736954783e-05,
|
| 968 |
+
"loss": 4.3309,
|
| 969 |
+
"step": 97000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.6968888888888889,
|
| 973 |
+
"grad_norm": 8.39154052734375,
|
| 974 |
+
"learning_rate": 1.5961165629935702e-05,
|
| 975 |
+
"loss": 4.3287,
|
| 976 |
+
"step": 98000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.704,
|
| 980 |
+
"grad_norm": 8.664682388305664,
|
| 981 |
+
"learning_rate": 1.558726879402364e-05,
|
| 982 |
+
"loss": 4.3453,
|
| 983 |
+
"step": 99000
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.7111111111111111,
|
| 987 |
+
"grad_norm": 6.261595249176025,
|
| 988 |
+
"learning_rate": 1.521299768700456e-05,
|
| 989 |
+
"loss": 4.3248,
|
| 990 |
+
"step": 100000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.7182222222222222,
|
| 994 |
+
"grad_norm": 6.0963006019592285,
|
| 995 |
+
"learning_rate": 1.4839100851092497e-05,
|
| 996 |
+
"loss": 4.3157,
|
| 997 |
+
"step": 101000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.7253333333333334,
|
| 1001 |
+
"grad_norm": 8.00066089630127,
|
| 1002 |
+
"learning_rate": 1.446482974407342e-05,
|
| 1003 |
+
"loss": 4.2899,
|
| 1004 |
+
"step": 102000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.7324444444444445,
|
| 1008 |
+
"grad_norm": 7.378486156463623,
|
| 1009 |
+
"learning_rate": 1.4090932908161355e-05,
|
| 1010 |
+
"loss": 4.2866,
|
| 1011 |
+
"step": 103000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.7395555555555555,
|
| 1015 |
+
"grad_norm": 7.146476745605469,
|
| 1016 |
+
"learning_rate": 1.3716661801142275e-05,
|
| 1017 |
+
"loss": 4.2811,
|
| 1018 |
+
"step": 104000
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.7466666666666667,
|
| 1022 |
+
"grad_norm": 6.750655174255371,
|
| 1023 |
+
"learning_rate": 1.3342764965230214e-05,
|
| 1024 |
+
"loss": 4.286,
|
| 1025 |
+
"step": 105000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.7466666666666667,
|
| 1029 |
+
"eval_loss": 4.117337703704834,
|
| 1030 |
+
"eval_runtime": 1173.3243,
|
| 1031 |
+
"eval_samples_per_second": 426.14,
|
| 1032 |
+
"eval_steps_per_second": 13.317,
|
| 1033 |
+
"step": 105000
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.7537777777777778,
|
| 1037 |
+
"grad_norm": 8.043438911437988,
|
| 1038 |
+
"learning_rate": 1.2968493858211133e-05,
|
| 1039 |
+
"loss": 4.2712,
|
| 1040 |
+
"step": 106000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.7608888888888888,
|
| 1044 |
+
"grad_norm": 6.856295585632324,
|
| 1045 |
+
"learning_rate": 1.2594597022299074e-05,
|
| 1046 |
+
"loss": 4.269,
|
| 1047 |
+
"step": 107000
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.768,
|
| 1051 |
+
"grad_norm": 7.801486968994141,
|
| 1052 |
+
"learning_rate": 1.2220325915279993e-05,
|
| 1053 |
+
"loss": 4.2669,
|
| 1054 |
+
"step": 108000
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.7751111111111111,
|
| 1058 |
+
"grad_norm": 6.378691673278809,
|
| 1059 |
+
"learning_rate": 1.184642907936793e-05,
|
| 1060 |
+
"loss": 4.2745,
|
| 1061 |
+
"step": 109000
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.7822222222222223,
|
| 1065 |
+
"grad_norm": 6.500033855438232,
|
| 1066 |
+
"learning_rate": 1.1472157972348852e-05,
|
| 1067 |
+
"loss": 4.2327,
|
| 1068 |
+
"step": 110000
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.7893333333333333,
|
| 1072 |
+
"grad_norm": 7.333186626434326,
|
| 1073 |
+
"learning_rate": 1.109826113643679e-05,
|
| 1074 |
+
"loss": 4.2546,
|
| 1075 |
+
"step": 111000
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.7964444444444444,
|
| 1079 |
+
"grad_norm": 6.290594577789307,
|
| 1080 |
+
"learning_rate": 1.0723990029417709e-05,
|
| 1081 |
+
"loss": 4.211,
|
| 1082 |
+
"step": 112000
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.8035555555555556,
|
| 1086 |
+
"grad_norm": 7.892796993255615,
|
| 1087 |
+
"learning_rate": 1.035009319350565e-05,
|
| 1088 |
+
"loss": 4.2283,
|
| 1089 |
+
"step": 113000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.8106666666666666,
|
| 1093 |
+
"grad_norm": 12.832432746887207,
|
| 1094 |
+
"learning_rate": 9.975822086486567e-06,
|
| 1095 |
+
"loss": 4.2151,
|
| 1096 |
+
"step": 114000
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 0.8177777777777778,
|
| 1100 |
+
"grad_norm": 7.7401885986328125,
|
| 1101 |
+
"learning_rate": 9.601925250574506e-06,
|
| 1102 |
+
"loss": 4.2408,
|
| 1103 |
+
"step": 115000
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 0.8248888888888889,
|
| 1107 |
+
"grad_norm": 7.005733489990234,
|
| 1108 |
+
"learning_rate": 9.227654143555427e-06,
|
| 1109 |
+
"loss": 4.2157,
|
| 1110 |
+
"step": 116000
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 0.832,
|
| 1114 |
+
"grad_norm": 6.389645576477051,
|
| 1115 |
+
"learning_rate": 8.853383036536345e-06,
|
| 1116 |
+
"loss": 4.1953,
|
| 1117 |
+
"step": 117000
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 0.8391111111111111,
|
| 1121 |
+
"grad_norm": 10.353365898132324,
|
| 1122 |
+
"learning_rate": 8.479860471731304e-06,
|
| 1123 |
+
"loss": 4.1834,
|
| 1124 |
+
"step": 118000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 0.8462222222222222,
|
| 1128 |
+
"grad_norm": 7.046708106994629,
|
| 1129 |
+
"learning_rate": 8.105589364712223e-06,
|
| 1130 |
+
"loss": 4.1948,
|
| 1131 |
+
"step": 119000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.8533333333333334,
|
| 1135 |
+
"grad_norm": 9.073925018310547,
|
| 1136 |
+
"learning_rate": 7.731318257693143e-06,
|
| 1137 |
+
"loss": 4.2043,
|
| 1138 |
+
"step": 120000
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.8533333333333334,
|
| 1142 |
+
"eval_loss": 4.04020881652832,
|
| 1143 |
+
"eval_runtime": 1223.3756,
|
| 1144 |
+
"eval_samples_per_second": 408.705,
|
| 1145 |
+
"eval_steps_per_second": 12.772,
|
| 1146 |
+
"step": 120000
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.8604444444444445,
|
| 1150 |
+
"grad_norm": 8.47717571258545,
|
| 1151 |
+
"learning_rate": 7.357421421781081e-06,
|
| 1152 |
+
"loss": 4.1805,
|
| 1153 |
+
"step": 121000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.8675555555555555,
|
| 1157 |
+
"grad_norm": 7.262242794036865,
|
| 1158 |
+
"learning_rate": 6.983150314762002e-06,
|
| 1159 |
+
"loss": 4.1904,
|
| 1160 |
+
"step": 122000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.8746666666666667,
|
| 1164 |
+
"grad_norm": 7.6930766105651855,
|
| 1165 |
+
"learning_rate": 6.608879207742922e-06,
|
| 1166 |
+
"loss": 4.1905,
|
| 1167 |
+
"step": 123000
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.8817777777777778,
|
| 1171 |
+
"grad_norm": 8.956729888916016,
|
| 1172 |
+
"learning_rate": 6.23460810072384e-06,
|
| 1173 |
+
"loss": 4.1768,
|
| 1174 |
+
"step": 124000
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.8888888888888888,
|
| 1178 |
+
"grad_norm": 8.849599838256836,
|
| 1179 |
+
"learning_rate": 5.860711264811779e-06,
|
| 1180 |
+
"loss": 4.1684,
|
| 1181 |
+
"step": 125000
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.896,
|
| 1185 |
+
"grad_norm": 7.687771320343018,
|
| 1186 |
+
"learning_rate": 5.486440157792699e-06,
|
| 1187 |
+
"loss": 4.1535,
|
| 1188 |
+
"step": 126000
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.9031111111111111,
|
| 1192 |
+
"grad_norm": 7.867640495300293,
|
| 1193 |
+
"learning_rate": 5.112543321880638e-06,
|
| 1194 |
+
"loss": 4.1821,
|
| 1195 |
+
"step": 127000
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.9102222222222223,
|
| 1199 |
+
"grad_norm": 6.583714008331299,
|
| 1200 |
+
"learning_rate": 4.738272214861557e-06,
|
| 1201 |
+
"loss": 4.1653,
|
| 1202 |
+
"step": 128000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.9173333333333333,
|
| 1206 |
+
"grad_norm": 6.076399326324463,
|
| 1207 |
+
"learning_rate": 4.3643753789494955e-06,
|
| 1208 |
+
"loss": 4.1669,
|
| 1209 |
+
"step": 129000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.9244444444444444,
|
| 1213 |
+
"grad_norm": 7.333767890930176,
|
| 1214 |
+
"learning_rate": 3.990104271930416e-06,
|
| 1215 |
+
"loss": 4.1656,
|
| 1216 |
+
"step": 130000
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.9315555555555556,
|
| 1220 |
+
"grad_norm": 7.766304969787598,
|
| 1221 |
+
"learning_rate": 3.616207436018355e-06,
|
| 1222 |
+
"loss": 4.1568,
|
| 1223 |
+
"step": 131000
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.9386666666666666,
|
| 1227 |
+
"grad_norm": 7.178610324859619,
|
| 1228 |
+
"learning_rate": 3.241936328999274e-06,
|
| 1229 |
+
"loss": 4.1382,
|
| 1230 |
+
"step": 132000
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 0.9457777777777778,
|
| 1234 |
+
"grad_norm": 7.358198165893555,
|
| 1235 |
+
"learning_rate": 2.868039493087213e-06,
|
| 1236 |
+
"loss": 4.1526,
|
| 1237 |
+
"step": 133000
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.9528888888888889,
|
| 1241 |
+
"grad_norm": 6.876594066619873,
|
| 1242 |
+
"learning_rate": 2.4937683860681324e-06,
|
| 1243 |
+
"loss": 4.1653,
|
| 1244 |
+
"step": 134000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.96,
|
| 1248 |
+
"grad_norm": 8.42979621887207,
|
| 1249 |
+
"learning_rate": 2.119871550156071e-06,
|
| 1250 |
+
"loss": 4.1835,
|
| 1251 |
+
"step": 135000
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.96,
|
| 1255 |
+
"eval_loss": 4.000138282775879,
|
| 1256 |
+
"eval_runtime": 1234.4744,
|
| 1257 |
+
"eval_samples_per_second": 405.031,
|
| 1258 |
+
"eval_steps_per_second": 12.657,
|
| 1259 |
+
"step": 135000
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.9671111111111111,
|
| 1263 |
+
"grad_norm": 10.133835792541504,
|
| 1264 |
+
"learning_rate": 1.7456004431369907e-06,
|
| 1265 |
+
"loss": 4.1556,
|
| 1266 |
+
"step": 136000
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.9742222222222222,
|
| 1270 |
+
"grad_norm": 8.190239906311035,
|
| 1271 |
+
"learning_rate": 1.3717036072249296e-06,
|
| 1272 |
+
"loss": 4.1504,
|
| 1273 |
+
"step": 137000
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.9813333333333333,
|
| 1277 |
+
"grad_norm": 8.191669464111328,
|
| 1278 |
+
"learning_rate": 9.974325002058493e-07,
|
| 1279 |
+
"loss": 4.1432,
|
| 1280 |
+
"step": 138000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.9884444444444445,
|
| 1284 |
+
"grad_norm": 7.776695728302002,
|
| 1285 |
+
"learning_rate": 6.235356642937879e-07,
|
| 1286 |
+
"loss": 4.1321,
|
| 1287 |
+
"step": 139000
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.9955555555555555,
|
| 1291 |
+
"grad_norm": 9.083742141723633,
|
| 1292 |
+
"learning_rate": 2.492645572747075e-07,
|
| 1293 |
+
"loss": 4.1393,
|
| 1294 |
+
"step": 140000
|
| 1295 |
+
}
|
| 1296 |
+
],
|
| 1297 |
+
"logging_steps": 1000,
|
| 1298 |
+
"max_steps": 140625,
|
| 1299 |
+
"num_input_tokens_seen": 0,
|
| 1300 |
+
"num_train_epochs": 1,
|
| 1301 |
+
"save_steps": 15000,
|
| 1302 |
+
"stateful_callbacks": {
|
| 1303 |
+
"TrainerControl": {
|
| 1304 |
+
"args": {
|
| 1305 |
+
"should_epoch_stop": false,
|
| 1306 |
+
"should_evaluate": false,
|
| 1307 |
+
"should_log": false,
|
| 1308 |
+
"should_save": true,
|
| 1309 |
+
"should_training_stop": true
|
| 1310 |
+
},
|
| 1311 |
+
"attributes": {}
|
| 1312 |
+
}
|
| 1313 |
+
},
|
| 1314 |
+
"total_flos": 6.541019136e+16,
|
| 1315 |
+
"train_batch_size": 32,
|
| 1316 |
+
"trial_name": null,
|
| 1317 |
+
"trial_params": null
|
| 1318 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c790402a35122c7a82291a2e6247264b479fe9628e489d72bdb3b32f66aff45d
|
| 3 |
+
size 5368
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|