Training in progress, step 106000, checkpoint
Browse files- checkpoint-106000/config.json +39 -0
- checkpoint-106000/generation_config.json +6 -0
- checkpoint-106000/model.safetensors +3 -0
- checkpoint-106000/optimizer.pt +3 -0
- checkpoint-106000/rng_state.pth +3 -0
- checkpoint-106000/scheduler.pt +3 -0
- checkpoint-106000/special_tokens_map.json +17 -0
- checkpoint-106000/tokenizer.json +0 -0
- checkpoint-106000/tokenizer_config.json +58 -0
- checkpoint-106000/trainer_state.json +837 -0
- checkpoint-106000/training_args.bin +3 -0
checkpoint-106000/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 5,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 4,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 128,
|
| 15 |
+
"n_embd": 128,
|
| 16 |
+
"n_head": 4,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 4,
|
| 19 |
+
"n_positions": 128,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.45.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 8192
|
| 39 |
+
}
|
checkpoint-106000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 5,
|
| 4 |
+
"eos_token_id": 4,
|
| 5 |
+
"transformers_version": "4.45.2"
|
| 6 |
+
}
|
checkpoint-106000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8508c8f4739f0451861f2d657ac0fd27fa36a8e815a7ac964a0a388370f25077
|
| 3 |
+
size 7438256
|
checkpoint-106000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0155d4b0a8bad83608c319a2e9780659716d53b5c23aff43dd3abcbc19252e68
|
| 3 |
+
size 14908602
|
checkpoint-106000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac23e1e2645ae00dddcd5ce73ac5adc2b8b09702302b762d2dea30d9ef50af9d
|
| 3 |
+
size 13990
|
checkpoint-106000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ee12704276f50a6205d3664b23e220239f223d653116f0028586f1cf12b6743
|
| 3 |
+
size 1192
|
checkpoint-106000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[BOS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "[EOS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "[EOS]"
|
| 17 |
+
}
|
checkpoint-106000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-106000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "[EOS]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "[BOS]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "[BOS]",
|
| 53 |
+
"clean_up_tokenization_spaces": true,
|
| 54 |
+
"eos_token": "[EOS]",
|
| 55 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 56 |
+
"pad_token": "[EOS]",
|
| 57 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 58 |
+
}
|
checkpoint-106000/trainer_state.json
ADDED
|
@@ -0,0 +1,837 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.461116313934326,
|
| 3 |
+
"best_model_checkpoint": "/Users/frapadovani/Desktop/babyLM_controlled/models_trained/reduce_on_plateau_convergence/age_random/checkpoint-100000",
|
| 4 |
+
"epoch": 0.5609029479153989,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 106000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.010583074488969791,
|
| 13 |
+
"grad_norm": 1.3282362222671509,
|
| 14 |
+
"learning_rate": 0.0001,
|
| 15 |
+
"loss": 4.8574,
|
| 16 |
+
"step": 2000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.010583074488969791,
|
| 20 |
+
"eval_loss": 4.1984477043151855,
|
| 21 |
+
"eval_runtime": 2.3492,
|
| 22 |
+
"eval_samples_per_second": 744.941,
|
| 23 |
+
"eval_steps_per_second": 46.825,
|
| 24 |
+
"step": 2000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.021166148977939583,
|
| 28 |
+
"grad_norm": 1.406479835510254,
|
| 29 |
+
"learning_rate": 0.0001,
|
| 30 |
+
"loss": 4.145,
|
| 31 |
+
"step": 4000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.021166148977939583,
|
| 35 |
+
"eval_loss": 3.9832916259765625,
|
| 36 |
+
"eval_runtime": 2.1928,
|
| 37 |
+
"eval_samples_per_second": 798.069,
|
| 38 |
+
"eval_steps_per_second": 50.164,
|
| 39 |
+
"step": 4000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03174922346690937,
|
| 43 |
+
"grad_norm": 1.4979146718978882,
|
| 44 |
+
"learning_rate": 0.0001,
|
| 45 |
+
"loss": 3.9948,
|
| 46 |
+
"step": 6000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.03174922346690937,
|
| 50 |
+
"eval_loss": 3.872448444366455,
|
| 51 |
+
"eval_runtime": 2.0908,
|
| 52 |
+
"eval_samples_per_second": 837.0,
|
| 53 |
+
"eval_steps_per_second": 52.611,
|
| 54 |
+
"step": 6000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.042332297955879165,
|
| 58 |
+
"grad_norm": 1.4652293920516968,
|
| 59 |
+
"learning_rate": 0.0001,
|
| 60 |
+
"loss": 3.9047,
|
| 61 |
+
"step": 8000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.042332297955879165,
|
| 65 |
+
"eval_loss": 3.8042104244232178,
|
| 66 |
+
"eval_runtime": 2.0939,
|
| 67 |
+
"eval_samples_per_second": 835.759,
|
| 68 |
+
"eval_steps_per_second": 52.533,
|
| 69 |
+
"step": 8000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05291537244484895,
|
| 73 |
+
"grad_norm": 1.523988127708435,
|
| 74 |
+
"learning_rate": 0.0001,
|
| 75 |
+
"loss": 3.8428,
|
| 76 |
+
"step": 10000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.05291537244484895,
|
| 80 |
+
"eval_loss": 3.751901149749756,
|
| 81 |
+
"eval_runtime": 2.1539,
|
| 82 |
+
"eval_samples_per_second": 812.471,
|
| 83 |
+
"eval_steps_per_second": 51.07,
|
| 84 |
+
"step": 10000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.06349844693381874,
|
| 88 |
+
"grad_norm": 1.6126410961151123,
|
| 89 |
+
"learning_rate": 0.0001,
|
| 90 |
+
"loss": 3.7955,
|
| 91 |
+
"step": 12000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.06349844693381874,
|
| 95 |
+
"eval_loss": 3.71409010887146,
|
| 96 |
+
"eval_runtime": 2.0662,
|
| 97 |
+
"eval_samples_per_second": 846.973,
|
| 98 |
+
"eval_steps_per_second": 53.238,
|
| 99 |
+
"step": 12000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07408152142278854,
|
| 103 |
+
"grad_norm": 1.656988263130188,
|
| 104 |
+
"learning_rate": 0.0001,
|
| 105 |
+
"loss": 3.7557,
|
| 106 |
+
"step": 14000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.07408152142278854,
|
| 110 |
+
"eval_loss": 3.6855504512786865,
|
| 111 |
+
"eval_runtime": 2.0523,
|
| 112 |
+
"eval_samples_per_second": 852.711,
|
| 113 |
+
"eval_steps_per_second": 53.599,
|
| 114 |
+
"step": 14000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.08466459591175833,
|
| 118 |
+
"grad_norm": 1.6087511777877808,
|
| 119 |
+
"learning_rate": 0.0001,
|
| 120 |
+
"loss": 3.725,
|
| 121 |
+
"step": 16000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.08466459591175833,
|
| 125 |
+
"eval_loss": 3.658583164215088,
|
| 126 |
+
"eval_runtime": 2.1352,
|
| 127 |
+
"eval_samples_per_second": 819.607,
|
| 128 |
+
"eval_steps_per_second": 51.518,
|
| 129 |
+
"step": 16000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.09524767040072811,
|
| 133 |
+
"grad_norm": 1.6472262144088745,
|
| 134 |
+
"learning_rate": 0.0001,
|
| 135 |
+
"loss": 3.6947,
|
| 136 |
+
"step": 18000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.09524767040072811,
|
| 140 |
+
"eval_loss": 3.638516664505005,
|
| 141 |
+
"eval_runtime": 95.757,
|
| 142 |
+
"eval_samples_per_second": 18.275,
|
| 143 |
+
"eval_steps_per_second": 1.149,
|
| 144 |
+
"step": 18000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.1058307448896979,
|
| 148 |
+
"grad_norm": 1.6628919839859009,
|
| 149 |
+
"learning_rate": 0.0001,
|
| 150 |
+
"loss": 3.6726,
|
| 151 |
+
"step": 20000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.1058307448896979,
|
| 155 |
+
"eval_loss": 3.622284412384033,
|
| 156 |
+
"eval_runtime": 2.1518,
|
| 157 |
+
"eval_samples_per_second": 813.27,
|
| 158 |
+
"eval_steps_per_second": 51.12,
|
| 159 |
+
"step": 20000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1164138193786677,
|
| 163 |
+
"grad_norm": 1.5287901163101196,
|
| 164 |
+
"learning_rate": 0.0001,
|
| 165 |
+
"loss": 3.6556,
|
| 166 |
+
"step": 22000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.1164138193786677,
|
| 170 |
+
"eval_loss": 3.6024463176727295,
|
| 171 |
+
"eval_runtime": 2.0124,
|
| 172 |
+
"eval_samples_per_second": 869.594,
|
| 173 |
+
"eval_steps_per_second": 54.66,
|
| 174 |
+
"step": 22000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.1269968938676375,
|
| 178 |
+
"grad_norm": 1.6352204084396362,
|
| 179 |
+
"learning_rate": 0.0001,
|
| 180 |
+
"loss": 3.6309,
|
| 181 |
+
"step": 24000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.1269968938676375,
|
| 185 |
+
"eval_loss": 3.5923054218292236,
|
| 186 |
+
"eval_runtime": 2.0331,
|
| 187 |
+
"eval_samples_per_second": 860.735,
|
| 188 |
+
"eval_steps_per_second": 54.103,
|
| 189 |
+
"step": 24000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.13757996835660727,
|
| 193 |
+
"grad_norm": 1.5545786619186401,
|
| 194 |
+
"learning_rate": 0.0001,
|
| 195 |
+
"loss": 3.619,
|
| 196 |
+
"step": 26000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.13757996835660727,
|
| 200 |
+
"eval_loss": 3.5808773040771484,
|
| 201 |
+
"eval_runtime": 2.1131,
|
| 202 |
+
"eval_samples_per_second": 828.175,
|
| 203 |
+
"eval_steps_per_second": 52.057,
|
| 204 |
+
"step": 26000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.14816304284557708,
|
| 208 |
+
"grad_norm": 1.6340019702911377,
|
| 209 |
+
"learning_rate": 0.0001,
|
| 210 |
+
"loss": 3.6045,
|
| 211 |
+
"step": 28000
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.14816304284557708,
|
| 215 |
+
"eval_loss": 3.5688397884368896,
|
| 216 |
+
"eval_runtime": 2.0238,
|
| 217 |
+
"eval_samples_per_second": 864.697,
|
| 218 |
+
"eval_steps_per_second": 54.352,
|
| 219 |
+
"step": 28000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.15874611733454685,
|
| 223 |
+
"grad_norm": 1.6332552433013916,
|
| 224 |
+
"learning_rate": 0.0001,
|
| 225 |
+
"loss": 3.5854,
|
| 226 |
+
"step": 30000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.15874611733454685,
|
| 230 |
+
"eval_loss": 3.5667507648468018,
|
| 231 |
+
"eval_runtime": 1.9535,
|
| 232 |
+
"eval_samples_per_second": 895.836,
|
| 233 |
+
"eval_steps_per_second": 56.31,
|
| 234 |
+
"step": 30000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.16932919182351666,
|
| 238 |
+
"grad_norm": 1.6340084075927734,
|
| 239 |
+
"learning_rate": 0.0001,
|
| 240 |
+
"loss": 3.5793,
|
| 241 |
+
"step": 32000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.16932919182351666,
|
| 245 |
+
"eval_loss": 3.557473659515381,
|
| 246 |
+
"eval_runtime": 2.0124,
|
| 247 |
+
"eval_samples_per_second": 869.611,
|
| 248 |
+
"eval_steps_per_second": 54.661,
|
| 249 |
+
"step": 32000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.17991226631248644,
|
| 253 |
+
"grad_norm": 1.5192989110946655,
|
| 254 |
+
"learning_rate": 0.0001,
|
| 255 |
+
"loss": 3.5685,
|
| 256 |
+
"step": 34000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.17991226631248644,
|
| 260 |
+
"eval_loss": 3.545267343521118,
|
| 261 |
+
"eval_runtime": 1.995,
|
| 262 |
+
"eval_samples_per_second": 877.2,
|
| 263 |
+
"eval_steps_per_second": 55.138,
|
| 264 |
+
"step": 34000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.19049534080145622,
|
| 268 |
+
"grad_norm": 1.5996226072311401,
|
| 269 |
+
"learning_rate": 0.0001,
|
| 270 |
+
"loss": 3.556,
|
| 271 |
+
"step": 36000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.19049534080145622,
|
| 275 |
+
"eval_loss": 3.540522336959839,
|
| 276 |
+
"eval_runtime": 1.9783,
|
| 277 |
+
"eval_samples_per_second": 884.601,
|
| 278 |
+
"eval_steps_per_second": 55.603,
|
| 279 |
+
"step": 36000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.20107841529042603,
|
| 283 |
+
"grad_norm": 1.5821503400802612,
|
| 284 |
+
"learning_rate": 0.0001,
|
| 285 |
+
"loss": 3.5475,
|
| 286 |
+
"step": 38000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.20107841529042603,
|
| 290 |
+
"eval_loss": 3.533203125,
|
| 291 |
+
"eval_runtime": 1.9335,
|
| 292 |
+
"eval_samples_per_second": 905.095,
|
| 293 |
+
"eval_steps_per_second": 56.892,
|
| 294 |
+
"step": 38000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.2116614897793958,
|
| 298 |
+
"grad_norm": 1.63215970993042,
|
| 299 |
+
"learning_rate": 0.0001,
|
| 300 |
+
"loss": 3.5358,
|
| 301 |
+
"step": 40000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.2116614897793958,
|
| 305 |
+
"eval_loss": 3.5292651653289795,
|
| 306 |
+
"eval_runtime": 2.0497,
|
| 307 |
+
"eval_samples_per_second": 853.794,
|
| 308 |
+
"eval_steps_per_second": 53.667,
|
| 309 |
+
"step": 40000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.2222445642683656,
|
| 313 |
+
"grad_norm": 1.6347813606262207,
|
| 314 |
+
"learning_rate": 0.0001,
|
| 315 |
+
"loss": 3.5305,
|
| 316 |
+
"step": 42000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.2222445642683656,
|
| 320 |
+
"eval_loss": 3.5237081050872803,
|
| 321 |
+
"eval_runtime": 2.0264,
|
| 322 |
+
"eval_samples_per_second": 863.619,
|
| 323 |
+
"eval_steps_per_second": 54.285,
|
| 324 |
+
"step": 42000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.2328276387573354,
|
| 328 |
+
"grad_norm": 1.617659091949463,
|
| 329 |
+
"learning_rate": 0.0001,
|
| 330 |
+
"loss": 3.5257,
|
| 331 |
+
"step": 44000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.2328276387573354,
|
| 335 |
+
"eval_loss": 3.518353223800659,
|
| 336 |
+
"eval_runtime": 2.0166,
|
| 337 |
+
"eval_samples_per_second": 867.799,
|
| 338 |
+
"eval_steps_per_second": 54.547,
|
| 339 |
+
"step": 44000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.24341071324630517,
|
| 343 |
+
"grad_norm": 1.5734567642211914,
|
| 344 |
+
"learning_rate": 0.0001,
|
| 345 |
+
"loss": 3.5122,
|
| 346 |
+
"step": 46000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.24341071324630517,
|
| 350 |
+
"eval_loss": 3.516266345977783,
|
| 351 |
+
"eval_runtime": 2.0078,
|
| 352 |
+
"eval_samples_per_second": 871.618,
|
| 353 |
+
"eval_steps_per_second": 54.787,
|
| 354 |
+
"step": 46000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.253993787735275,
|
| 358 |
+
"grad_norm": 1.559778094291687,
|
| 359 |
+
"learning_rate": 0.0001,
|
| 360 |
+
"loss": 3.5099,
|
| 361 |
+
"step": 48000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.253993787735275,
|
| 365 |
+
"eval_loss": 3.509239435195923,
|
| 366 |
+
"eval_runtime": 2.0647,
|
| 367 |
+
"eval_samples_per_second": 847.6,
|
| 368 |
+
"eval_steps_per_second": 53.278,
|
| 369 |
+
"step": 48000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.26457686222424476,
|
| 373 |
+
"grad_norm": 1.4903326034545898,
|
| 374 |
+
"learning_rate": 0.0001,
|
| 375 |
+
"loss": 3.503,
|
| 376 |
+
"step": 50000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.26457686222424476,
|
| 380 |
+
"eval_loss": 3.509716510772705,
|
| 381 |
+
"eval_runtime": 2.0953,
|
| 382 |
+
"eval_samples_per_second": 835.185,
|
| 383 |
+
"eval_steps_per_second": 52.497,
|
| 384 |
+
"step": 50000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.27515993671321454,
|
| 388 |
+
"grad_norm": 1.5261775255203247,
|
| 389 |
+
"learning_rate": 0.0001,
|
| 390 |
+
"loss": 3.494,
|
| 391 |
+
"step": 52000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.27515993671321454,
|
| 395 |
+
"eval_loss": 3.505798578262329,
|
| 396 |
+
"eval_runtime": 2.0237,
|
| 397 |
+
"eval_samples_per_second": 864.765,
|
| 398 |
+
"eval_steps_per_second": 54.357,
|
| 399 |
+
"step": 52000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.28574301120218437,
|
| 403 |
+
"grad_norm": 1.5844075679779053,
|
| 404 |
+
"learning_rate": 0.0001,
|
| 405 |
+
"loss": 3.4923,
|
| 406 |
+
"step": 54000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.28574301120218437,
|
| 410 |
+
"eval_loss": 3.5029475688934326,
|
| 411 |
+
"eval_runtime": 2.0259,
|
| 412 |
+
"eval_samples_per_second": 863.817,
|
| 413 |
+
"eval_steps_per_second": 54.297,
|
| 414 |
+
"step": 54000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.29632608569115415,
|
| 418 |
+
"grad_norm": 1.5451163053512573,
|
| 419 |
+
"learning_rate": 0.0001,
|
| 420 |
+
"loss": 3.4839,
|
| 421 |
+
"step": 56000
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.29632608569115415,
|
| 425 |
+
"eval_loss": 3.4993185997009277,
|
| 426 |
+
"eval_runtime": 2.0088,
|
| 427 |
+
"eval_samples_per_second": 871.183,
|
| 428 |
+
"eval_steps_per_second": 54.76,
|
| 429 |
+
"step": 56000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.30690916018012393,
|
| 433 |
+
"grad_norm": 1.5733637809753418,
|
| 434 |
+
"learning_rate": 0.0001,
|
| 435 |
+
"loss": 3.4794,
|
| 436 |
+
"step": 58000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.30690916018012393,
|
| 440 |
+
"eval_loss": 3.4978885650634766,
|
| 441 |
+
"eval_runtime": 1.9995,
|
| 442 |
+
"eval_samples_per_second": 875.202,
|
| 443 |
+
"eval_steps_per_second": 55.013,
|
| 444 |
+
"step": 58000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3174922346690937,
|
| 448 |
+
"grad_norm": 1.6223269701004028,
|
| 449 |
+
"learning_rate": 0.0001,
|
| 450 |
+
"loss": 3.4784,
|
| 451 |
+
"step": 60000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3174922346690937,
|
| 455 |
+
"eval_loss": 3.4934513568878174,
|
| 456 |
+
"eval_runtime": 1.9989,
|
| 457 |
+
"eval_samples_per_second": 875.488,
|
| 458 |
+
"eval_steps_per_second": 55.031,
|
| 459 |
+
"step": 60000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.3280753091580635,
|
| 463 |
+
"grad_norm": 1.5811946392059326,
|
| 464 |
+
"learning_rate": 0.0001,
|
| 465 |
+
"loss": 3.4688,
|
| 466 |
+
"step": 62000
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.3280753091580635,
|
| 470 |
+
"eval_loss": 3.4919357299804688,
|
| 471 |
+
"eval_runtime": 2.0391,
|
| 472 |
+
"eval_samples_per_second": 858.204,
|
| 473 |
+
"eval_steps_per_second": 53.944,
|
| 474 |
+
"step": 62000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.3386583836470333,
|
| 478 |
+
"grad_norm": 1.5161172151565552,
|
| 479 |
+
"learning_rate": 0.0001,
|
| 480 |
+
"loss": 3.4672,
|
| 481 |
+
"step": 64000
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.3386583836470333,
|
| 485 |
+
"eval_loss": 3.488752841949463,
|
| 486 |
+
"eval_runtime": 2.0568,
|
| 487 |
+
"eval_samples_per_second": 850.842,
|
| 488 |
+
"eval_steps_per_second": 53.481,
|
| 489 |
+
"step": 64000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.3492414581360031,
|
| 493 |
+
"grad_norm": 1.6205577850341797,
|
| 494 |
+
"learning_rate": 0.0001,
|
| 495 |
+
"loss": 3.4651,
|
| 496 |
+
"step": 66000
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.3492414581360031,
|
| 500 |
+
"eval_loss": 3.486372709274292,
|
| 501 |
+
"eval_runtime": 2.0004,
|
| 502 |
+
"eval_samples_per_second": 874.843,
|
| 503 |
+
"eval_steps_per_second": 54.99,
|
| 504 |
+
"step": 66000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.3598245326249729,
|
| 508 |
+
"grad_norm": 1.5026018619537354,
|
| 509 |
+
"learning_rate": 0.0001,
|
| 510 |
+
"loss": 3.454,
|
| 511 |
+
"step": 68000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 0.3598245326249729,
|
| 515 |
+
"eval_loss": 3.484797477722168,
|
| 516 |
+
"eval_runtime": 1.9967,
|
| 517 |
+
"eval_samples_per_second": 876.437,
|
| 518 |
+
"eval_steps_per_second": 55.09,
|
| 519 |
+
"step": 68000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.37040760711394266,
|
| 523 |
+
"grad_norm": 1.5378326177597046,
|
| 524 |
+
"learning_rate": 0.0001,
|
| 525 |
+
"loss": 3.4579,
|
| 526 |
+
"step": 70000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.37040760711394266,
|
| 530 |
+
"eval_loss": 3.482553482055664,
|
| 531 |
+
"eval_runtime": 2.0263,
|
| 532 |
+
"eval_samples_per_second": 863.637,
|
| 533 |
+
"eval_steps_per_second": 54.286,
|
| 534 |
+
"step": 70000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.38099068160291244,
|
| 538 |
+
"grad_norm": 1.47434401512146,
|
| 539 |
+
"learning_rate": 0.0001,
|
| 540 |
+
"loss": 3.4525,
|
| 541 |
+
"step": 72000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.38099068160291244,
|
| 545 |
+
"eval_loss": 3.4789111614227295,
|
| 546 |
+
"eval_runtime": 2.0378,
|
| 547 |
+
"eval_samples_per_second": 858.781,
|
| 548 |
+
"eval_steps_per_second": 53.981,
|
| 549 |
+
"step": 72000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3915737560918823,
|
| 553 |
+
"grad_norm": 1.5712401866912842,
|
| 554 |
+
"learning_rate": 0.0001,
|
| 555 |
+
"loss": 3.4448,
|
| 556 |
+
"step": 74000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.3915737560918823,
|
| 560 |
+
"eval_loss": 3.4793760776519775,
|
| 561 |
+
"eval_runtime": 2.0176,
|
| 562 |
+
"eval_samples_per_second": 867.379,
|
| 563 |
+
"eval_steps_per_second": 54.521,
|
| 564 |
+
"step": 74000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.40215683058085205,
|
| 568 |
+
"grad_norm": 1.542845368385315,
|
| 569 |
+
"learning_rate": 0.0001,
|
| 570 |
+
"loss": 3.4483,
|
| 571 |
+
"step": 76000
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.40215683058085205,
|
| 575 |
+
"eval_loss": 3.477855920791626,
|
| 576 |
+
"eval_runtime": 2.0056,
|
| 577 |
+
"eval_samples_per_second": 872.574,
|
| 578 |
+
"eval_steps_per_second": 54.848,
|
| 579 |
+
"step": 76000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.41273990506982183,
|
| 583 |
+
"grad_norm": 1.4774751663208008,
|
| 584 |
+
"learning_rate": 0.0001,
|
| 585 |
+
"loss": 3.4422,
|
| 586 |
+
"step": 78000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.41273990506982183,
|
| 590 |
+
"eval_loss": 3.4766182899475098,
|
| 591 |
+
"eval_runtime": 2.0003,
|
| 592 |
+
"eval_samples_per_second": 874.855,
|
| 593 |
+
"eval_steps_per_second": 54.991,
|
| 594 |
+
"step": 78000
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.4233229795587916,
|
| 598 |
+
"grad_norm": 1.5308395624160767,
|
| 599 |
+
"learning_rate": 0.0001,
|
| 600 |
+
"loss": 3.4365,
|
| 601 |
+
"step": 80000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.4233229795587916,
|
| 605 |
+
"eval_loss": 3.474513292312622,
|
| 606 |
+
"eval_runtime": 2.0652,
|
| 607 |
+
"eval_samples_per_second": 847.387,
|
| 608 |
+
"eval_steps_per_second": 53.264,
|
| 609 |
+
"step": 80000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.4339060540477614,
|
| 613 |
+
"grad_norm": 1.4749510288238525,
|
| 614 |
+
"learning_rate": 0.0001,
|
| 615 |
+
"loss": 3.4383,
|
| 616 |
+
"step": 82000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.4339060540477614,
|
| 620 |
+
"eval_loss": 3.472466468811035,
|
| 621 |
+
"eval_runtime": 2.0372,
|
| 622 |
+
"eval_samples_per_second": 859.028,
|
| 623 |
+
"eval_steps_per_second": 53.996,
|
| 624 |
+
"step": 82000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.4444891285367312,
|
| 628 |
+
"grad_norm": 1.597090721130371,
|
| 629 |
+
"learning_rate": 0.0001,
|
| 630 |
+
"loss": 3.4311,
|
| 631 |
+
"step": 84000
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.4444891285367312,
|
| 635 |
+
"eval_loss": 3.471325397491455,
|
| 636 |
+
"eval_runtime": 1.9964,
|
| 637 |
+
"eval_samples_per_second": 876.594,
|
| 638 |
+
"eval_steps_per_second": 55.1,
|
| 639 |
+
"step": 84000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.455072203025701,
|
| 643 |
+
"grad_norm": 1.5905334949493408,
|
| 644 |
+
"learning_rate": 0.0001,
|
| 645 |
+
"loss": 3.4304,
|
| 646 |
+
"step": 86000
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.455072203025701,
|
| 650 |
+
"eval_loss": 3.4709312915802,
|
| 651 |
+
"eval_runtime": 2.0085,
|
| 652 |
+
"eval_samples_per_second": 871.317,
|
| 653 |
+
"eval_steps_per_second": 54.769,
|
| 654 |
+
"step": 86000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.4656552775146708,
|
| 658 |
+
"grad_norm": 1.5072293281555176,
|
| 659 |
+
"learning_rate": 0.0001,
|
| 660 |
+
"loss": 3.4293,
|
| 661 |
+
"step": 88000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4656552775146708,
|
| 665 |
+
"eval_loss": 3.4678661823272705,
|
| 666 |
+
"eval_runtime": 2.2582,
|
| 667 |
+
"eval_samples_per_second": 774.963,
|
| 668 |
+
"eval_steps_per_second": 48.712,
|
| 669 |
+
"step": 88000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.47623835200364056,
|
| 673 |
+
"grad_norm": 1.5479974746704102,
|
| 674 |
+
"learning_rate": 0.0001,
|
| 675 |
+
"loss": 3.4218,
|
| 676 |
+
"step": 90000
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.47623835200364056,
|
| 680 |
+
"eval_loss": 3.4672610759735107,
|
| 681 |
+
"eval_runtime": 1.9971,
|
| 682 |
+
"eval_samples_per_second": 876.254,
|
| 683 |
+
"eval_steps_per_second": 55.079,
|
| 684 |
+
"step": 90000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.48682142649261034,
|
| 688 |
+
"grad_norm": 1.498063325881958,
|
| 689 |
+
"learning_rate": 0.0001,
|
| 690 |
+
"loss": 3.4226,
|
| 691 |
+
"step": 92000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.48682142649261034,
|
| 695 |
+
"eval_loss": 3.4682064056396484,
|
| 696 |
+
"eval_runtime": 2.0036,
|
| 697 |
+
"eval_samples_per_second": 873.414,
|
| 698 |
+
"eval_steps_per_second": 54.9,
|
| 699 |
+
"step": 92000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.4974045009815802,
|
| 703 |
+
"grad_norm": 1.548446536064148,
|
| 704 |
+
"learning_rate": 0.0001,
|
| 705 |
+
"loss": 3.4231,
|
| 706 |
+
"step": 94000
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.4974045009815802,
|
| 710 |
+
"eval_loss": 3.4639084339141846,
|
| 711 |
+
"eval_runtime": 2.0158,
|
| 712 |
+
"eval_samples_per_second": 868.139,
|
| 713 |
+
"eval_steps_per_second": 54.569,
|
| 714 |
+
"step": 94000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.50798757547055,
|
| 718 |
+
"grad_norm": 1.5000747442245483,
|
| 719 |
+
"learning_rate": 0.0001,
|
| 720 |
+
"loss": 3.4182,
|
| 721 |
+
"step": 96000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.50798757547055,
|
| 725 |
+
"eval_loss": 3.4658689498901367,
|
| 726 |
+
"eval_runtime": 2.0467,
|
| 727 |
+
"eval_samples_per_second": 855.02,
|
| 728 |
+
"eval_steps_per_second": 53.744,
|
| 729 |
+
"step": 96000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.5185706499595197,
|
| 733 |
+
"grad_norm": 1.4724396467208862,
|
| 734 |
+
"learning_rate": 0.0001,
|
| 735 |
+
"loss": 3.4165,
|
| 736 |
+
"step": 98000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.5185706499595197,
|
| 740 |
+
"eval_loss": 3.4674134254455566,
|
| 741 |
+
"eval_runtime": 2.0034,
|
| 742 |
+
"eval_samples_per_second": 873.532,
|
| 743 |
+
"eval_steps_per_second": 54.908,
|
| 744 |
+
"step": 98000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.5291537244484895,
|
| 748 |
+
"grad_norm": 1.5290071964263916,
|
| 749 |
+
"learning_rate": 0.0001,
|
| 750 |
+
"loss": 3.4137,
|
| 751 |
+
"step": 100000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.5291537244484895,
|
| 755 |
+
"eval_loss": 3.461116313934326,
|
| 756 |
+
"eval_runtime": 2.0485,
|
| 757 |
+
"eval_samples_per_second": 854.29,
|
| 758 |
+
"eval_steps_per_second": 53.698,
|
| 759 |
+
"step": 100000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.5397367989374593,
|
| 763 |
+
"grad_norm": 1.5508872270584106,
|
| 764 |
+
"learning_rate": 0.0001,
|
| 765 |
+
"loss": 3.4101,
|
| 766 |
+
"step": 102000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.5397367989374593,
|
| 770 |
+
"eval_loss": 3.4652554988861084,
|
| 771 |
+
"eval_runtime": 1.9932,
|
| 772 |
+
"eval_samples_per_second": 877.983,
|
| 773 |
+
"eval_steps_per_second": 55.188,
|
| 774 |
+
"step": 102000
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.5503198734264291,
|
| 778 |
+
"grad_norm": 1.4633408784866333,
|
| 779 |
+
"learning_rate": 0.0001,
|
| 780 |
+
"loss": 3.4136,
|
| 781 |
+
"step": 104000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.5503198734264291,
|
| 785 |
+
"eval_loss": 3.4647574424743652,
|
| 786 |
+
"eval_runtime": 6.716,
|
| 787 |
+
"eval_samples_per_second": 260.574,
|
| 788 |
+
"eval_steps_per_second": 16.379,
|
| 789 |
+
"step": 104000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.5609029479153989,
|
| 793 |
+
"grad_norm": 1.530918836593628,
|
| 794 |
+
"learning_rate": 0.0001,
|
| 795 |
+
"loss": 3.4059,
|
| 796 |
+
"step": 106000
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.5609029479153989,
|
| 800 |
+
"eval_loss": 3.461215019226074,
|
| 801 |
+
"eval_runtime": 2.0399,
|
| 802 |
+
"eval_samples_per_second": 857.878,
|
| 803 |
+
"eval_steps_per_second": 53.924,
|
| 804 |
+
"step": 106000
|
| 805 |
+
}
|
| 806 |
+
],
|
| 807 |
+
"logging_steps": 2000,
|
| 808 |
+
"max_steps": 188981,
|
| 809 |
+
"num_input_tokens_seen": 0,
|
| 810 |
+
"num_train_epochs": 1,
|
| 811 |
+
"save_steps": 2000,
|
| 812 |
+
"stateful_callbacks": {
|
| 813 |
+
"EarlyStoppingCallback": {
|
| 814 |
+
"args": {
|
| 815 |
+
"early_stopping_patience": 3,
|
| 816 |
+
"early_stopping_threshold": 0.001
|
| 817 |
+
},
|
| 818 |
+
"attributes": {
|
| 819 |
+
"early_stopping_patience_counter": 3
|
| 820 |
+
}
|
| 821 |
+
},
|
| 822 |
+
"TrainerControl": {
|
| 823 |
+
"args": {
|
| 824 |
+
"should_epoch_stop": false,
|
| 825 |
+
"should_evaluate": false,
|
| 826 |
+
"should_log": false,
|
| 827 |
+
"should_save": true,
|
| 828 |
+
"should_training_stop": true
|
| 829 |
+
},
|
| 830 |
+
"attributes": {}
|
| 831 |
+
}
|
| 832 |
+
},
|
| 833 |
+
"total_flos": 1033352621309952.0,
|
| 834 |
+
"train_batch_size": 16,
|
| 835 |
+
"trial_name": null,
|
| 836 |
+
"trial_params": null
|
| 837 |
+
}
|
checkpoint-106000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c0a2b1811aeefb927284bf3c5c8de0a89d0ad3fd57a0b61184713eb6f012eba
|
| 3 |
+
size 5432
|