Training in progress, step 33000, checkpoint
Browse files- checkpoint-33000/config.json +39 -0
- checkpoint-33000/generation_config.json +6 -0
- checkpoint-33000/model.safetensors +3 -0
- checkpoint-33000/optimizer.pt +3 -0
- checkpoint-33000/rng_state.pth +3 -0
- checkpoint-33000/scheduler.pt +3 -0
- checkpoint-33000/special_tokens_map.json +17 -0
- checkpoint-33000/tokenizer.json +0 -0
- checkpoint-33000/tokenizer_config.json +58 -0
- checkpoint-33000/trainer_state.json +768 -0
- checkpoint-33000/training_args.bin +3 -0
checkpoint-33000/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": 1024,
|
| 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-33000/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-33000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74aa03b1dac3ae2270c273bae69d91c13b144cc3fc06119b5bf586dd1d11a0ae
|
| 3 |
+
size 7438256
|
checkpoint-33000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8da1fb6ff39094ef1627b905d4349da82ec76ede48397a85c79b59da2c5a65bd
|
| 3 |
+
size 14910010
|
checkpoint-33000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7900d766219e2183af349bcd4141097832afabdba914c434d354b1a43d4d0d91
|
| 3 |
+
size 14244
|
checkpoint-33000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b2d3430f439301edf529a816adeffc23c6f0192008f9998817d807eac97a86b
|
| 3 |
+
size 1192
|
checkpoint-33000/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-33000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-33000/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-33000/trainer_state.json
ADDED
|
@@ -0,0 +1,768 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.25608491897583,
|
| 3 |
+
"best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/reduce_on_plateau_convergence/random_transcript_conv/checkpoint-33000",
|
| 4 |
+
"epoch": 0.8380101069097743,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 33000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.012697122831966277,
|
| 13 |
+
"grad_norm": 0.7364352941513062,
|
| 14 |
+
"learning_rate": 0.0001,
|
| 15 |
+
"loss": 5.9868,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.025394245663932554,
|
| 20 |
+
"grad_norm": 1.3591667413711548,
|
| 21 |
+
"learning_rate": 0.0001,
|
| 22 |
+
"loss": 4.7264,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.025394245663932554,
|
| 27 |
+
"eval_loss": 4.496066570281982,
|
| 28 |
+
"eval_runtime": 1.8776,
|
| 29 |
+
"eval_samples_per_second": 932.025,
|
| 30 |
+
"eval_steps_per_second": 29.292,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03809136849589883,
|
| 35 |
+
"grad_norm": 0.9609436988830566,
|
| 36 |
+
"learning_rate": 0.0001,
|
| 37 |
+
"loss": 4.4273,
|
| 38 |
+
"step": 1500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05078849132786511,
|
| 42 |
+
"grad_norm": 1.208341360092163,
|
| 43 |
+
"learning_rate": 0.0001,
|
| 44 |
+
"loss": 4.2766,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05078849132786511,
|
| 49 |
+
"eval_loss": 4.21427583694458,
|
| 50 |
+
"eval_runtime": 1.8912,
|
| 51 |
+
"eval_samples_per_second": 925.334,
|
| 52 |
+
"eval_steps_per_second": 29.082,
|
| 53 |
+
"step": 2000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.06348561415983138,
|
| 57 |
+
"grad_norm": 1.4926683902740479,
|
| 58 |
+
"learning_rate": 0.0001,
|
| 59 |
+
"loss": 4.2317,
|
| 60 |
+
"step": 2500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.07618273699179766,
|
| 64 |
+
"grad_norm": 1.3337597846984863,
|
| 65 |
+
"learning_rate": 0.0001,
|
| 66 |
+
"loss": 4.1231,
|
| 67 |
+
"step": 3000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.07618273699179766,
|
| 71 |
+
"eval_loss": 4.032348155975342,
|
| 72 |
+
"eval_runtime": 1.8734,
|
| 73 |
+
"eval_samples_per_second": 934.155,
|
| 74 |
+
"eval_steps_per_second": 29.359,
|
| 75 |
+
"step": 3000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.08887985982376394,
|
| 79 |
+
"grad_norm": 1.7601583003997803,
|
| 80 |
+
"learning_rate": 0.0001,
|
| 81 |
+
"loss": 4.0229,
|
| 82 |
+
"step": 3500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.10157698265573022,
|
| 86 |
+
"grad_norm": 1.3109067678451538,
|
| 87 |
+
"learning_rate": 0.0001,
|
| 88 |
+
"loss": 4.0307,
|
| 89 |
+
"step": 4000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.10157698265573022,
|
| 93 |
+
"eval_loss": 3.9221267700195312,
|
| 94 |
+
"eval_runtime": 1.8807,
|
| 95 |
+
"eval_samples_per_second": 930.486,
|
| 96 |
+
"eval_steps_per_second": 29.244,
|
| 97 |
+
"step": 4000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.11427410548769648,
|
| 101 |
+
"grad_norm": 1.6231205463409424,
|
| 102 |
+
"learning_rate": 0.0001,
|
| 103 |
+
"loss": 3.9838,
|
| 104 |
+
"step": 4500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.12697122831966276,
|
| 108 |
+
"grad_norm": 1.6827378273010254,
|
| 109 |
+
"learning_rate": 0.0001,
|
| 110 |
+
"loss": 3.8887,
|
| 111 |
+
"step": 5000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.12697122831966276,
|
| 115 |
+
"eval_loss": 3.857755661010742,
|
| 116 |
+
"eval_runtime": 1.8825,
|
| 117 |
+
"eval_samples_per_second": 929.612,
|
| 118 |
+
"eval_steps_per_second": 29.216,
|
| 119 |
+
"step": 5000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.13966835115162904,
|
| 123 |
+
"grad_norm": 1.4547417163848877,
|
| 124 |
+
"learning_rate": 0.0001,
|
| 125 |
+
"loss": 3.8996,
|
| 126 |
+
"step": 5500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.15236547398359532,
|
| 130 |
+
"grad_norm": 1.4457532167434692,
|
| 131 |
+
"learning_rate": 0.0001,
|
| 132 |
+
"loss": 3.8689,
|
| 133 |
+
"step": 6000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.15236547398359532,
|
| 137 |
+
"eval_loss": 3.779956579208374,
|
| 138 |
+
"eval_runtime": 1.8835,
|
| 139 |
+
"eval_samples_per_second": 929.122,
|
| 140 |
+
"eval_steps_per_second": 29.201,
|
| 141 |
+
"step": 6000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1650625968155616,
|
| 145 |
+
"grad_norm": 1.6317448616027832,
|
| 146 |
+
"learning_rate": 0.0001,
|
| 147 |
+
"loss": 3.8136,
|
| 148 |
+
"step": 6500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.17775971964752788,
|
| 152 |
+
"grad_norm": 1.5866583585739136,
|
| 153 |
+
"learning_rate": 0.0001,
|
| 154 |
+
"loss": 3.7808,
|
| 155 |
+
"step": 7000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.17775971964752788,
|
| 159 |
+
"eval_loss": 3.7245218753814697,
|
| 160 |
+
"eval_runtime": 2.2249,
|
| 161 |
+
"eval_samples_per_second": 786.548,
|
| 162 |
+
"eval_steps_per_second": 24.72,
|
| 163 |
+
"step": 7000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.19045684247949415,
|
| 167 |
+
"grad_norm": 1.6744858026504517,
|
| 168 |
+
"learning_rate": 0.0001,
|
| 169 |
+
"loss": 3.7905,
|
| 170 |
+
"step": 7500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.20315396531146043,
|
| 174 |
+
"grad_norm": 1.818229079246521,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 3.742,
|
| 177 |
+
"step": 8000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.20315396531146043,
|
| 181 |
+
"eval_loss": 3.685417413711548,
|
| 182 |
+
"eval_runtime": 1.8966,
|
| 183 |
+
"eval_samples_per_second": 922.71,
|
| 184 |
+
"eval_steps_per_second": 28.999,
|
| 185 |
+
"step": 8000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.2158510881434267,
|
| 189 |
+
"grad_norm": 1.648987054824829,
|
| 190 |
+
"learning_rate": 0.0001,
|
| 191 |
+
"loss": 3.6802,
|
| 192 |
+
"step": 8500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.22854821097539296,
|
| 196 |
+
"grad_norm": 1.5762256383895874,
|
| 197 |
+
"learning_rate": 0.0001,
|
| 198 |
+
"loss": 3.7303,
|
| 199 |
+
"step": 9000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.22854821097539296,
|
| 203 |
+
"eval_loss": 3.6259124279022217,
|
| 204 |
+
"eval_runtime": 1.8817,
|
| 205 |
+
"eval_samples_per_second": 930.029,
|
| 206 |
+
"eval_steps_per_second": 29.229,
|
| 207 |
+
"step": 9000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.24124533380735924,
|
| 211 |
+
"grad_norm": 1.7662715911865234,
|
| 212 |
+
"learning_rate": 0.0001,
|
| 213 |
+
"loss": 3.6795,
|
| 214 |
+
"step": 9500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.2539424566393255,
|
| 218 |
+
"grad_norm": 1.4495737552642822,
|
| 219 |
+
"learning_rate": 0.0001,
|
| 220 |
+
"loss": 3.5985,
|
| 221 |
+
"step": 10000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.2539424566393255,
|
| 225 |
+
"eval_loss": 3.6000101566314697,
|
| 226 |
+
"eval_runtime": 1.878,
|
| 227 |
+
"eval_samples_per_second": 931.832,
|
| 228 |
+
"eval_steps_per_second": 29.286,
|
| 229 |
+
"step": 10000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.2666395794712918,
|
| 233 |
+
"grad_norm": 1.66859769821167,
|
| 234 |
+
"learning_rate": 0.0001,
|
| 235 |
+
"loss": 3.6678,
|
| 236 |
+
"step": 10500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.2793367023032581,
|
| 240 |
+
"grad_norm": 1.732608437538147,
|
| 241 |
+
"learning_rate": 0.0001,
|
| 242 |
+
"loss": 3.6448,
|
| 243 |
+
"step": 11000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.2793367023032581,
|
| 247 |
+
"eval_loss": 3.5645763874053955,
|
| 248 |
+
"eval_runtime": 1.8955,
|
| 249 |
+
"eval_samples_per_second": 923.251,
|
| 250 |
+
"eval_steps_per_second": 29.016,
|
| 251 |
+
"step": 11000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.29203382513522436,
|
| 255 |
+
"grad_norm": 1.6916662454605103,
|
| 256 |
+
"learning_rate": 0.0001,
|
| 257 |
+
"loss": 3.5147,
|
| 258 |
+
"step": 11500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.30473094796719064,
|
| 262 |
+
"grad_norm": 1.5045229196548462,
|
| 263 |
+
"learning_rate": 0.0001,
|
| 264 |
+
"loss": 3.6531,
|
| 265 |
+
"step": 12000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.30473094796719064,
|
| 269 |
+
"eval_loss": 3.5309834480285645,
|
| 270 |
+
"eval_runtime": 1.8924,
|
| 271 |
+
"eval_samples_per_second": 924.776,
|
| 272 |
+
"eval_steps_per_second": 29.064,
|
| 273 |
+
"step": 12000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.3174280707991569,
|
| 277 |
+
"grad_norm": 1.6316158771514893,
|
| 278 |
+
"learning_rate": 0.0001,
|
| 279 |
+
"loss": 3.6017,
|
| 280 |
+
"step": 12500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.3301251936311232,
|
| 284 |
+
"grad_norm": 1.919342279434204,
|
| 285 |
+
"learning_rate": 0.0001,
|
| 286 |
+
"loss": 3.463,
|
| 287 |
+
"step": 13000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.3301251936311232,
|
| 291 |
+
"eval_loss": 3.511993885040283,
|
| 292 |
+
"eval_runtime": 1.8642,
|
| 293 |
+
"eval_samples_per_second": 938.717,
|
| 294 |
+
"eval_steps_per_second": 29.503,
|
| 295 |
+
"step": 13000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.34282231646308947,
|
| 299 |
+
"grad_norm": 1.7749569416046143,
|
| 300 |
+
"learning_rate": 0.0001,
|
| 301 |
+
"loss": 3.5823,
|
| 302 |
+
"step": 13500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.35551943929505575,
|
| 306 |
+
"grad_norm": 1.533130407333374,
|
| 307 |
+
"learning_rate": 0.0001,
|
| 308 |
+
"loss": 3.5609,
|
| 309 |
+
"step": 14000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.35551943929505575,
|
| 313 |
+
"eval_loss": 3.482698917388916,
|
| 314 |
+
"eval_runtime": 1.8848,
|
| 315 |
+
"eval_samples_per_second": 928.478,
|
| 316 |
+
"eval_steps_per_second": 29.181,
|
| 317 |
+
"step": 14000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.36821656212702203,
|
| 321 |
+
"grad_norm": 1.6455868482589722,
|
| 322 |
+
"learning_rate": 0.0001,
|
| 323 |
+
"loss": 3.4647,
|
| 324 |
+
"step": 14500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.3809136849589883,
|
| 328 |
+
"grad_norm": 1.7260792255401611,
|
| 329 |
+
"learning_rate": 0.0001,
|
| 330 |
+
"loss": 3.5348,
|
| 331 |
+
"step": 15000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3809136849589883,
|
| 335 |
+
"eval_loss": 3.4513492584228516,
|
| 336 |
+
"eval_runtime": 1.8871,
|
| 337 |
+
"eval_samples_per_second": 927.351,
|
| 338 |
+
"eval_steps_per_second": 29.145,
|
| 339 |
+
"step": 15000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3936108077909546,
|
| 343 |
+
"grad_norm": 1.6242613792419434,
|
| 344 |
+
"learning_rate": 0.0001,
|
| 345 |
+
"loss": 3.5033,
|
| 346 |
+
"step": 15500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.40630793062292087,
|
| 350 |
+
"grad_norm": 1.9164397716522217,
|
| 351 |
+
"learning_rate": 0.0001,
|
| 352 |
+
"loss": 3.4552,
|
| 353 |
+
"step": 16000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.40630793062292087,
|
| 357 |
+
"eval_loss": 3.4490864276885986,
|
| 358 |
+
"eval_runtime": 1.8939,
|
| 359 |
+
"eval_samples_per_second": 923.998,
|
| 360 |
+
"eval_steps_per_second": 29.04,
|
| 361 |
+
"step": 16000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.41900505345488714,
|
| 365 |
+
"grad_norm": 2.06667423248291,
|
| 366 |
+
"learning_rate": 0.0001,
|
| 367 |
+
"loss": 3.4767,
|
| 368 |
+
"step": 16500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.4317021762868534,
|
| 372 |
+
"grad_norm": 1.7688324451446533,
|
| 373 |
+
"learning_rate": 0.0001,
|
| 374 |
+
"loss": 3.4829,
|
| 375 |
+
"step": 17000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.4317021762868534,
|
| 379 |
+
"eval_loss": 3.4177420139312744,
|
| 380 |
+
"eval_runtime": 1.8943,
|
| 381 |
+
"eval_samples_per_second": 923.832,
|
| 382 |
+
"eval_steps_per_second": 29.035,
|
| 383 |
+
"step": 17000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.4443992991188197,
|
| 387 |
+
"grad_norm": 1.7661221027374268,
|
| 388 |
+
"learning_rate": 0.0001,
|
| 389 |
+
"loss": 3.4318,
|
| 390 |
+
"step": 17500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.4570964219507859,
|
| 394 |
+
"grad_norm": 1.850075602531433,
|
| 395 |
+
"learning_rate": 0.0001,
|
| 396 |
+
"loss": 3.4333,
|
| 397 |
+
"step": 18000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.4570964219507859,
|
| 401 |
+
"eval_loss": 3.399797201156616,
|
| 402 |
+
"eval_runtime": 1.8894,
|
| 403 |
+
"eval_samples_per_second": 926.224,
|
| 404 |
+
"eval_steps_per_second": 29.11,
|
| 405 |
+
"step": 18000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.4697935447827522,
|
| 409 |
+
"grad_norm": 1.7300879955291748,
|
| 410 |
+
"learning_rate": 0.0001,
|
| 411 |
+
"loss": 3.4536,
|
| 412 |
+
"step": 18500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.4824906676147185,
|
| 416 |
+
"grad_norm": 1.766664981842041,
|
| 417 |
+
"learning_rate": 0.0001,
|
| 418 |
+
"loss": 3.4369,
|
| 419 |
+
"step": 19000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.4824906676147185,
|
| 423 |
+
"eval_loss": 3.392703056335449,
|
| 424 |
+
"eval_runtime": 1.8918,
|
| 425 |
+
"eval_samples_per_second": 925.055,
|
| 426 |
+
"eval_steps_per_second": 29.073,
|
| 427 |
+
"step": 19000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.49518779044668476,
|
| 431 |
+
"grad_norm": 1.7910844087600708,
|
| 432 |
+
"learning_rate": 0.0001,
|
| 433 |
+
"loss": 3.3695,
|
| 434 |
+
"step": 19500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.507884913278651,
|
| 438 |
+
"grad_norm": 1.9836139678955078,
|
| 439 |
+
"learning_rate": 0.0001,
|
| 440 |
+
"loss": 3.4465,
|
| 441 |
+
"step": 20000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.507884913278651,
|
| 445 |
+
"eval_loss": 3.369419574737549,
|
| 446 |
+
"eval_runtime": 1.8933,
|
| 447 |
+
"eval_samples_per_second": 924.32,
|
| 448 |
+
"eval_steps_per_second": 29.05,
|
| 449 |
+
"step": 20000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.5205820361106174,
|
| 453 |
+
"grad_norm": 1.8442771434783936,
|
| 454 |
+
"learning_rate": 0.0001,
|
| 455 |
+
"loss": 3.4164,
|
| 456 |
+
"step": 20500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.5332791589425836,
|
| 460 |
+
"grad_norm": 1.7625914812088013,
|
| 461 |
+
"learning_rate": 0.0001,
|
| 462 |
+
"loss": 3.2959,
|
| 463 |
+
"step": 21000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.5332791589425836,
|
| 467 |
+
"eval_loss": 3.375471830368042,
|
| 468 |
+
"eval_runtime": 1.9032,
|
| 469 |
+
"eval_samples_per_second": 919.503,
|
| 470 |
+
"eval_steps_per_second": 28.899,
|
| 471 |
+
"step": 21000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.5459762817745499,
|
| 475 |
+
"grad_norm": 1.8907791376113892,
|
| 476 |
+
"learning_rate": 0.0001,
|
| 477 |
+
"loss": 3.4429,
|
| 478 |
+
"step": 21500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.5586734046065162,
|
| 482 |
+
"grad_norm": 1.8483226299285889,
|
| 483 |
+
"learning_rate": 0.0001,
|
| 484 |
+
"loss": 3.3914,
|
| 485 |
+
"step": 22000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.5586734046065162,
|
| 489 |
+
"eval_loss": 3.350785255432129,
|
| 490 |
+
"eval_runtime": 1.8845,
|
| 491 |
+
"eval_samples_per_second": 928.642,
|
| 492 |
+
"eval_steps_per_second": 29.186,
|
| 493 |
+
"step": 22000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.5713705274384825,
|
| 497 |
+
"grad_norm": 2.0661497116088867,
|
| 498 |
+
"learning_rate": 0.0001,
|
| 499 |
+
"loss": 3.2699,
|
| 500 |
+
"step": 22500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5840676502704487,
|
| 504 |
+
"grad_norm": 1.5977550745010376,
|
| 505 |
+
"learning_rate": 0.0001,
|
| 506 |
+
"loss": 3.419,
|
| 507 |
+
"step": 23000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5840676502704487,
|
| 511 |
+
"eval_loss": 3.329608201980591,
|
| 512 |
+
"eval_runtime": 1.896,
|
| 513 |
+
"eval_samples_per_second": 923.014,
|
| 514 |
+
"eval_steps_per_second": 29.009,
|
| 515 |
+
"step": 23000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.596764773102415,
|
| 519 |
+
"grad_norm": 1.6787301301956177,
|
| 520 |
+
"learning_rate": 0.0001,
|
| 521 |
+
"loss": 3.3888,
|
| 522 |
+
"step": 23500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.6094618959343813,
|
| 526 |
+
"grad_norm": 1.872283935546875,
|
| 527 |
+
"learning_rate": 0.0001,
|
| 528 |
+
"loss": 3.2619,
|
| 529 |
+
"step": 24000
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.6094618959343813,
|
| 533 |
+
"eval_loss": 3.3345563411712646,
|
| 534 |
+
"eval_runtime": 1.8879,
|
| 535 |
+
"eval_samples_per_second": 926.958,
|
| 536 |
+
"eval_steps_per_second": 29.133,
|
| 537 |
+
"step": 24000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6221590187663475,
|
| 541 |
+
"grad_norm": 1.785620927810669,
|
| 542 |
+
"learning_rate": 0.0001,
|
| 543 |
+
"loss": 3.3991,
|
| 544 |
+
"step": 24500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.6348561415983138,
|
| 548 |
+
"grad_norm": 1.7891900539398193,
|
| 549 |
+
"learning_rate": 0.0001,
|
| 550 |
+
"loss": 3.3485,
|
| 551 |
+
"step": 25000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.6348561415983138,
|
| 555 |
+
"eval_loss": 3.317343235015869,
|
| 556 |
+
"eval_runtime": 1.8869,
|
| 557 |
+
"eval_samples_per_second": 927.433,
|
| 558 |
+
"eval_steps_per_second": 29.148,
|
| 559 |
+
"step": 25000
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.64755326443028,
|
| 563 |
+
"grad_norm": 2.1394989490509033,
|
| 564 |
+
"learning_rate": 0.0001,
|
| 565 |
+
"loss": 3.2727,
|
| 566 |
+
"step": 25500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.6602503872622464,
|
| 570 |
+
"grad_norm": 1.7931321859359741,
|
| 571 |
+
"learning_rate": 0.0001,
|
| 572 |
+
"loss": 3.3355,
|
| 573 |
+
"step": 26000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.6602503872622464,
|
| 577 |
+
"eval_loss": 3.30899715423584,
|
| 578 |
+
"eval_runtime": 1.8677,
|
| 579 |
+
"eval_samples_per_second": 937.0,
|
| 580 |
+
"eval_steps_per_second": 29.449,
|
| 581 |
+
"step": 26000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.6729475100942126,
|
| 585 |
+
"grad_norm": 1.6096218824386597,
|
| 586 |
+
"learning_rate": 0.0001,
|
| 587 |
+
"loss": 3.3523,
|
| 588 |
+
"step": 26500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.6856446329261789,
|
| 592 |
+
"grad_norm": 1.7073876857757568,
|
| 593 |
+
"learning_rate": 0.0001,
|
| 594 |
+
"loss": 3.3004,
|
| 595 |
+
"step": 27000
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 0.6856446329261789,
|
| 599 |
+
"eval_loss": 3.3027215003967285,
|
| 600 |
+
"eval_runtime": 1.8867,
|
| 601 |
+
"eval_samples_per_second": 927.567,
|
| 602 |
+
"eval_steps_per_second": 29.152,
|
| 603 |
+
"step": 27000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.6983417557581452,
|
| 607 |
+
"grad_norm": 2.086873769760132,
|
| 608 |
+
"learning_rate": 0.0001,
|
| 609 |
+
"loss": 3.2913,
|
| 610 |
+
"step": 27500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.7110388785901115,
|
| 614 |
+
"grad_norm": 1.8759254217147827,
|
| 615 |
+
"learning_rate": 0.0001,
|
| 616 |
+
"loss": 3.3105,
|
| 617 |
+
"step": 28000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.7110388785901115,
|
| 621 |
+
"eval_loss": 3.2893998622894287,
|
| 622 |
+
"eval_runtime": 1.9141,
|
| 623 |
+
"eval_samples_per_second": 914.246,
|
| 624 |
+
"eval_steps_per_second": 28.733,
|
| 625 |
+
"step": 28000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.7237360014220777,
|
| 629 |
+
"grad_norm": 1.829256534576416,
|
| 630 |
+
"learning_rate": 0.0001,
|
| 631 |
+
"loss": 3.306,
|
| 632 |
+
"step": 28500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.7364331242540441,
|
| 636 |
+
"grad_norm": 1.7779229879379272,
|
| 637 |
+
"learning_rate": 0.0001,
|
| 638 |
+
"loss": 3.2625,
|
| 639 |
+
"step": 29000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.7364331242540441,
|
| 643 |
+
"eval_loss": 3.280762195587158,
|
| 644 |
+
"eval_runtime": 1.8923,
|
| 645 |
+
"eval_samples_per_second": 924.789,
|
| 646 |
+
"eval_steps_per_second": 29.065,
|
| 647 |
+
"step": 29000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.7491302470860103,
|
| 651 |
+
"grad_norm": 2.136992931365967,
|
| 652 |
+
"learning_rate": 0.0001,
|
| 653 |
+
"loss": 3.3047,
|
| 654 |
+
"step": 29500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7618273699179766,
|
| 658 |
+
"grad_norm": 1.8829364776611328,
|
| 659 |
+
"learning_rate": 0.0001,
|
| 660 |
+
"loss": 3.3031,
|
| 661 |
+
"step": 30000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.7618273699179766,
|
| 665 |
+
"eval_loss": 3.2878408432006836,
|
| 666 |
+
"eval_runtime": 1.9013,
|
| 667 |
+
"eval_samples_per_second": 920.423,
|
| 668 |
+
"eval_steps_per_second": 28.928,
|
| 669 |
+
"step": 30000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.7745244927499428,
|
| 673 |
+
"grad_norm": 1.6958101987838745,
|
| 674 |
+
"learning_rate": 0.0001,
|
| 675 |
+
"loss": 3.2108,
|
| 676 |
+
"step": 30500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.7872216155819092,
|
| 680 |
+
"grad_norm": 2.244068145751953,
|
| 681 |
+
"learning_rate": 0.0001,
|
| 682 |
+
"loss": 3.3047,
|
| 683 |
+
"step": 31000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.7872216155819092,
|
| 687 |
+
"eval_loss": 3.2691428661346436,
|
| 688 |
+
"eval_runtime": 1.8783,
|
| 689 |
+
"eval_samples_per_second": 931.715,
|
| 690 |
+
"eval_steps_per_second": 29.282,
|
| 691 |
+
"step": 31000
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 0.7999187384138754,
|
| 695 |
+
"grad_norm": 1.7616338729858398,
|
| 696 |
+
"learning_rate": 0.0001,
|
| 697 |
+
"loss": 3.3167,
|
| 698 |
+
"step": 31500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.8126158612458417,
|
| 702 |
+
"grad_norm": 1.564754843711853,
|
| 703 |
+
"learning_rate": 0.0001,
|
| 704 |
+
"loss": 3.1521,
|
| 705 |
+
"step": 32000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.8126158612458417,
|
| 709 |
+
"eval_loss": 3.274914503097534,
|
| 710 |
+
"eval_runtime": 1.8953,
|
| 711 |
+
"eval_samples_per_second": 923.316,
|
| 712 |
+
"eval_steps_per_second": 29.018,
|
| 713 |
+
"step": 32000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.825312984077808,
|
| 717 |
+
"grad_norm": 1.7152769565582275,
|
| 718 |
+
"learning_rate": 0.0001,
|
| 719 |
+
"loss": 3.3201,
|
| 720 |
+
"step": 32500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.8380101069097743,
|
| 724 |
+
"grad_norm": 1.748099684715271,
|
| 725 |
+
"learning_rate": 0.0001,
|
| 726 |
+
"loss": 3.2836,
|
| 727 |
+
"step": 33000
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.8380101069097743,
|
| 731 |
+
"eval_loss": 3.25608491897583,
|
| 732 |
+
"eval_runtime": 1.8883,
|
| 733 |
+
"eval_samples_per_second": 926.758,
|
| 734 |
+
"eval_steps_per_second": 29.127,
|
| 735 |
+
"step": 33000
|
| 736 |
+
}
|
| 737 |
+
],
|
| 738 |
+
"logging_steps": 500,
|
| 739 |
+
"max_steps": 39379,
|
| 740 |
+
"num_input_tokens_seen": 0,
|
| 741 |
+
"num_train_epochs": 1,
|
| 742 |
+
"save_steps": 1000,
|
| 743 |
+
"stateful_callbacks": {
|
| 744 |
+
"EarlyStoppingCallback": {
|
| 745 |
+
"args": {
|
| 746 |
+
"early_stopping_patience": 3,
|
| 747 |
+
"early_stopping_threshold": 0.001
|
| 748 |
+
},
|
| 749 |
+
"attributes": {
|
| 750 |
+
"early_stopping_patience_counter": 0
|
| 751 |
+
}
|
| 752 |
+
},
|
| 753 |
+
"TrainerControl": {
|
| 754 |
+
"args": {
|
| 755 |
+
"should_epoch_stop": false,
|
| 756 |
+
"should_evaluate": false,
|
| 757 |
+
"should_log": false,
|
| 758 |
+
"should_save": true,
|
| 759 |
+
"should_training_stop": false
|
| 760 |
+
},
|
| 761 |
+
"attributes": {}
|
| 762 |
+
}
|
| 763 |
+
},
|
| 764 |
+
"total_flos": 643408330752000.0,
|
| 765 |
+
"train_batch_size": 32,
|
| 766 |
+
"trial_name": null,
|
| 767 |
+
"trial_params": null
|
| 768 |
+
}
|
checkpoint-33000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e446b19bfdd079c96f93f25aba6c168e7eaf20eb6abb93593c603320e1446ee9
|
| 3 |
+
size 5432
|