Upload 13 files
Browse files- added_tokens.json +4 -0
- all_results.json +15 -0
- config.json +38 -0
- eval_results.json +10 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +25 -0
- tokenizer.json +0 -0
- tokenizer_config.json +34 -0
- train_results.json +8 -0
- trainer_state.json +541 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<MASK>": 50258,
|
| 3 |
+
"<PAD>": 50257
|
| 4 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_accuracy": 0.791762140185717,
|
| 4 |
+
"eval_loss": 1.2498760223388672,
|
| 5 |
+
"eval_runtime": 27.7085,
|
| 6 |
+
"eval_samples": 1987,
|
| 7 |
+
"eval_samples_per_second": 71.711,
|
| 8 |
+
"eval_steps_per_second": 3.609,
|
| 9 |
+
"perplexity": 3.4899102597284046,
|
| 10 |
+
"train_loss": 0.9664699619099245,
|
| 11 |
+
"train_runtime": 20866.4149,
|
| 12 |
+
"train_samples": 9478,
|
| 13 |
+
"train_samples_per_second": 22.711,
|
| 14 |
+
"train_steps_per_second": 0.283
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/DialoGPT-small",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 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 |
+
"conversational": {
|
| 31 |
+
"max_length": 1000
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.24.0",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50259
|
| 38 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_accuracy": 0.791762140185717,
|
| 4 |
+
"eval_loss": 1.2498760223388672,
|
| 5 |
+
"eval_runtime": 27.7085,
|
| 6 |
+
"eval_samples": 1987,
|
| 7 |
+
"eval_samples_per_second": 71.711,
|
| 8 |
+
"eval_steps_per_second": 3.609,
|
| 9 |
+
"perplexity": 3.4899102597284046
|
| 10 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c05c0f7dc4208ccc41f4c50e6814f476091d85c84c9ce031c1e8ce5ec5d77c6
|
| 3 |
+
size 510404157
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"mask_token": "<MASK>",
|
| 17 |
+
"pad_token": "<PAD>",
|
| 18 |
+
"unk_token": {
|
| 19 |
+
"content": "<|endoftext|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": true,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
}
|
| 25 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"eos_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"errors": "replace",
|
| 21 |
+
"model_max_length": 1024,
|
| 22 |
+
"name_or_path": "microsoft/DialoGPT-small",
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"special_tokens_map_file": null,
|
| 25 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"__type": "AddedToken",
|
| 28 |
+
"content": "<|endoftext|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 0.9664699619099245,
|
| 4 |
+
"train_runtime": 20866.4149,
|
| 5 |
+
"train_samples": 9478,
|
| 6 |
+
"train_samples_per_second": 22.711,
|
| 7 |
+
"train_steps_per_second": 0.283
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,541 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.9957805907173,
|
| 5 |
+
"global_step": 5900,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.7731608395748838,
|
| 13 |
+
"eval_loss": 1.273674726486206,
|
| 14 |
+
"eval_runtime": 27.8473,
|
| 15 |
+
"eval_samples_per_second": 71.353,
|
| 16 |
+
"eval_steps_per_second": 3.591,
|
| 17 |
+
"step": 118
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.0,
|
| 21 |
+
"eval_accuracy": 0.7844064852916506,
|
| 22 |
+
"eval_loss": 1.149436354637146,
|
| 23 |
+
"eval_runtime": 27.7157,
|
| 24 |
+
"eval_samples_per_second": 71.692,
|
| 25 |
+
"eval_steps_per_second": 3.608,
|
| 26 |
+
"step": 236
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 3.0,
|
| 30 |
+
"eval_accuracy": 0.7886655417073725,
|
| 31 |
+
"eval_loss": 1.115924596786499,
|
| 32 |
+
"eval_runtime": 27.7526,
|
| 33 |
+
"eval_samples_per_second": 71.597,
|
| 34 |
+
"eval_steps_per_second": 3.603,
|
| 35 |
+
"step": 354
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 4.0,
|
| 39 |
+
"eval_accuracy": 0.7905562627668078,
|
| 40 |
+
"eval_loss": 1.0954861640930176,
|
| 41 |
+
"eval_runtime": 27.7193,
|
| 42 |
+
"eval_samples_per_second": 71.683,
|
| 43 |
+
"eval_steps_per_second": 3.608,
|
| 44 |
+
"step": 472
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.24,
|
| 48 |
+
"learning_rate": 4.5762711864406784e-05,
|
| 49 |
+
"loss": 3.3542,
|
| 50 |
+
"step": 500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 5.0,
|
| 54 |
+
"eval_accuracy": 0.7918075332800458,
|
| 55 |
+
"eval_loss": 1.0870832204818726,
|
| 56 |
+
"eval_runtime": 27.7224,
|
| 57 |
+
"eval_samples_per_second": 71.675,
|
| 58 |
+
"eval_steps_per_second": 3.607,
|
| 59 |
+
"step": 590
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 6.0,
|
| 63 |
+
"eval_accuracy": 0.7928476272240149,
|
| 64 |
+
"eval_loss": 1.0806066989898682,
|
| 65 |
+
"eval_runtime": 27.72,
|
| 66 |
+
"eval_samples_per_second": 71.681,
|
| 67 |
+
"eval_steps_per_second": 3.607,
|
| 68 |
+
"step": 708
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 7.0,
|
| 72 |
+
"eval_accuracy": 0.7931219594027847,
|
| 73 |
+
"eval_loss": 1.0786826610565186,
|
| 74 |
+
"eval_runtime": 27.7079,
|
| 75 |
+
"eval_samples_per_second": 71.712,
|
| 76 |
+
"eval_steps_per_second": 3.609,
|
| 77 |
+
"step": 826
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 8.0,
|
| 81 |
+
"eval_accuracy": 0.7938285127840768,
|
| 82 |
+
"eval_loss": 1.0748920440673828,
|
| 83 |
+
"eval_runtime": 27.7168,
|
| 84 |
+
"eval_samples_per_second": 71.689,
|
| 85 |
+
"eval_steps_per_second": 3.608,
|
| 86 |
+
"step": 944
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 8.47,
|
| 90 |
+
"learning_rate": 4.152542372881356e-05,
|
| 91 |
+
"loss": 1.0048,
|
| 92 |
+
"step": 1000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 9.0,
|
| 96 |
+
"eval_accuracy": 0.7937554891105914,
|
| 97 |
+
"eval_loss": 1.0768133401870728,
|
| 98 |
+
"eval_runtime": 27.8358,
|
| 99 |
+
"eval_samples_per_second": 71.383,
|
| 100 |
+
"eval_steps_per_second": 3.592,
|
| 101 |
+
"step": 1062
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 10.0,
|
| 105 |
+
"eval_accuracy": 0.793783119689748,
|
| 106 |
+
"eval_loss": 1.076497197151184,
|
| 107 |
+
"eval_runtime": 27.7645,
|
| 108 |
+
"eval_samples_per_second": 71.566,
|
| 109 |
+
"eval_steps_per_second": 3.602,
|
| 110 |
+
"step": 1180
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 11.0,
|
| 114 |
+
"eval_accuracy": 0.7941719214107384,
|
| 115 |
+
"eval_loss": 1.0760843753814697,
|
| 116 |
+
"eval_runtime": 28.0837,
|
| 117 |
+
"eval_samples_per_second": 70.753,
|
| 118 |
+
"eval_steps_per_second": 3.561,
|
| 119 |
+
"step": 1298
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 12.0,
|
| 123 |
+
"eval_accuracy": 0.7943712563032259,
|
| 124 |
+
"eval_loss": 1.078471064567566,
|
| 125 |
+
"eval_runtime": 27.7304,
|
| 126 |
+
"eval_samples_per_second": 71.654,
|
| 127 |
+
"eval_steps_per_second": 3.606,
|
| 128 |
+
"step": 1416
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 12.71,
|
| 132 |
+
"learning_rate": 3.728813559322034e-05,
|
| 133 |
+
"loss": 0.9221,
|
| 134 |
+
"step": 1500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 13.0,
|
| 138 |
+
"eval_accuracy": 0.7942034992154889,
|
| 139 |
+
"eval_loss": 1.0854936838150024,
|
| 140 |
+
"eval_runtime": 27.702,
|
| 141 |
+
"eval_samples_per_second": 71.728,
|
| 142 |
+
"eval_steps_per_second": 3.61,
|
| 143 |
+
"step": 1534
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 14.0,
|
| 147 |
+
"eval_accuracy": 0.7943969132695856,
|
| 148 |
+
"eval_loss": 1.0861722230911255,
|
| 149 |
+
"eval_runtime": 27.7005,
|
| 150 |
+
"eval_samples_per_second": 71.731,
|
| 151 |
+
"eval_steps_per_second": 3.61,
|
| 152 |
+
"step": 1652
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 15.0,
|
| 156 |
+
"eval_accuracy": 0.7947047968659029,
|
| 157 |
+
"eval_loss": 1.0891741514205933,
|
| 158 |
+
"eval_runtime": 27.7017,
|
| 159 |
+
"eval_samples_per_second": 71.729,
|
| 160 |
+
"eval_steps_per_second": 3.61,
|
| 161 |
+
"step": 1770
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 16.0,
|
| 165 |
+
"eval_accuracy": 0.7944600688790866,
|
| 166 |
+
"eval_loss": 1.0921040773391724,
|
| 167 |
+
"eval_runtime": 27.6967,
|
| 168 |
+
"eval_samples_per_second": 71.741,
|
| 169 |
+
"eval_steps_per_second": 3.611,
|
| 170 |
+
"step": 1888
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 16.95,
|
| 174 |
+
"learning_rate": 3.305084745762712e-05,
|
| 175 |
+
"loss": 0.8534,
|
| 176 |
+
"step": 2000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 17.0,
|
| 180 |
+
"eval_accuracy": 0.7944245438487423,
|
| 181 |
+
"eval_loss": 1.0993601083755493,
|
| 182 |
+
"eval_runtime": 27.7053,
|
| 183 |
+
"eval_samples_per_second": 71.719,
|
| 184 |
+
"eval_steps_per_second": 3.609,
|
| 185 |
+
"step": 2006
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 18.0,
|
| 189 |
+
"eval_accuracy": 0.7944719105558681,
|
| 190 |
+
"eval_loss": 1.100709319114685,
|
| 191 |
+
"eval_runtime": 27.7072,
|
| 192 |
+
"eval_samples_per_second": 71.714,
|
| 193 |
+
"eval_steps_per_second": 3.609,
|
| 194 |
+
"step": 2124
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 19.0,
|
| 198 |
+
"eval_accuracy": 0.7942567867610053,
|
| 199 |
+
"eval_loss": 1.1095192432403564,
|
| 200 |
+
"eval_runtime": 27.6924,
|
| 201 |
+
"eval_samples_per_second": 71.753,
|
| 202 |
+
"eval_steps_per_second": 3.611,
|
| 203 |
+
"step": 2242
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 20.0,
|
| 207 |
+
"eval_accuracy": 0.7939962698718138,
|
| 208 |
+
"eval_loss": 1.1117533445358276,
|
| 209 |
+
"eval_runtime": 27.706,
|
| 210 |
+
"eval_samples_per_second": 71.717,
|
| 211 |
+
"eval_steps_per_second": 3.609,
|
| 212 |
+
"step": 2360
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 21.0,
|
| 216 |
+
"eval_accuracy": 0.7940456101917365,
|
| 217 |
+
"eval_loss": 1.1208868026733398,
|
| 218 |
+
"eval_runtime": 27.7121,
|
| 219 |
+
"eval_samples_per_second": 71.702,
|
| 220 |
+
"eval_steps_per_second": 3.609,
|
| 221 |
+
"step": 2478
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 21.19,
|
| 225 |
+
"learning_rate": 2.88135593220339e-05,
|
| 226 |
+
"loss": 0.7959,
|
| 227 |
+
"step": 2500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 22.0,
|
| 231 |
+
"eval_accuracy": 0.7939271934239222,
|
| 232 |
+
"eval_loss": 1.1249679327011108,
|
| 233 |
+
"eval_runtime": 27.7085,
|
| 234 |
+
"eval_samples_per_second": 71.711,
|
| 235 |
+
"eval_steps_per_second": 3.609,
|
| 236 |
+
"step": 2596
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 23.0,
|
| 240 |
+
"eval_accuracy": 0.7937811460769512,
|
| 241 |
+
"eval_loss": 1.1323717832565308,
|
| 242 |
+
"eval_runtime": 27.7079,
|
| 243 |
+
"eval_samples_per_second": 71.712,
|
| 244 |
+
"eval_steps_per_second": 3.609,
|
| 245 |
+
"step": 2714
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 24.0,
|
| 249 |
+
"eval_accuracy": 0.7939074572959531,
|
| 250 |
+
"eval_loss": 1.136080026626587,
|
| 251 |
+
"eval_runtime": 27.704,
|
| 252 |
+
"eval_samples_per_second": 71.723,
|
| 253 |
+
"eval_steps_per_second": 3.61,
|
| 254 |
+
"step": 2832
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 25.0,
|
| 258 |
+
"eval_accuracy": 0.7935601014436977,
|
| 259 |
+
"eval_loss": 1.1441864967346191,
|
| 260 |
+
"eval_runtime": 27.6972,
|
| 261 |
+
"eval_samples_per_second": 71.74,
|
| 262 |
+
"eval_steps_per_second": 3.61,
|
| 263 |
+
"step": 2950
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 25.42,
|
| 267 |
+
"learning_rate": 2.457627118644068e-05,
|
| 268 |
+
"loss": 0.7458,
|
| 269 |
+
"step": 3000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 26.0,
|
| 273 |
+
"eval_accuracy": 0.7934377374502897,
|
| 274 |
+
"eval_loss": 1.1540361642837524,
|
| 275 |
+
"eval_runtime": 27.7164,
|
| 276 |
+
"eval_samples_per_second": 71.69,
|
| 277 |
+
"eval_steps_per_second": 3.608,
|
| 278 |
+
"step": 3068
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 27.0,
|
| 282 |
+
"eval_accuracy": 0.7932680067497557,
|
| 283 |
+
"eval_loss": 1.1579915285110474,
|
| 284 |
+
"eval_runtime": 27.7102,
|
| 285 |
+
"eval_samples_per_second": 71.706,
|
| 286 |
+
"eval_steps_per_second": 3.609,
|
| 287 |
+
"step": 3186
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 28.0,
|
| 291 |
+
"eval_accuracy": 0.793429842999102,
|
| 292 |
+
"eval_loss": 1.1653059720993042,
|
| 293 |
+
"eval_runtime": 27.7095,
|
| 294 |
+
"eval_samples_per_second": 71.708,
|
| 295 |
+
"eval_steps_per_second": 3.609,
|
| 296 |
+
"step": 3304
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 29.0,
|
| 300 |
+
"eval_accuracy": 0.7931002496620189,
|
| 301 |
+
"eval_loss": 1.1742562055587769,
|
| 302 |
+
"eval_runtime": 27.7109,
|
| 303 |
+
"eval_samples_per_second": 71.705,
|
| 304 |
+
"eval_steps_per_second": 3.609,
|
| 305 |
+
"step": 3422
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 29.66,
|
| 309 |
+
"learning_rate": 2.033898305084746e-05,
|
| 310 |
+
"loss": 0.7034,
|
| 311 |
+
"step": 3500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 30.0,
|
| 315 |
+
"eval_accuracy": 0.7932344553322084,
|
| 316 |
+
"eval_loss": 1.1726936101913452,
|
| 317 |
+
"eval_runtime": 27.7127,
|
| 318 |
+
"eval_samples_per_second": 71.7,
|
| 319 |
+
"eval_steps_per_second": 3.608,
|
| 320 |
+
"step": 3540
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 31.0,
|
| 324 |
+
"eval_accuracy": 0.7930153843117519,
|
| 325 |
+
"eval_loss": 1.1811208724975586,
|
| 326 |
+
"eval_runtime": 27.7003,
|
| 327 |
+
"eval_samples_per_second": 71.732,
|
| 328 |
+
"eval_steps_per_second": 3.61,
|
| 329 |
+
"step": 3658
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 32.0,
|
| 333 |
+
"eval_accuracy": 0.7930114370861581,
|
| 334 |
+
"eval_loss": 1.1879879236221313,
|
| 335 |
+
"eval_runtime": 27.7125,
|
| 336 |
+
"eval_samples_per_second": 71.701,
|
| 337 |
+
"eval_steps_per_second": 3.608,
|
| 338 |
+
"step": 3776
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 33.0,
|
| 342 |
+
"eval_accuracy": 0.7927528938097634,
|
| 343 |
+
"eval_loss": 1.1952810287475586,
|
| 344 |
+
"eval_runtime": 27.7028,
|
| 345 |
+
"eval_samples_per_second": 71.726,
|
| 346 |
+
"eval_steps_per_second": 3.61,
|
| 347 |
+
"step": 3894
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 33.89,
|
| 351 |
+
"learning_rate": 1.6101694915254237e-05,
|
| 352 |
+
"loss": 0.6688,
|
| 353 |
+
"step": 4000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 34.0,
|
| 357 |
+
"eval_accuracy": 0.7928298647088428,
|
| 358 |
+
"eval_loss": 1.200770378112793,
|
| 359 |
+
"eval_runtime": 27.7087,
|
| 360 |
+
"eval_samples_per_second": 71.71,
|
| 361 |
+
"eval_steps_per_second": 3.609,
|
| 362 |
+
"step": 4012
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 35.0,
|
| 366 |
+
"eval_accuracy": 0.7926384242675429,
|
| 367 |
+
"eval_loss": 1.205856442451477,
|
| 368 |
+
"eval_runtime": 27.7159,
|
| 369 |
+
"eval_samples_per_second": 71.692,
|
| 370 |
+
"eval_steps_per_second": 3.608,
|
| 371 |
+
"step": 4130
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 36.0,
|
| 375 |
+
"eval_accuracy": 0.7925101394357441,
|
| 376 |
+
"eval_loss": 1.2133612632751465,
|
| 377 |
+
"eval_runtime": 27.7077,
|
| 378 |
+
"eval_samples_per_second": 71.713,
|
| 379 |
+
"eval_steps_per_second": 3.609,
|
| 380 |
+
"step": 4248
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 37.0,
|
| 384 |
+
"eval_accuracy": 0.7922279128057866,
|
| 385 |
+
"eval_loss": 1.2220430374145508,
|
| 386 |
+
"eval_runtime": 27.7023,
|
| 387 |
+
"eval_samples_per_second": 71.727,
|
| 388 |
+
"eval_steps_per_second": 3.61,
|
| 389 |
+
"step": 4366
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 38.0,
|
| 393 |
+
"eval_accuracy": 0.7922910684152876,
|
| 394 |
+
"eval_loss": 1.2201595306396484,
|
| 395 |
+
"eval_runtime": 27.6967,
|
| 396 |
+
"eval_samples_per_second": 71.741,
|
| 397 |
+
"eval_steps_per_second": 3.611,
|
| 398 |
+
"step": 4484
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 38.14,
|
| 402 |
+
"learning_rate": 1.1864406779661018e-05,
|
| 403 |
+
"loss": 0.6427,
|
| 404 |
+
"step": 4500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 39.0,
|
| 408 |
+
"eval_accuracy": 0.7922890948024907,
|
| 409 |
+
"eval_loss": 1.2266799211502075,
|
| 410 |
+
"eval_runtime": 27.7206,
|
| 411 |
+
"eval_samples_per_second": 71.68,
|
| 412 |
+
"eval_steps_per_second": 3.607,
|
| 413 |
+
"step": 4602
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 40.0,
|
| 417 |
+
"eval_accuracy": 0.7919200292094694,
|
| 418 |
+
"eval_loss": 1.2350112199783325,
|
| 419 |
+
"eval_runtime": 27.709,
|
| 420 |
+
"eval_samples_per_second": 71.709,
|
| 421 |
+
"eval_steps_per_second": 3.609,
|
| 422 |
+
"step": 4720
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 41.0,
|
| 426 |
+
"eval_accuracy": 0.792095680748394,
|
| 427 |
+
"eval_loss": 1.23201584815979,
|
| 428 |
+
"eval_runtime": 27.6985,
|
| 429 |
+
"eval_samples_per_second": 71.737,
|
| 430 |
+
"eval_steps_per_second": 3.61,
|
| 431 |
+
"step": 4838
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 42.0,
|
| 435 |
+
"eval_accuracy": 0.791866741663953,
|
| 436 |
+
"eval_loss": 1.2356910705566406,
|
| 437 |
+
"eval_runtime": 27.7184,
|
| 438 |
+
"eval_samples_per_second": 71.685,
|
| 439 |
+
"eval_steps_per_second": 3.608,
|
| 440 |
+
"step": 4956
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 42.37,
|
| 444 |
+
"learning_rate": 7.627118644067798e-06,
|
| 445 |
+
"loss": 0.6219,
|
| 446 |
+
"step": 5000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 43.0,
|
| 450 |
+
"eval_accuracy": 0.791991079270158,
|
| 451 |
+
"eval_loss": 1.23865807056427,
|
| 452 |
+
"eval_runtime": 27.7193,
|
| 453 |
+
"eval_samples_per_second": 71.683,
|
| 454 |
+
"eval_steps_per_second": 3.608,
|
| 455 |
+
"step": 5074
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 44.0,
|
| 459 |
+
"eval_accuracy": 0.7919575278526106,
|
| 460 |
+
"eval_loss": 1.2408578395843506,
|
| 461 |
+
"eval_runtime": 27.719,
|
| 462 |
+
"eval_samples_per_second": 71.684,
|
| 463 |
+
"eval_steps_per_second": 3.608,
|
| 464 |
+
"step": 5192
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 45.0,
|
| 468 |
+
"eval_accuracy": 0.791886477791922,
|
| 469 |
+
"eval_loss": 1.244328260421753,
|
| 470 |
+
"eval_runtime": 27.7249,
|
| 471 |
+
"eval_samples_per_second": 71.668,
|
| 472 |
+
"eval_steps_per_second": 3.607,
|
| 473 |
+
"step": 5310
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 46.0,
|
| 477 |
+
"eval_accuracy": 0.7917897707648737,
|
| 478 |
+
"eval_loss": 1.2477593421936035,
|
| 479 |
+
"eval_runtime": 27.6986,
|
| 480 |
+
"eval_samples_per_second": 71.736,
|
| 481 |
+
"eval_steps_per_second": 3.61,
|
| 482 |
+
"step": 5428
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 46.61,
|
| 486 |
+
"learning_rate": 3.3898305084745763e-06,
|
| 487 |
+
"loss": 0.6097,
|
| 488 |
+
"step": 5500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 47.0,
|
| 492 |
+
"eval_accuracy": 0.7917739818624984,
|
| 493 |
+
"eval_loss": 1.2487553358078003,
|
| 494 |
+
"eval_runtime": 27.7426,
|
| 495 |
+
"eval_samples_per_second": 71.623,
|
| 496 |
+
"eval_steps_per_second": 3.605,
|
| 497 |
+
"step": 5546
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 48.0,
|
| 501 |
+
"eval_accuracy": 0.7917522721217325,
|
| 502 |
+
"eval_loss": 1.2487850189208984,
|
| 503 |
+
"eval_runtime": 27.7184,
|
| 504 |
+
"eval_samples_per_second": 71.685,
|
| 505 |
+
"eval_steps_per_second": 3.608,
|
| 506 |
+
"step": 5664
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 49.0,
|
| 510 |
+
"eval_accuracy": 0.7917424040577479,
|
| 511 |
+
"eval_loss": 1.2495468854904175,
|
| 512 |
+
"eval_runtime": 27.7228,
|
| 513 |
+
"eval_samples_per_second": 71.674,
|
| 514 |
+
"eval_steps_per_second": 3.607,
|
| 515 |
+
"step": 5782
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 50.0,
|
| 519 |
+
"eval_accuracy": 0.791762140185717,
|
| 520 |
+
"eval_loss": 1.2498760223388672,
|
| 521 |
+
"eval_runtime": 27.7268,
|
| 522 |
+
"eval_samples_per_second": 71.664,
|
| 523 |
+
"eval_steps_per_second": 3.607,
|
| 524 |
+
"step": 5900
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 50.0,
|
| 528 |
+
"step": 5900,
|
| 529 |
+
"total_flos": 6.1908182433792e+16,
|
| 530 |
+
"train_loss": 0.9664699619099245,
|
| 531 |
+
"train_runtime": 20866.4149,
|
| 532 |
+
"train_samples_per_second": 22.711,
|
| 533 |
+
"train_steps_per_second": 0.283
|
| 534 |
+
}
|
| 535 |
+
],
|
| 536 |
+
"max_steps": 5900,
|
| 537 |
+
"num_train_epochs": 50,
|
| 538 |
+
"total_flos": 6.1908182433792e+16,
|
| 539 |
+
"trial_name": null,
|
| 540 |
+
"trial_params": null
|
| 541 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24e2dd9b341b4a3957a649463d27424b2198bfac1a4b65904a90b5daa586e451
|
| 3 |
+
size 3451
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|