Upload 13 files
Browse files- added_tokens.json +7 -0
- all_results.json +8 -0
- config.json +41 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +36 -0
- tokenizer.json +0 -0
- tokenizer_config.json +68 -0
- train_results.json +8 -0
- trainer_state.json +358 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 50261,
|
| 3 |
+
"<|ASSISTANT|>": 50259,
|
| 4 |
+
"<|End|>": 50258,
|
| 5 |
+
"<|USER|>": 50260,
|
| 6 |
+
"[PAD]": 50257
|
| 7 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.19717555102511977,
|
| 4 |
+
"train_runtime": 3239.6632,
|
| 5 |
+
"train_samples": 1519,
|
| 6 |
+
"train_samples_per_second": 4.689,
|
| 7 |
+
"train_steps_per_second": 0.522
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "CreitinGameplays/elisa-chan-gpt2-medium",
|
| 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": 1024,
|
| 16 |
+
"n_head": 16,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 24,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"n_special": 0,
|
| 21 |
+
"predict_special_tokens": true,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.38.0.dev0",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50262
|
| 41 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.38.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9040b992a0cbaf8bf990ea4f82cb8ff641087e9d95a28dd2c28e8729b0ef170e
|
| 3 |
+
size 1419343360
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|ASSISTANT|>",
|
| 4 |
+
"<|USER|>",
|
| 5 |
+
"<|End|>",
|
| 6 |
+
"<mask>"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<|endoftext|>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "<|End|>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<|endoftext|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"50257": {
|
| 14 |
+
"content": "[PAD]",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"50258": {
|
| 22 |
+
"content": "<|End|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"50259": {
|
| 30 |
+
"content": "<|ASSISTANT|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"50260": {
|
| 38 |
+
"content": "<|USER|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"50261": {
|
| 46 |
+
"content": "<mask>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
}
|
| 53 |
+
},
|
| 54 |
+
"additional_special_tokens": [
|
| 55 |
+
"<|ASSISTANT|>",
|
| 56 |
+
"<|USER|>",
|
| 57 |
+
"<|End|>",
|
| 58 |
+
"<mask>"
|
| 59 |
+
],
|
| 60 |
+
"bos_token": "<|endoftext|>",
|
| 61 |
+
"clean_up_tokenization_spaces": true,
|
| 62 |
+
"eos_token": "<|End|>",
|
| 63 |
+
"errors": "replace",
|
| 64 |
+
"model_max_length": 1024,
|
| 65 |
+
"pad_token": "[PAD]",
|
| 66 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 67 |
+
"unk_token": "<|endoftext|>"
|
| 68 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.19717555102511977,
|
| 4 |
+
"train_runtime": 3239.6632,
|
| 5 |
+
"train_samples": 1519,
|
| 6 |
+
"train_samples_per_second": 4.689,
|
| 7 |
+
"train_steps_per_second": 0.522
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,358 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 6.297296047210693,
|
| 3 |
+
"best_model_checkpoint": "./output_dir/checkpoint-169",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 50.0,
|
| 6 |
+
"global_step": 1690,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.3,
|
| 13 |
+
"learning_rate": 9.70414201183432e-05,
|
| 14 |
+
"loss": 1.5791,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.59,
|
| 19 |
+
"learning_rate": 9.408284023668639e-05,
|
| 20 |
+
"loss": 0.6789,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.89,
|
| 25 |
+
"learning_rate": 9.112426035502959e-05,
|
| 26 |
+
"loss": 0.5388,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.0,
|
| 31 |
+
"eval_bleu-1": 20.7834,
|
| 32 |
+
"eval_bleu-2": 4.6208,
|
| 33 |
+
"eval_bleu-3": 2.9929,
|
| 34 |
+
"eval_bleu-4": 2.6572,
|
| 35 |
+
"eval_gen_len": 178.3333,
|
| 36 |
+
"eval_loss": 6.297296047210693,
|
| 37 |
+
"eval_runtime": 43.3624,
|
| 38 |
+
"eval_samples_per_second": 0.277,
|
| 39 |
+
"eval_steps_per_second": 0.277,
|
| 40 |
+
"step": 169
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.18,
|
| 44 |
+
"learning_rate": 8.816568047337278e-05,
|
| 45 |
+
"loss": 0.3897,
|
| 46 |
+
"step": 200
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.48,
|
| 50 |
+
"learning_rate": 8.520710059171599e-05,
|
| 51 |
+
"loss": 0.3148,
|
| 52 |
+
"step": 250
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.78,
|
| 56 |
+
"learning_rate": 8.224852071005918e-05,
|
| 57 |
+
"loss": 0.2681,
|
| 58 |
+
"step": 300
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.0,
|
| 62 |
+
"eval_bleu-1": 21.2042,
|
| 63 |
+
"eval_bleu-2": 4.6329,
|
| 64 |
+
"eval_bleu-3": 2.8663,
|
| 65 |
+
"eval_bleu-4": 2.5449,
|
| 66 |
+
"eval_gen_len": 178.3333,
|
| 67 |
+
"eval_loss": 7.237356662750244,
|
| 68 |
+
"eval_runtime": 42.1638,
|
| 69 |
+
"eval_samples_per_second": 0.285,
|
| 70 |
+
"eval_steps_per_second": 0.285,
|
| 71 |
+
"step": 338
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.07,
|
| 75 |
+
"learning_rate": 7.928994082840237e-05,
|
| 76 |
+
"loss": 0.2515,
|
| 77 |
+
"step": 350
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 2.37,
|
| 81 |
+
"learning_rate": 7.633136094674557e-05,
|
| 82 |
+
"loss": 0.17,
|
| 83 |
+
"step": 400
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.66,
|
| 87 |
+
"learning_rate": 7.337278106508876e-05,
|
| 88 |
+
"loss": 0.1873,
|
| 89 |
+
"step": 450
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.96,
|
| 93 |
+
"learning_rate": 7.041420118343195e-05,
|
| 94 |
+
"loss": 0.1854,
|
| 95 |
+
"step": 500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.0,
|
| 99 |
+
"eval_bleu-1": 20.1899,
|
| 100 |
+
"eval_bleu-2": 4.4735,
|
| 101 |
+
"eval_bleu-3": 2.9681,
|
| 102 |
+
"eval_bleu-4": 2.5725,
|
| 103 |
+
"eval_gen_len": 178.3333,
|
| 104 |
+
"eval_loss": 7.7388596534729,
|
| 105 |
+
"eval_runtime": 43.0592,
|
| 106 |
+
"eval_samples_per_second": 0.279,
|
| 107 |
+
"eval_steps_per_second": 0.279,
|
| 108 |
+
"step": 507
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.25,
|
| 112 |
+
"learning_rate": 6.745562130177515e-05,
|
| 113 |
+
"loss": 0.1395,
|
| 114 |
+
"step": 550
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.55,
|
| 118 |
+
"learning_rate": 6.449704142011834e-05,
|
| 119 |
+
"loss": 0.1228,
|
| 120 |
+
"step": 600
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.85,
|
| 124 |
+
"learning_rate": 6.153846153846155e-05,
|
| 125 |
+
"loss": 0.1209,
|
| 126 |
+
"step": 650
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 4.0,
|
| 130 |
+
"eval_bleu-1": 22.4915,
|
| 131 |
+
"eval_bleu-2": 5.2106,
|
| 132 |
+
"eval_bleu-3": 3.0103,
|
| 133 |
+
"eval_bleu-4": 2.4905,
|
| 134 |
+
"eval_gen_len": 178.3333,
|
| 135 |
+
"eval_loss": 8.396303176879883,
|
| 136 |
+
"eval_runtime": 42.158,
|
| 137 |
+
"eval_samples_per_second": 0.285,
|
| 138 |
+
"eval_steps_per_second": 0.285,
|
| 139 |
+
"step": 676
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.14,
|
| 143 |
+
"learning_rate": 5.863905325443787e-05,
|
| 144 |
+
"loss": 0.1079,
|
| 145 |
+
"step": 700
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.44,
|
| 149 |
+
"learning_rate": 5.568047337278107e-05,
|
| 150 |
+
"loss": 0.1073,
|
| 151 |
+
"step": 750
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 4.73,
|
| 155 |
+
"learning_rate": 5.272189349112427e-05,
|
| 156 |
+
"loss": 0.0988,
|
| 157 |
+
"step": 800
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 5.0,
|
| 161 |
+
"eval_bleu-1": 20.999,
|
| 162 |
+
"eval_bleu-2": 5.0478,
|
| 163 |
+
"eval_bleu-3": 3.0062,
|
| 164 |
+
"eval_bleu-4": 2.5449,
|
| 165 |
+
"eval_gen_len": 178.3333,
|
| 166 |
+
"eval_loss": 8.886907577514648,
|
| 167 |
+
"eval_runtime": 43.2859,
|
| 168 |
+
"eval_samples_per_second": 0.277,
|
| 169 |
+
"eval_steps_per_second": 0.277,
|
| 170 |
+
"step": 845
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 5.03,
|
| 174 |
+
"learning_rate": 4.976331360946746e-05,
|
| 175 |
+
"loss": 0.0991,
|
| 176 |
+
"step": 850
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 5.33,
|
| 180 |
+
"learning_rate": 4.6804733727810654e-05,
|
| 181 |
+
"loss": 0.0864,
|
| 182 |
+
"step": 900
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 5.62,
|
| 186 |
+
"learning_rate": 4.384615384615385e-05,
|
| 187 |
+
"loss": 0.0882,
|
| 188 |
+
"step": 950
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.92,
|
| 192 |
+
"learning_rate": 4.088757396449705e-05,
|
| 193 |
+
"loss": 0.0883,
|
| 194 |
+
"step": 1000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.0,
|
| 198 |
+
"eval_bleu-1": 22.8262,
|
| 199 |
+
"eval_bleu-2": 4.6692,
|
| 200 |
+
"eval_bleu-3": 2.9419,
|
| 201 |
+
"eval_bleu-4": 2.4905,
|
| 202 |
+
"eval_gen_len": 178.3333,
|
| 203 |
+
"eval_loss": 9.158414840698242,
|
| 204 |
+
"eval_runtime": 42.9666,
|
| 205 |
+
"eval_samples_per_second": 0.279,
|
| 206 |
+
"eval_steps_per_second": 0.279,
|
| 207 |
+
"step": 1014
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.21,
|
| 211 |
+
"learning_rate": 3.792899408284024e-05,
|
| 212 |
+
"loss": 0.0856,
|
| 213 |
+
"step": 1050
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 6.51,
|
| 217 |
+
"learning_rate": 3.4970414201183435e-05,
|
| 218 |
+
"loss": 0.0786,
|
| 219 |
+
"step": 1100
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 6.8,
|
| 223 |
+
"learning_rate": 3.201183431952663e-05,
|
| 224 |
+
"loss": 0.0806,
|
| 225 |
+
"step": 1150
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 7.0,
|
| 229 |
+
"eval_bleu-1": 22.2906,
|
| 230 |
+
"eval_bleu-2": 4.6692,
|
| 231 |
+
"eval_bleu-3": 2.9419,
|
| 232 |
+
"eval_bleu-4": 2.4905,
|
| 233 |
+
"eval_gen_len": 178.3333,
|
| 234 |
+
"eval_loss": 9.391822814941406,
|
| 235 |
+
"eval_runtime": 42.3982,
|
| 236 |
+
"eval_samples_per_second": 0.283,
|
| 237 |
+
"eval_steps_per_second": 0.283,
|
| 238 |
+
"step": 1183
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 7.1,
|
| 242 |
+
"learning_rate": 2.9053254437869826e-05,
|
| 243 |
+
"loss": 0.0786,
|
| 244 |
+
"step": 1200
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 7.4,
|
| 248 |
+
"learning_rate": 2.6094674556213016e-05,
|
| 249 |
+
"loss": 0.0765,
|
| 250 |
+
"step": 1250
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 7.69,
|
| 254 |
+
"learning_rate": 2.3136094674556213e-05,
|
| 255 |
+
"loss": 0.0747,
|
| 256 |
+
"step": 1300
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 7.99,
|
| 260 |
+
"learning_rate": 2.017751479289941e-05,
|
| 261 |
+
"loss": 0.0787,
|
| 262 |
+
"step": 1350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 8.0,
|
| 266 |
+
"eval_bleu-1": 23.8184,
|
| 267 |
+
"eval_bleu-2": 5.1303,
|
| 268 |
+
"eval_bleu-3": 2.9739,
|
| 269 |
+
"eval_bleu-4": 2.6574,
|
| 270 |
+
"eval_gen_len": 178.3333,
|
| 271 |
+
"eval_loss": 9.662525177001953,
|
| 272 |
+
"eval_runtime": 42.8982,
|
| 273 |
+
"eval_samples_per_second": 0.28,
|
| 274 |
+
"eval_steps_per_second": 0.28,
|
| 275 |
+
"step": 1352
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 8.28,
|
| 279 |
+
"learning_rate": 1.7218934911242603e-05,
|
| 280 |
+
"loss": 0.0734,
|
| 281 |
+
"step": 1400
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 8.58,
|
| 285 |
+
"learning_rate": 1.42603550295858e-05,
|
| 286 |
+
"loss": 0.0744,
|
| 287 |
+
"step": 1450
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 8.88,
|
| 291 |
+
"learning_rate": 1.1301775147928994e-05,
|
| 292 |
+
"loss": 0.0714,
|
| 293 |
+
"step": 1500
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 9.0,
|
| 297 |
+
"eval_bleu-1": 23.7162,
|
| 298 |
+
"eval_bleu-2": 5.522,
|
| 299 |
+
"eval_bleu-3": 3.0388,
|
| 300 |
+
"eval_bleu-4": 2.7154,
|
| 301 |
+
"eval_gen_len": 178.3333,
|
| 302 |
+
"eval_loss": 9.930649757385254,
|
| 303 |
+
"eval_runtime": 45.1011,
|
| 304 |
+
"eval_samples_per_second": 0.266,
|
| 305 |
+
"eval_steps_per_second": 0.266,
|
| 306 |
+
"step": 1521
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 9.17,
|
| 310 |
+
"learning_rate": 8.34319526627219e-06,
|
| 311 |
+
"loss": 0.0724,
|
| 312 |
+
"step": 1550
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 9.47,
|
| 316 |
+
"learning_rate": 5.3846153846153855e-06,
|
| 317 |
+
"loss": 0.0704,
|
| 318 |
+
"step": 1600
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 9.76,
|
| 322 |
+
"learning_rate": 2.42603550295858e-06,
|
| 323 |
+
"loss": 0.0706,
|
| 324 |
+
"step": 1650
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 10.0,
|
| 328 |
+
"eval_bleu-1": 24.1567,
|
| 329 |
+
"eval_bleu-2": 5.3356,
|
| 330 |
+
"eval_bleu-3": 2.9739,
|
| 331 |
+
"eval_bleu-4": 2.6574,
|
| 332 |
+
"eval_gen_len": 178.3333,
|
| 333 |
+
"eval_loss": 9.996184349060059,
|
| 334 |
+
"eval_runtime": 44.2153,
|
| 335 |
+
"eval_samples_per_second": 0.271,
|
| 336 |
+
"eval_steps_per_second": 0.271,
|
| 337 |
+
"step": 1690
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 10.0,
|
| 341 |
+
"step": 1690,
|
| 342 |
+
"total_flos": 7053481774940160.0,
|
| 343 |
+
"train_loss": 0.19717555102511977,
|
| 344 |
+
"train_runtime": 3239.6632,
|
| 345 |
+
"train_samples_per_second": 4.689,
|
| 346 |
+
"train_steps_per_second": 0.522
|
| 347 |
+
}
|
| 348 |
+
],
|
| 349 |
+
"logging_steps": 50,
|
| 350 |
+
"max_steps": 1690,
|
| 351 |
+
"num_input_tokens_seen": 0,
|
| 352 |
+
"num_train_epochs": 10,
|
| 353 |
+
"save_steps": 500,
|
| 354 |
+
"total_flos": 7053481774940160.0,
|
| 355 |
+
"train_batch_size": 3,
|
| 356 |
+
"trial_name": null,
|
| 357 |
+
"trial_params": null
|
| 358 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7754cb059b5c0c296af00e860e5d33b1f3ed3fb3b768dd9ef00fbe2ddf76d9e6
|
| 3 |
+
size 5048
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|