Training in progress, step 500, checkpoint
Browse files- checkpoint-500/config.json +39 -0
- checkpoint-500/merges.txt +0 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/special_tokens_map.json +15 -0
- checkpoint-500/tokenizer.json +0 -0
- checkpoint-500/tokenizer_config.json +57 -0
- checkpoint-500/trainer_state.json +409 -0
- checkpoint-500/training_args.bin +3 -0
- checkpoint-500/vocab.json +0 -0
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSentimentClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"finetuning_task": "text-classification",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "0",
|
| 16 |
+
"1": "1",
|
| 17 |
+
"2": "2"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"0": 0,
|
| 23 |
+
"1": 1,
|
| 24 |
+
"2": 2
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"max_position_embeddings": 514,
|
| 28 |
+
"model_type": "roberta",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.34.1",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50265
|
| 39 |
+
}
|
checkpoint-500/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf34a6733d5227eb85d55def447818a330bc1eae397c5506bc1e75b3797e4fda
|
| 3 |
+
size 997351674
|
checkpoint-500/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:340c33a4987169203c067a0a28b9c570a1f740be29bc9ad9b441418693a54d36
|
| 3 |
+
size 498661166
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b422432f050f31232fd8bfedc63b986c036bf46b6cf0b466f2e329905094359
|
| 3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71970c5dfe3440001b08f26882ef33379714e402bdea5de11ccf4733cf0f157f
|
| 3 |
+
size 1064
|
checkpoint-500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,409 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3762227238525207,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 5e-07,
|
| 14 |
+
"loss": 1.1001,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 1e-06,
|
| 20 |
+
"loss": 1.0661,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 1.5e-06,
|
| 26 |
+
"loss": 1.0782,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 2e-06,
|
| 32 |
+
"loss": 1.0578,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.04,
|
| 37 |
+
"learning_rate": 2.5e-06,
|
| 38 |
+
"loss": 1.0395,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.04,
|
| 43 |
+
"eval_accuracy": 0.4754781102152329,
|
| 44 |
+
"eval_loss": 1.0322505235671997,
|
| 45 |
+
"eval_runtime": 49.5848,
|
| 46 |
+
"eval_samples_per_second": 605.307,
|
| 47 |
+
"eval_steps_per_second": 1.19,
|
| 48 |
+
"step": 50
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.05,
|
| 52 |
+
"learning_rate": 3e-06,
|
| 53 |
+
"loss": 1.0308,
|
| 54 |
+
"step": 60
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.05,
|
| 58 |
+
"learning_rate": 3.5e-06,
|
| 59 |
+
"loss": 1.0044,
|
| 60 |
+
"step": 70
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.06,
|
| 64 |
+
"learning_rate": 4e-06,
|
| 65 |
+
"loss": 1.0398,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.07,
|
| 70 |
+
"learning_rate": 4.5e-06,
|
| 71 |
+
"loss": 1.0116,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.08,
|
| 76 |
+
"learning_rate": 5e-06,
|
| 77 |
+
"loss": 1.0067,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.08,
|
| 82 |
+
"eval_accuracy": 0.5313187179316319,
|
| 83 |
+
"eval_loss": 0.9863238334655762,
|
| 84 |
+
"eval_runtime": 49.2356,
|
| 85 |
+
"eval_samples_per_second": 609.599,
|
| 86 |
+
"eval_steps_per_second": 1.198,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.08,
|
| 91 |
+
"learning_rate": 5.5e-06,
|
| 92 |
+
"loss": 1.0131,
|
| 93 |
+
"step": 110
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 6e-06,
|
| 98 |
+
"loss": 1.0235,
|
| 99 |
+
"step": 120
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.1,
|
| 103 |
+
"learning_rate": 6.5e-06,
|
| 104 |
+
"loss": 1.0073,
|
| 105 |
+
"step": 130
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.11,
|
| 109 |
+
"learning_rate": 7e-06,
|
| 110 |
+
"loss": 0.9856,
|
| 111 |
+
"step": 140
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.11,
|
| 115 |
+
"learning_rate": 7.5e-06,
|
| 116 |
+
"loss": 1.0062,
|
| 117 |
+
"step": 150
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"eval_accuracy": 0.5358499366962084,
|
| 122 |
+
"eval_loss": 0.9735665917396545,
|
| 123 |
+
"eval_runtime": 49.4568,
|
| 124 |
+
"eval_samples_per_second": 606.874,
|
| 125 |
+
"eval_steps_per_second": 1.193,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.12,
|
| 130 |
+
"learning_rate": 8e-06,
|
| 131 |
+
"loss": 0.9622,
|
| 132 |
+
"step": 160
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.13,
|
| 136 |
+
"learning_rate": 8.500000000000002e-06,
|
| 137 |
+
"loss": 0.9583,
|
| 138 |
+
"step": 170
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.14,
|
| 142 |
+
"learning_rate": 9e-06,
|
| 143 |
+
"loss": 0.987,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.14,
|
| 148 |
+
"learning_rate": 9.5e-06,
|
| 149 |
+
"loss": 0.9995,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.15,
|
| 154 |
+
"learning_rate": 1e-05,
|
| 155 |
+
"loss": 0.9953,
|
| 156 |
+
"step": 200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.15,
|
| 160 |
+
"eval_accuracy": 0.5406476977410541,
|
| 161 |
+
"eval_loss": 0.9847397804260254,
|
| 162 |
+
"eval_runtime": 49.5469,
|
| 163 |
+
"eval_samples_per_second": 605.769,
|
| 164 |
+
"eval_steps_per_second": 1.191,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16,
|
| 169 |
+
"learning_rate": 1.0500000000000001e-05,
|
| 170 |
+
"loss": 0.9894,
|
| 171 |
+
"step": 210
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.17,
|
| 175 |
+
"learning_rate": 1.1e-05,
|
| 176 |
+
"loss": 0.9857,
|
| 177 |
+
"step": 220
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17,
|
| 181 |
+
"learning_rate": 1.15e-05,
|
| 182 |
+
"loss": 0.9806,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.18,
|
| 187 |
+
"learning_rate": 1.2e-05,
|
| 188 |
+
"loss": 0.9802,
|
| 189 |
+
"step": 240
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.19,
|
| 193 |
+
"learning_rate": 1.25e-05,
|
| 194 |
+
"loss": 0.9559,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.19,
|
| 199 |
+
"eval_accuracy": 0.5136269740787632,
|
| 200 |
+
"eval_loss": 1.0206754207611084,
|
| 201 |
+
"eval_runtime": 49.5108,
|
| 202 |
+
"eval_samples_per_second": 606.212,
|
| 203 |
+
"eval_steps_per_second": 1.192,
|
| 204 |
+
"step": 250
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.2,
|
| 208 |
+
"learning_rate": 1.3e-05,
|
| 209 |
+
"loss": 0.9877,
|
| 210 |
+
"step": 260
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.2,
|
| 214 |
+
"learning_rate": 1.35e-05,
|
| 215 |
+
"loss": 0.9878,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.21,
|
| 220 |
+
"learning_rate": 1.4e-05,
|
| 221 |
+
"loss": 0.9646,
|
| 222 |
+
"step": 280
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.22,
|
| 226 |
+
"learning_rate": 1.4500000000000002e-05,
|
| 227 |
+
"loss": 0.9598,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.23,
|
| 232 |
+
"learning_rate": 1.5e-05,
|
| 233 |
+
"loss": 0.9567,
|
| 234 |
+
"step": 300
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.23,
|
| 238 |
+
"eval_accuracy": 0.5693676284400613,
|
| 239 |
+
"eval_loss": 0.9298574924468994,
|
| 240 |
+
"eval_runtime": 49.5798,
|
| 241 |
+
"eval_samples_per_second": 605.367,
|
| 242 |
+
"eval_steps_per_second": 1.19,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.23,
|
| 247 |
+
"learning_rate": 1.55e-05,
|
| 248 |
+
"loss": 0.9659,
|
| 249 |
+
"step": 310
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.24,
|
| 253 |
+
"learning_rate": 1.6e-05,
|
| 254 |
+
"loss": 0.9803,
|
| 255 |
+
"step": 320
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.25,
|
| 259 |
+
"learning_rate": 1.65e-05,
|
| 260 |
+
"loss": 0.959,
|
| 261 |
+
"step": 330
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.26,
|
| 265 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 266 |
+
"loss": 0.9298,
|
| 267 |
+
"step": 340
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.26,
|
| 271 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 272 |
+
"loss": 0.8923,
|
| 273 |
+
"step": 350
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.26,
|
| 277 |
+
"eval_accuracy": 0.603285133604318,
|
| 278 |
+
"eval_loss": 0.8731092810630798,
|
| 279 |
+
"eval_runtime": 49.5126,
|
| 280 |
+
"eval_samples_per_second": 606.189,
|
| 281 |
+
"eval_steps_per_second": 1.192,
|
| 282 |
+
"step": 350
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.27,
|
| 286 |
+
"learning_rate": 1.8e-05,
|
| 287 |
+
"loss": 0.9255,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.28,
|
| 292 |
+
"learning_rate": 1.85e-05,
|
| 293 |
+
"loss": 0.9567,
|
| 294 |
+
"step": 370
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.29,
|
| 298 |
+
"learning_rate": 1.9e-05,
|
| 299 |
+
"loss": 0.9135,
|
| 300 |
+
"step": 380
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.29,
|
| 304 |
+
"learning_rate": 1.95e-05,
|
| 305 |
+
"loss": 0.8978,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.3,
|
| 310 |
+
"learning_rate": 2e-05,
|
| 311 |
+
"loss": 0.9617,
|
| 312 |
+
"step": 400
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.3,
|
| 316 |
+
"eval_accuracy": 0.5401479309655494,
|
| 317 |
+
"eval_loss": 0.9500759840011597,
|
| 318 |
+
"eval_runtime": 49.5248,
|
| 319 |
+
"eval_samples_per_second": 606.04,
|
| 320 |
+
"eval_steps_per_second": 1.191,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.31,
|
| 325 |
+
"learning_rate": 2.05e-05,
|
| 326 |
+
"loss": 0.9387,
|
| 327 |
+
"step": 410
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.32,
|
| 331 |
+
"learning_rate": 2.1000000000000002e-05,
|
| 332 |
+
"loss": 0.8832,
|
| 333 |
+
"step": 420
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.32,
|
| 337 |
+
"learning_rate": 2.1499999999999997e-05,
|
| 338 |
+
"loss": 0.9087,
|
| 339 |
+
"step": 430
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.33,
|
| 343 |
+
"learning_rate": 2.2e-05,
|
| 344 |
+
"loss": 0.9192,
|
| 345 |
+
"step": 440
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.34,
|
| 349 |
+
"learning_rate": 2.2499999999999998e-05,
|
| 350 |
+
"loss": 0.8456,
|
| 351 |
+
"step": 450
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.34,
|
| 355 |
+
"eval_accuracy": 0.6245085626707536,
|
| 356 |
+
"eval_loss": 0.8298193216323853,
|
| 357 |
+
"eval_runtime": 49.5226,
|
| 358 |
+
"eval_samples_per_second": 606.066,
|
| 359 |
+
"eval_steps_per_second": 1.191,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.35,
|
| 364 |
+
"learning_rate": 2.3e-05,
|
| 365 |
+
"loss": 0.8511,
|
| 366 |
+
"step": 460
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.35,
|
| 370 |
+
"learning_rate": 2.3500000000000002e-05,
|
| 371 |
+
"loss": 0.9211,
|
| 372 |
+
"step": 470
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.36,
|
| 376 |
+
"learning_rate": 2.4e-05,
|
| 377 |
+
"loss": 0.8416,
|
| 378 |
+
"step": 480
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.37,
|
| 382 |
+
"learning_rate": 2.4500000000000003e-05,
|
| 383 |
+
"loss": 0.849,
|
| 384 |
+
"step": 490
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.38,
|
| 388 |
+
"learning_rate": 2.5e-05,
|
| 389 |
+
"loss": 0.8098,
|
| 390 |
+
"step": 500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.38,
|
| 394 |
+
"eval_accuracy": 0.6523622309588859,
|
| 395 |
+
"eval_loss": 0.771039605140686,
|
| 396 |
+
"eval_runtime": 49.4859,
|
| 397 |
+
"eval_samples_per_second": 606.517,
|
| 398 |
+
"eval_steps_per_second": 1.192,
|
| 399 |
+
"step": 500
|
| 400 |
+
}
|
| 401 |
+
],
|
| 402 |
+
"logging_steps": 10,
|
| 403 |
+
"max_steps": 3987,
|
| 404 |
+
"num_train_epochs": 3,
|
| 405 |
+
"save_steps": 250,
|
| 406 |
+
"total_flos": 1.6839258144768e+16,
|
| 407 |
+
"trial_name": null,
|
| 408 |
+
"trial_params": null
|
| 409 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:842788c44aca7ccbca2d57d8869e43eb15da3880b4cadb0b091bb46a3e020fcc
|
| 3 |
+
size 4536
|
checkpoint-500/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|