Training in progress, step 48000, checkpoint
Browse files- checkpoint-48000/added_tokens.json +3 -0
- checkpoint-48000/bpe.codes +0 -0
- checkpoint-48000/config.json +31 -0
- checkpoint-48000/model.safetensors +3 -0
- checkpoint-48000/optimizer.pt +3 -0
- checkpoint-48000/rng_state.pth +3 -0
- checkpoint-48000/scheduler.pt +3 -0
- checkpoint-48000/special_tokens_map.json +9 -0
- checkpoint-48000/tokenizer_config.json +54 -0
- checkpoint-48000/trainer_state.json +412 -0
- checkpoint-48000/training_args.bin +3 -0
- checkpoint-48000/vocab.txt +0 -0
checkpoint-48000/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 64000
|
| 3 |
+
}
|
checkpoint-48000/bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-48000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "demdecuong/vihealthbert-base-word",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 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": "word-level",
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 258,
|
| 19 |
+
"model_type": "roberta",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"output_hidden_states": true,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.40.2",
|
| 28 |
+
"type_vocab_size": 1,
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 64001
|
| 31 |
+
}
|
checkpoint-48000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:964f8e70705b22f12e52936c62f18d91c63694120d04a7732dc647fb9bbb4e0f
|
| 3 |
+
size 540279452
|
checkpoint-48000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7df599508d558c9b7bae84512adef731ef3335d1b8d630086d385c710d14f0c
|
| 3 |
+
size 1080631290
|
checkpoint-48000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7129a36ebb20f7f993d656480cb5e0bf2da52aedd66f62e7bc12a4cf3a747ab
|
| 3 |
+
size 14244
|
checkpoint-48000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d58622a445edf7d3717f81d48738b3af47c92ab8e6045e34a3e9a23bffd94c8f
|
| 3 |
+
size 1064
|
checkpoint-48000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "</s>",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
checkpoint-48000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"64000": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"pad_token": "<pad>",
|
| 51 |
+
"sep_token": "</s>",
|
| 52 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 53 |
+
"unk_token": "<unk>"
|
| 54 |
+
}
|
checkpoint-48000/trainer_state.json
ADDED
|
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6842720181437064,
|
| 3 |
+
"best_model_checkpoint": "output/pretraining/vihealthbert-w_unsup-SynPD/lr3e-5_wr0.1_wd0.0/checkpoint-48000",
|
| 4 |
+
"epoch": 8.271583663622264,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 48000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00017232465965879716,
|
| 13 |
+
"grad_norm": 35.608882904052734,
|
| 14 |
+
"learning_rate": 5.169739789763915e-09,
|
| 15 |
+
"loss": 10.7382,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.34464931931759435,
|
| 20 |
+
"grad_norm": 4.884454250335693,
|
| 21 |
+
"learning_rate": 1.033947957952783e-05,
|
| 22 |
+
"loss": 5.8543,
|
| 23 |
+
"step": 2000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.34464931931759435,
|
| 27 |
+
"eval_accuracy": 0.3950195480446223,
|
| 28 |
+
"eval_loss": 3.896709680557251,
|
| 29 |
+
"eval_runtime": 24.6709,
|
| 30 |
+
"eval_samples_per_second": 396.175,
|
| 31 |
+
"eval_steps_per_second": 24.766,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.6892986386351887,
|
| 36 |
+
"grad_norm": 5.278345108032227,
|
| 37 |
+
"learning_rate": 2.067895915905566e-05,
|
| 38 |
+
"loss": 3.4544,
|
| 39 |
+
"step": 4000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.6892986386351887,
|
| 43 |
+
"eval_accuracy": 0.530626322082222,
|
| 44 |
+
"eval_loss": 2.811899423599243,
|
| 45 |
+
"eval_runtime": 24.6443,
|
| 46 |
+
"eval_samples_per_second": 396.602,
|
| 47 |
+
"eval_steps_per_second": 24.793,
|
| 48 |
+
"step": 4000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.033947957952783,
|
| 52 |
+
"grad_norm": 4.731122016906738,
|
| 53 |
+
"learning_rate": 2.988684014015739e-05,
|
| 54 |
+
"loss": 2.8312,
|
| 55 |
+
"step": 6000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 1.033947957952783,
|
| 59 |
+
"eval_accuracy": 0.5771132321637026,
|
| 60 |
+
"eval_loss": 2.4039628505706787,
|
| 61 |
+
"eval_runtime": 24.6266,
|
| 62 |
+
"eval_samples_per_second": 396.889,
|
| 63 |
+
"eval_steps_per_second": 24.811,
|
| 64 |
+
"step": 6000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.3785972772703774,
|
| 68 |
+
"grad_norm": 12.213573455810547,
|
| 69 |
+
"learning_rate": 2.873800907576541e-05,
|
| 70 |
+
"loss": 2.5914,
|
| 71 |
+
"step": 8000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.3785972772703774,
|
| 75 |
+
"eval_accuracy": 0.5349752225383133,
|
| 76 |
+
"eval_loss": 2.6481692790985107,
|
| 77 |
+
"eval_runtime": 24.6033,
|
| 78 |
+
"eval_samples_per_second": 397.264,
|
| 79 |
+
"eval_steps_per_second": 24.834,
|
| 80 |
+
"step": 8000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.7232465965879717,
|
| 84 |
+
"grad_norm": 5.172228813171387,
|
| 85 |
+
"learning_rate": 2.758917801137343e-05,
|
| 86 |
+
"loss": 2.5649,
|
| 87 |
+
"step": 10000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.7232465965879717,
|
| 91 |
+
"eval_accuracy": 0.6087076297937304,
|
| 92 |
+
"eval_loss": 2.13348388671875,
|
| 93 |
+
"eval_runtime": 24.6211,
|
| 94 |
+
"eval_samples_per_second": 396.976,
|
| 95 |
+
"eval_steps_per_second": 24.816,
|
| 96 |
+
"step": 10000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.067895915905566,
|
| 100 |
+
"grad_norm": 4.871993064880371,
|
| 101 |
+
"learning_rate": 2.6440346946981447e-05,
|
| 102 |
+
"loss": 2.2749,
|
| 103 |
+
"step": 12000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 2.067895915905566,
|
| 107 |
+
"eval_accuracy": 0.6281529792701336,
|
| 108 |
+
"eval_loss": 1.9895449876785278,
|
| 109 |
+
"eval_runtime": 24.453,
|
| 110 |
+
"eval_samples_per_second": 399.705,
|
| 111 |
+
"eval_steps_per_second": 24.987,
|
| 112 |
+
"step": 12000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.4125452352231607,
|
| 116 |
+
"grad_norm": 8.037242889404297,
|
| 117 |
+
"learning_rate": 2.5291515882589467e-05,
|
| 118 |
+
"loss": 2.1572,
|
| 119 |
+
"step": 14000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.4125452352231607,
|
| 123 |
+
"eval_accuracy": 0.6353159252095423,
|
| 124 |
+
"eval_loss": 1.9312896728515625,
|
| 125 |
+
"eval_runtime": 24.4658,
|
| 126 |
+
"eval_samples_per_second": 399.496,
|
| 127 |
+
"eval_steps_per_second": 24.974,
|
| 128 |
+
"step": 14000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.757194554540755,
|
| 132 |
+
"grad_norm": 4.320974349975586,
|
| 133 |
+
"learning_rate": 2.4142684818197487e-05,
|
| 134 |
+
"loss": 2.1009,
|
| 135 |
+
"step": 16000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.757194554540755,
|
| 139 |
+
"eval_accuracy": 0.6428579553856829,
|
| 140 |
+
"eval_loss": 1.864585280418396,
|
| 141 |
+
"eval_runtime": 24.4545,
|
| 142 |
+
"eval_samples_per_second": 399.68,
|
| 143 |
+
"eval_steps_per_second": 24.985,
|
| 144 |
+
"step": 16000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.101843873858349,
|
| 148 |
+
"grad_norm": 4.6416168212890625,
|
| 149 |
+
"learning_rate": 2.2993853753805504e-05,
|
| 150 |
+
"loss": 2.0609,
|
| 151 |
+
"step": 18000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 3.101843873858349,
|
| 155 |
+
"eval_accuracy": 0.6450457483325106,
|
| 156 |
+
"eval_loss": 1.8571828603744507,
|
| 157 |
+
"eval_runtime": 24.4634,
|
| 158 |
+
"eval_samples_per_second": 399.535,
|
| 159 |
+
"eval_steps_per_second": 24.976,
|
| 160 |
+
"step": 18000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 3.4464931931759435,
|
| 164 |
+
"grad_norm": 4.341440677642822,
|
| 165 |
+
"learning_rate": 2.184502268941352e-05,
|
| 166 |
+
"loss": 2.0885,
|
| 167 |
+
"step": 20000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.4464931931759435,
|
| 171 |
+
"eval_accuracy": 0.6284792764252838,
|
| 172 |
+
"eval_loss": 1.9489394426345825,
|
| 173 |
+
"eval_runtime": 24.6433,
|
| 174 |
+
"eval_samples_per_second": 396.618,
|
| 175 |
+
"eval_steps_per_second": 24.794,
|
| 176 |
+
"step": 20000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.791142512493538,
|
| 180 |
+
"grad_norm": 4.660053253173828,
|
| 181 |
+
"learning_rate": 2.069619162502154e-05,
|
| 182 |
+
"loss": 1.9891,
|
| 183 |
+
"step": 22000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.791142512493538,
|
| 187 |
+
"eval_accuracy": 0.6582960564701575,
|
| 188 |
+
"eval_loss": 1.7700080871582031,
|
| 189 |
+
"eval_runtime": 24.616,
|
| 190 |
+
"eval_samples_per_second": 397.059,
|
| 191 |
+
"eval_steps_per_second": 24.821,
|
| 192 |
+
"step": 22000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 4.135791831811132,
|
| 196 |
+
"grad_norm": 3.9445292949676514,
|
| 197 |
+
"learning_rate": 1.954736056062956e-05,
|
| 198 |
+
"loss": 1.9368,
|
| 199 |
+
"step": 24000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 4.135791831811132,
|
| 203 |
+
"eval_accuracy": 0.6608816779512006,
|
| 204 |
+
"eval_loss": 1.7397598028182983,
|
| 205 |
+
"eval_runtime": 24.6251,
|
| 206 |
+
"eval_samples_per_second": 396.912,
|
| 207 |
+
"eval_steps_per_second": 24.812,
|
| 208 |
+
"step": 24000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 4.480441151128726,
|
| 212 |
+
"grad_norm": 4.561331748962402,
|
| 213 |
+
"learning_rate": 1.839852949623758e-05,
|
| 214 |
+
"loss": 1.9003,
|
| 215 |
+
"step": 26000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.480441151128726,
|
| 219 |
+
"eval_accuracy": 0.666368433126864,
|
| 220 |
+
"eval_loss": 1.7164973020553589,
|
| 221 |
+
"eval_runtime": 24.4665,
|
| 222 |
+
"eval_samples_per_second": 399.485,
|
| 223 |
+
"eval_steps_per_second": 24.973,
|
| 224 |
+
"step": 26000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.825090470446321,
|
| 228 |
+
"grad_norm": 4.358778476715088,
|
| 229 |
+
"learning_rate": 1.72496984318456e-05,
|
| 230 |
+
"loss": 1.9058,
|
| 231 |
+
"step": 28000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 4.825090470446321,
|
| 235 |
+
"eval_accuracy": 0.666961039556835,
|
| 236 |
+
"eval_loss": 1.703224539756775,
|
| 237 |
+
"eval_runtime": 24.4455,
|
| 238 |
+
"eval_samples_per_second": 399.829,
|
| 239 |
+
"eval_steps_per_second": 24.994,
|
| 240 |
+
"step": 28000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.1697397897639155,
|
| 244 |
+
"grad_norm": 4.522342205047607,
|
| 245 |
+
"learning_rate": 1.6100867367453616e-05,
|
| 246 |
+
"loss": 1.859,
|
| 247 |
+
"step": 30000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 5.1697397897639155,
|
| 251 |
+
"eval_accuracy": 0.6717793867023528,
|
| 252 |
+
"eval_loss": 1.677147626876831,
|
| 253 |
+
"eval_runtime": 24.4697,
|
| 254 |
+
"eval_samples_per_second": 399.432,
|
| 255 |
+
"eval_steps_per_second": 24.97,
|
| 256 |
+
"step": 30000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 5.51438910908151,
|
| 260 |
+
"grad_norm": 4.162671089172363,
|
| 261 |
+
"learning_rate": 1.4952036303061636e-05,
|
| 262 |
+
"loss": 1.8401,
|
| 263 |
+
"step": 32000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 5.51438910908151,
|
| 267 |
+
"eval_accuracy": 0.6709595439247201,
|
| 268 |
+
"eval_loss": 1.665189504623413,
|
| 269 |
+
"eval_runtime": 24.6261,
|
| 270 |
+
"eval_samples_per_second": 396.897,
|
| 271 |
+
"eval_steps_per_second": 24.811,
|
| 272 |
+
"step": 32000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 5.859038428399104,
|
| 276 |
+
"grad_norm": 4.618478775024414,
|
| 277 |
+
"learning_rate": 1.3803205238669653e-05,
|
| 278 |
+
"loss": 1.8181,
|
| 279 |
+
"step": 34000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 5.859038428399104,
|
| 283 |
+
"eval_accuracy": 0.675394469972155,
|
| 284 |
+
"eval_loss": 1.6417487859725952,
|
| 285 |
+
"eval_runtime": 24.5944,
|
| 286 |
+
"eval_samples_per_second": 397.408,
|
| 287 |
+
"eval_steps_per_second": 24.843,
|
| 288 |
+
"step": 34000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 6.203687747716698,
|
| 292 |
+
"grad_norm": 4.046966075897217,
|
| 293 |
+
"learning_rate": 1.2654374174277672e-05,
|
| 294 |
+
"loss": 1.8133,
|
| 295 |
+
"step": 36000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.203687747716698,
|
| 299 |
+
"eval_accuracy": 0.6748118789132058,
|
| 300 |
+
"eval_loss": 1.6430697441101074,
|
| 301 |
+
"eval_runtime": 24.6651,
|
| 302 |
+
"eval_samples_per_second": 396.268,
|
| 303 |
+
"eval_steps_per_second": 24.772,
|
| 304 |
+
"step": 36000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 6.548337067034293,
|
| 308 |
+
"grad_norm": 4.522408962249756,
|
| 309 |
+
"learning_rate": 1.1505543109885692e-05,
|
| 310 |
+
"loss": 1.7888,
|
| 311 |
+
"step": 38000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 6.548337067034293,
|
| 315 |
+
"eval_accuracy": 0.6755271447952356,
|
| 316 |
+
"eval_loss": 1.6363412141799927,
|
| 317 |
+
"eval_runtime": 24.6146,
|
| 318 |
+
"eval_samples_per_second": 397.081,
|
| 319 |
+
"eval_steps_per_second": 24.823,
|
| 320 |
+
"step": 38000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.892986386351887,
|
| 324 |
+
"grad_norm": 4.334969520568848,
|
| 325 |
+
"learning_rate": 1.035671204549371e-05,
|
| 326 |
+
"loss": 1.7811,
|
| 327 |
+
"step": 40000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 6.892986386351887,
|
| 331 |
+
"eval_accuracy": 0.679264661758257,
|
| 332 |
+
"eval_loss": 1.6205224990844727,
|
| 333 |
+
"eval_runtime": 24.6327,
|
| 334 |
+
"eval_samples_per_second": 396.79,
|
| 335 |
+
"eval_steps_per_second": 24.804,
|
| 336 |
+
"step": 40000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 7.237635705669481,
|
| 340 |
+
"grad_norm": 3.82973313331604,
|
| 341 |
+
"learning_rate": 9.20788098110173e-06,
|
| 342 |
+
"loss": 1.7481,
|
| 343 |
+
"step": 42000
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 7.237635705669481,
|
| 347 |
+
"eval_accuracy": 0.6806846415754118,
|
| 348 |
+
"eval_loss": 1.61899995803833,
|
| 349 |
+
"eval_runtime": 24.6165,
|
| 350 |
+
"eval_samples_per_second": 397.051,
|
| 351 |
+
"eval_steps_per_second": 24.821,
|
| 352 |
+
"step": 42000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.582285024987076,
|
| 356 |
+
"grad_norm": 4.882840633392334,
|
| 357 |
+
"learning_rate": 8.059049916709748e-06,
|
| 358 |
+
"loss": 1.7509,
|
| 359 |
+
"step": 44000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.582285024987076,
|
| 363 |
+
"eval_accuracy": 0.679368029739777,
|
| 364 |
+
"eval_loss": 1.614187240600586,
|
| 365 |
+
"eval_runtime": 24.6302,
|
| 366 |
+
"eval_samples_per_second": 396.829,
|
| 367 |
+
"eval_steps_per_second": 24.807,
|
| 368 |
+
"step": 44000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 7.92693434430467,
|
| 372 |
+
"grad_norm": 5.021098613739014,
|
| 373 |
+
"learning_rate": 6.910218852317767e-06,
|
| 374 |
+
"loss": 1.7517,
|
| 375 |
+
"step": 46000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 7.92693434430467,
|
| 379 |
+
"eval_accuracy": 0.6818803989003784,
|
| 380 |
+
"eval_loss": 1.594929814338684,
|
| 381 |
+
"eval_runtime": 24.6331,
|
| 382 |
+
"eval_samples_per_second": 396.783,
|
| 383 |
+
"eval_steps_per_second": 24.804,
|
| 384 |
+
"step": 46000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.271583663622264,
|
| 388 |
+
"grad_norm": 4.21428108215332,
|
| 389 |
+
"learning_rate": 5.761387787925786e-06,
|
| 390 |
+
"loss": 1.7358,
|
| 391 |
+
"step": 48000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 8.271583663622264,
|
| 395 |
+
"eval_accuracy": 0.6842720181437064,
|
| 396 |
+
"eval_loss": 1.5908812284469604,
|
| 397 |
+
"eval_runtime": 24.6065,
|
| 398 |
+
"eval_samples_per_second": 397.212,
|
| 399 |
+
"eval_steps_per_second": 24.831,
|
| 400 |
+
"step": 48000
|
| 401 |
+
}
|
| 402 |
+
],
|
| 403 |
+
"logging_steps": 2000,
|
| 404 |
+
"max_steps": 58030,
|
| 405 |
+
"num_input_tokens_seen": 0,
|
| 406 |
+
"num_train_epochs": 10,
|
| 407 |
+
"save_steps": 2000,
|
| 408 |
+
"total_flos": 0.0,
|
| 409 |
+
"train_batch_size": 32,
|
| 410 |
+
"trial_name": null,
|
| 411 |
+
"trial_params": null
|
| 412 |
+
}
|
checkpoint-48000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:828a11e9b75940b4120312d1450c3472eb18a2c7fa0179d8afafbcd0800beb75
|
| 3 |
+
size 5304
|
checkpoint-48000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|