Upload folder using huggingface_hub
Browse files- config.json +39 -0
- model.safetensors +3 -0
- optimizer_state_dict.pth +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +53 -0
- trainer_state.json +481 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pGenomeOcean/GenomeOcean-100M",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "pGenomeOcean/GenomeOcean-100M--configuration_mistral.MistralConfig",
|
| 9 |
+
"AutoModel": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralModel",
|
| 10 |
+
"AutoModelForCausalLM": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralForCausalLM",
|
| 11 |
+
"AutoModelForMaskedLM": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralForMaskedLM",
|
| 12 |
+
"AutoModelForSequenceClassification": "pGenomeOcean/GenomeOcean-100M--modeling_mistral.MistralForSequenceClassification"
|
| 13 |
+
},
|
| 14 |
+
"bos_token_id": 1,
|
| 15 |
+
"classifier_dropout": 0.1,
|
| 16 |
+
"eos_token_id": 2,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 768,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"is_causal": true,
|
| 22 |
+
"max_position_embeddings": 32768,
|
| 23 |
+
"model_type": "mistral",
|
| 24 |
+
"num_attention_heads": 8,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"num_key_value_heads": 8,
|
| 27 |
+
"output_router_logits": false,
|
| 28 |
+
"pad_token_id": 3,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"rms_norm_eps": 1e-05,
|
| 31 |
+
"rope_theta": 1000000.0,
|
| 32 |
+
"router_aux_loss_coef": 0.02,
|
| 33 |
+
"sliding_window": null,
|
| 34 |
+
"tie_word_embeddings": false,
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.45.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 4096
|
| 39 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04ac521cfeddce7fb6a5a9b6400a33f0577daa74ca7da7865618f7b3bf612a73
|
| 3 |
+
size 465662960
|
optimizer_state_dict.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41102730b44f0129dfe37b8363c0946c841266a962359d3aaee8fc650fa51673
|
| 3 |
+
size 931398901
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"mask_token": "[MASK]",
|
| 47 |
+
"model_max_length": 256,
|
| 48 |
+
"pad_token": "[PAD]",
|
| 49 |
+
"padding_side": "right",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 52 |
+
"unk_token": "[UNK]"
|
| 53 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,481 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2197728157043457,
|
| 3 |
+
"best_model_checkpoint": "output_pipe/1/origin/checkpoint-1600",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 3372,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.11862396204033215,
|
| 13 |
+
"grad_norm": 9.243636131286621,
|
| 14 |
+
"learning_rate": 2.957555689343769e-05,
|
| 15 |
+
"loss": 0.4501,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2372479240806643,
|
| 20 |
+
"grad_norm": 6.825350761413574,
|
| 21 |
+
"learning_rate": 2.8672486453943407e-05,
|
| 22 |
+
"loss": 0.2984,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2372479240806643,
|
| 27 |
+
"eval_accuracy": 0.8756115641215715,
|
| 28 |
+
"eval_f1": 0.8753583742291109,
|
| 29 |
+
"eval_loss": 0.2889566719532013,
|
| 30 |
+
"eval_matthews_correlation": 0.7552199511937604,
|
| 31 |
+
"eval_precision": 0.8793427094656048,
|
| 32 |
+
"eval_recall": 0.8758851563831229,
|
| 33 |
+
"eval_runtime": 1.416,
|
| 34 |
+
"eval_samples_per_second": 4763.557,
|
| 35 |
+
"eval_steps_per_second": 74.861,
|
| 36 |
+
"step": 200
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.35587188612099646,
|
| 40 |
+
"grad_norm": 9.723295211791992,
|
| 41 |
+
"learning_rate": 2.7769416014449128e-05,
|
| 42 |
+
"loss": 0.2867,
|
| 43 |
+
"step": 300
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.4744958481613286,
|
| 47 |
+
"grad_norm": 4.6286139488220215,
|
| 48 |
+
"learning_rate": 2.686634557495485e-05,
|
| 49 |
+
"loss": 0.2692,
|
| 50 |
+
"step": 400
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.4744958481613286,
|
| 54 |
+
"eval_accuracy": 0.8923647146034099,
|
| 55 |
+
"eval_f1": 0.8923344963363296,
|
| 56 |
+
"eval_loss": 0.2463846057653427,
|
| 57 |
+
"eval_matthews_correlation": 0.7855525209874886,
|
| 58 |
+
"eval_precision": 0.8930692687442148,
|
| 59 |
+
"eval_recall": 0.892483470662371,
|
| 60 |
+
"eval_runtime": 1.4056,
|
| 61 |
+
"eval_samples_per_second": 4798.74,
|
| 62 |
+
"eval_steps_per_second": 75.414,
|
| 63 |
+
"step": 400
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.5931198102016607,
|
| 67 |
+
"grad_norm": 6.366510391235352,
|
| 68 |
+
"learning_rate": 2.5963275135460566e-05,
|
| 69 |
+
"loss": 0.2648,
|
| 70 |
+
"step": 500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.7117437722419929,
|
| 74 |
+
"grad_norm": 6.894649505615234,
|
| 75 |
+
"learning_rate": 2.5060204695966287e-05,
|
| 76 |
+
"loss": 0.2594,
|
| 77 |
+
"step": 600
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.7117437722419929,
|
| 81 |
+
"eval_accuracy": 0.9012601927353595,
|
| 82 |
+
"eval_f1": 0.901260173202269,
|
| 83 |
+
"eval_loss": 0.22498522698879242,
|
| 84 |
+
"eval_matthews_correlation": 0.8025661484949196,
|
| 85 |
+
"eval_precision": 0.9012812748493957,
|
| 86 |
+
"eval_recall": 0.9012848736535926,
|
| 87 |
+
"eval_runtime": 1.4052,
|
| 88 |
+
"eval_samples_per_second": 4800.055,
|
| 89 |
+
"eval_steps_per_second": 75.435,
|
| 90 |
+
"step": 600
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.830367734282325,
|
| 94 |
+
"grad_norm": 16.520292282104492,
|
| 95 |
+
"learning_rate": 2.4157134256472004e-05,
|
| 96 |
+
"loss": 0.2517,
|
| 97 |
+
"step": 700
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.9489916963226572,
|
| 101 |
+
"grad_norm": 3.2996578216552734,
|
| 102 |
+
"learning_rate": 2.3254063816977725e-05,
|
| 103 |
+
"loss": 0.2432,
|
| 104 |
+
"step": 800
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.9489916963226572,
|
| 108 |
+
"eval_accuracy": 0.8917716827279466,
|
| 109 |
+
"eval_f1": 0.8917528361445037,
|
| 110 |
+
"eval_loss": 0.24542774260044098,
|
| 111 |
+
"eval_matthews_correlation": 0.7836117160608459,
|
| 112 |
+
"eval_precision": 0.8918855979873312,
|
| 113 |
+
"eval_recall": 0.891726134298813,
|
| 114 |
+
"eval_runtime": 1.4043,
|
| 115 |
+
"eval_samples_per_second": 4803.154,
|
| 116 |
+
"eval_steps_per_second": 75.483,
|
| 117 |
+
"step": 800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.0676156583629894,
|
| 121 |
+
"grad_norm": 6.839262962341309,
|
| 122 |
+
"learning_rate": 2.2350993377483446e-05,
|
| 123 |
+
"loss": 0.2125,
|
| 124 |
+
"step": 900
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.1862396204033214,
|
| 128 |
+
"grad_norm": 10.704083442687988,
|
| 129 |
+
"learning_rate": 2.1447922937989163e-05,
|
| 130 |
+
"loss": 0.1561,
|
| 131 |
+
"step": 1000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.1862396204033214,
|
| 135 |
+
"eval_accuracy": 0.8956263899184581,
|
| 136 |
+
"eval_f1": 0.8951017745713171,
|
| 137 |
+
"eval_loss": 0.2612854242324829,
|
| 138 |
+
"eval_matthews_correlation": 0.8007606389596266,
|
| 139 |
+
"eval_precision": 0.904766892075258,
|
| 140 |
+
"eval_recall": 0.8960412854047166,
|
| 141 |
+
"eval_runtime": 1.4053,
|
| 142 |
+
"eval_samples_per_second": 4799.797,
|
| 143 |
+
"eval_steps_per_second": 75.43,
|
| 144 |
+
"step": 1000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.3048635824436536,
|
| 148 |
+
"grad_norm": 4.566791534423828,
|
| 149 |
+
"learning_rate": 2.0544852498494884e-05,
|
| 150 |
+
"loss": 0.1685,
|
| 151 |
+
"step": 1100
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.4234875444839858,
|
| 155 |
+
"grad_norm": 3.4650704860687256,
|
| 156 |
+
"learning_rate": 1.96417820590006e-05,
|
| 157 |
+
"loss": 0.1607,
|
| 158 |
+
"step": 1200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.4234875444839858,
|
| 162 |
+
"eval_accuracy": 0.9071905114899926,
|
| 163 |
+
"eval_f1": 0.9071251020390567,
|
| 164 |
+
"eval_loss": 0.22077599167823792,
|
| 165 |
+
"eval_matthews_correlation": 0.8161151585361717,
|
| 166 |
+
"eval_precision": 0.9087529499988971,
|
| 167 |
+
"eval_recall": 0.9073633915023229,
|
| 168 |
+
"eval_runtime": 1.4041,
|
| 169 |
+
"eval_samples_per_second": 4803.697,
|
| 170 |
+
"eval_steps_per_second": 75.492,
|
| 171 |
+
"step": 1200
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.5421115065243178,
|
| 175 |
+
"grad_norm": 9.395886421203613,
|
| 176 |
+
"learning_rate": 1.8738711619506322e-05,
|
| 177 |
+
"loss": 0.1751,
|
| 178 |
+
"step": 1300
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.66073546856465,
|
| 182 |
+
"grad_norm": 5.750766277313232,
|
| 183 |
+
"learning_rate": 1.7835641180012043e-05,
|
| 184 |
+
"loss": 0.1617,
|
| 185 |
+
"step": 1400
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.66073546856465,
|
| 189 |
+
"eval_accuracy": 0.9033358042994811,
|
| 190 |
+
"eval_f1": 0.9032721716896848,
|
| 191 |
+
"eval_loss": 0.23882386088371277,
|
| 192 |
+
"eval_matthews_correlation": 0.8072800092044834,
|
| 193 |
+
"eval_precision": 0.9040581552977713,
|
| 194 |
+
"eval_recall": 0.9032222866414605,
|
| 195 |
+
"eval_runtime": 1.4054,
|
| 196 |
+
"eval_samples_per_second": 4799.439,
|
| 197 |
+
"eval_steps_per_second": 75.425,
|
| 198 |
+
"step": 1400
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.7793594306049823,
|
| 202 |
+
"grad_norm": 10.305908203125,
|
| 203 |
+
"learning_rate": 1.693257074051776e-05,
|
| 204 |
+
"loss": 0.1615,
|
| 205 |
+
"step": 1500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.8979833926453145,
|
| 209 |
+
"grad_norm": 6.007554531097412,
|
| 210 |
+
"learning_rate": 1.602950030102348e-05,
|
| 211 |
+
"loss": 0.1669,
|
| 212 |
+
"step": 1600
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.8979833926453145,
|
| 216 |
+
"eval_accuracy": 0.9058561897702001,
|
| 217 |
+
"eval_f1": 0.9057890959881881,
|
| 218 |
+
"eval_loss": 0.2197728157043457,
|
| 219 |
+
"eval_matthews_correlation": 0.8134577263257711,
|
| 220 |
+
"eval_precision": 0.9074290868275333,
|
| 221 |
+
"eval_recall": 0.9060298429301878,
|
| 222 |
+
"eval_runtime": 1.4038,
|
| 223 |
+
"eval_samples_per_second": 4804.94,
|
| 224 |
+
"eval_steps_per_second": 75.511,
|
| 225 |
+
"step": 1600
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.0166073546856467,
|
| 229 |
+
"grad_norm": 17.52599334716797,
|
| 230 |
+
"learning_rate": 1.5126429861529199e-05,
|
| 231 |
+
"loss": 0.1482,
|
| 232 |
+
"step": 1700
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.135231316725979,
|
| 236 |
+
"grad_norm": 13.2647066116333,
|
| 237 |
+
"learning_rate": 1.422335942203492e-05,
|
| 238 |
+
"loss": 0.0629,
|
| 239 |
+
"step": 1800
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.135231316725979,
|
| 243 |
+
"eval_accuracy": 0.900815418828762,
|
| 244 |
+
"eval_f1": 0.9008021532090624,
|
| 245 |
+
"eval_loss": 0.37351372838020325,
|
| 246 |
+
"eval_matthews_correlation": 0.8016708933554149,
|
| 247 |
+
"eval_precision": 0.9008918124334665,
|
| 248 |
+
"eval_recall": 0.9007790888470252,
|
| 249 |
+
"eval_runtime": 1.4037,
|
| 250 |
+
"eval_samples_per_second": 4805.322,
|
| 251 |
+
"eval_steps_per_second": 75.517,
|
| 252 |
+
"step": 1800
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.2538552787663106,
|
| 256 |
+
"grad_norm": 5.28846549987793,
|
| 257 |
+
"learning_rate": 1.3320288982540638e-05,
|
| 258 |
+
"loss": 0.0622,
|
| 259 |
+
"step": 1900
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.372479240806643,
|
| 263 |
+
"grad_norm": 11.060345649719238,
|
| 264 |
+
"learning_rate": 1.2417218543046358e-05,
|
| 265 |
+
"loss": 0.0748,
|
| 266 |
+
"step": 2000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.372479240806643,
|
| 270 |
+
"eval_accuracy": 0.9082283172720533,
|
| 271 |
+
"eval_f1": 0.9082064942582599,
|
| 272 |
+
"eval_loss": 0.342942476272583,
|
| 273 |
+
"eval_matthews_correlation": 0.8172074539472458,
|
| 274 |
+
"eval_precision": 0.908867392978981,
|
| 275 |
+
"eval_recall": 0.9083402309983616,
|
| 276 |
+
"eval_runtime": 1.425,
|
| 277 |
+
"eval_samples_per_second": 4733.445,
|
| 278 |
+
"eval_steps_per_second": 74.388,
|
| 279 |
+
"step": 2000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.491103202846975,
|
| 283 |
+
"grad_norm": 16.14167594909668,
|
| 284 |
+
"learning_rate": 1.1514148103552077e-05,
|
| 285 |
+
"loss": 0.0678,
|
| 286 |
+
"step": 2100
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.6097271648873073,
|
| 290 |
+
"grad_norm": 14.60816478729248,
|
| 291 |
+
"learning_rate": 1.0611077664057798e-05,
|
| 292 |
+
"loss": 0.0651,
|
| 293 |
+
"step": 2200
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.6097271648873073,
|
| 297 |
+
"eval_accuracy": 0.9015567086730912,
|
| 298 |
+
"eval_f1": 0.9015537463069576,
|
| 299 |
+
"eval_loss": 0.3432765305042267,
|
| 300 |
+
"eval_matthews_correlation": 0.8031074926139152,
|
| 301 |
+
"eval_precision": 0.9015537463069576,
|
| 302 |
+
"eval_recall": 0.9015537463069576,
|
| 303 |
+
"eval_runtime": 1.413,
|
| 304 |
+
"eval_samples_per_second": 4773.585,
|
| 305 |
+
"eval_steps_per_second": 75.019,
|
| 306 |
+
"step": 2200
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.7283511269276395,
|
| 310 |
+
"grad_norm": 19.60405731201172,
|
| 311 |
+
"learning_rate": 9.708007224563517e-06,
|
| 312 |
+
"loss": 0.0573,
|
| 313 |
+
"step": 2300
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.8469750889679717,
|
| 317 |
+
"grad_norm": 12.747634887695312,
|
| 318 |
+
"learning_rate": 8.804936785069236e-06,
|
| 319 |
+
"loss": 0.0587,
|
| 320 |
+
"step": 2400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.8469750889679717,
|
| 324 |
+
"eval_accuracy": 0.9012601927353595,
|
| 325 |
+
"eval_f1": 0.9012397677542721,
|
| 326 |
+
"eval_loss": 0.3955250680446625,
|
| 327 |
+
"eval_matthews_correlation": 0.8026222319497477,
|
| 328 |
+
"eval_precision": 0.9014138348009262,
|
| 329 |
+
"eval_recall": 0.901208423433808,
|
| 330 |
+
"eval_runtime": 1.4171,
|
| 331 |
+
"eval_samples_per_second": 4759.731,
|
| 332 |
+
"eval_steps_per_second": 74.801,
|
| 333 |
+
"step": 2400
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.9655990510083035,
|
| 337 |
+
"grad_norm": 13.178675651550293,
|
| 338 |
+
"learning_rate": 7.901866345574955e-06,
|
| 339 |
+
"loss": 0.0569,
|
| 340 |
+
"step": 2500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.0842230130486357,
|
| 344 |
+
"grad_norm": 0.011187891475856304,
|
| 345 |
+
"learning_rate": 6.998795906080675e-06,
|
| 346 |
+
"loss": 0.0263,
|
| 347 |
+
"step": 2600
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.0842230130486357,
|
| 351 |
+
"eval_accuracy": 0.9057079318013344,
|
| 352 |
+
"eval_f1": 0.9057078799868117,
|
| 353 |
+
"eval_loss": 0.525695264339447,
|
| 354 |
+
"eval_matthews_correlation": 0.8114565321991912,
|
| 355 |
+
"eval_precision": 0.9057254122582752,
|
| 356 |
+
"eval_recall": 0.9057311199609897,
|
| 357 |
+
"eval_runtime": 1.4153,
|
| 358 |
+
"eval_samples_per_second": 4765.722,
|
| 359 |
+
"eval_steps_per_second": 74.895,
|
| 360 |
+
"step": 2600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.202846975088968,
|
| 364 |
+
"grad_norm": 0.2136336714029312,
|
| 365 |
+
"learning_rate": 6.104756170981336e-06,
|
| 366 |
+
"loss": 0.011,
|
| 367 |
+
"step": 2700
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 3.3214709371293,
|
| 371 |
+
"grad_norm": 33.0368766784668,
|
| 372 |
+
"learning_rate": 5.201685731487056e-06,
|
| 373 |
+
"loss": 0.018,
|
| 374 |
+
"step": 2800
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.3214709371293,
|
| 378 |
+
"eval_accuracy": 0.9057079318013344,
|
| 379 |
+
"eval_f1": 0.9056997050145418,
|
| 380 |
+
"eval_loss": 0.6456906199455261,
|
| 381 |
+
"eval_matthews_correlation": 0.8117977167650796,
|
| 382 |
+
"eval_precision": 0.9060113235426336,
|
| 383 |
+
"eval_recall": 0.905786424375302,
|
| 384 |
+
"eval_runtime": 1.4245,
|
| 385 |
+
"eval_samples_per_second": 4734.973,
|
| 386 |
+
"eval_steps_per_second": 74.412,
|
| 387 |
+
"step": 2800
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.4400948991696323,
|
| 391 |
+
"grad_norm": 0.03287828713655472,
|
| 392 |
+
"learning_rate": 4.2986152919927755e-06,
|
| 393 |
+
"loss": 0.0134,
|
| 394 |
+
"step": 2900
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 3.5587188612099645,
|
| 398 |
+
"grad_norm": 0.05251970514655113,
|
| 399 |
+
"learning_rate": 3.395544852498495e-06,
|
| 400 |
+
"loss": 0.0197,
|
| 401 |
+
"step": 3000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.5587188612099645,
|
| 405 |
+
"eval_accuracy": 0.9027427724240178,
|
| 406 |
+
"eval_f1": 0.9027319948057138,
|
| 407 |
+
"eval_loss": 0.5632529258728027,
|
| 408 |
+
"eval_matthews_correlation": 0.805927089741698,
|
| 409 |
+
"eval_precision": 0.9030994533926766,
|
| 410 |
+
"eval_recall": 0.9028276821717736,
|
| 411 |
+
"eval_runtime": 1.4184,
|
| 412 |
+
"eval_samples_per_second": 4755.316,
|
| 413 |
+
"eval_steps_per_second": 74.731,
|
| 414 |
+
"step": 3000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.6773428232502967,
|
| 418 |
+
"grad_norm": 0.18964755535125732,
|
| 419 |
+
"learning_rate": 2.4924744130042145e-06,
|
| 420 |
+
"loss": 0.0103,
|
| 421 |
+
"step": 3100
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 3.795966785290629,
|
| 425 |
+
"grad_norm": 2.074934244155884,
|
| 426 |
+
"learning_rate": 1.5894039735099338e-06,
|
| 427 |
+
"loss": 0.0067,
|
| 428 |
+
"step": 3200
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.795966785290629,
|
| 432 |
+
"eval_accuracy": 0.9052631578947369,
|
| 433 |
+
"eval_f1": 0.9052587514243154,
|
| 434 |
+
"eval_loss": 0.6363104581832886,
|
| 435 |
+
"eval_matthews_correlation": 0.8107917228123425,
|
| 436 |
+
"eval_precision": 0.905463923256376,
|
| 437 |
+
"eval_recall": 0.9053278109809421,
|
| 438 |
+
"eval_runtime": 1.4184,
|
| 439 |
+
"eval_samples_per_second": 4755.362,
|
| 440 |
+
"eval_steps_per_second": 74.732,
|
| 441 |
+
"step": 3200
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.914590747330961,
|
| 445 |
+
"grad_norm": 0.007920457050204277,
|
| 446 |
+
"learning_rate": 6.863335340156533e-07,
|
| 447 |
+
"loss": 0.0084,
|
| 448 |
+
"step": 3300
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 4.0,
|
| 452 |
+
"step": 3372,
|
| 453 |
+
"total_flos": 5866539036180480.0,
|
| 454 |
+
"train_loss": 0.1323915239189302,
|
| 455 |
+
"train_runtime": 204.5834,
|
| 456 |
+
"train_samples_per_second": 1054.865,
|
| 457 |
+
"train_steps_per_second": 16.482
|
| 458 |
+
}
|
| 459 |
+
],
|
| 460 |
+
"logging_steps": 100,
|
| 461 |
+
"max_steps": 3372,
|
| 462 |
+
"num_input_tokens_seen": 0,
|
| 463 |
+
"num_train_epochs": 4,
|
| 464 |
+
"save_steps": 200,
|
| 465 |
+
"stateful_callbacks": {
|
| 466 |
+
"TrainerControl": {
|
| 467 |
+
"args": {
|
| 468 |
+
"should_epoch_stop": false,
|
| 469 |
+
"should_evaluate": false,
|
| 470 |
+
"should_log": false,
|
| 471 |
+
"should_save": true,
|
| 472 |
+
"should_training_stop": true
|
| 473 |
+
},
|
| 474 |
+
"attributes": {}
|
| 475 |
+
}
|
| 476 |
+
},
|
| 477 |
+
"total_flos": 5866539036180480.0,
|
| 478 |
+
"train_batch_size": 64,
|
| 479 |
+
"trial_name": null,
|
| 480 |
+
"trial_params": null
|
| 481 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3437ac5717655ab79710df94f304f8369fe5dc9bb162c16af1fb1dd819b7b6e
|
| 3 |
+
size 5368
|