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 +427 -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 sha256:53d20487ac393414c3ebdba6aba2219326ddda9ecc46153f56e175330ee22b13
|
| 3 |
+
size 465662960
|
optimizer_state_dict.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22dadd6131e1d89ac05f5bf5d09fd1afc1f07c742c38fe3dc3930c2830c7807c
|
| 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 +1,427 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.42440202832221985,
|
| 3 |
+
"best_model_checkpoint": "output_pipe/prom_core_all/origin/checkpoint-1400",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 2960,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.13513513513513514,
|
| 13 |
+
"grad_norm": 4.876448154449463,
|
| 14 |
+
"learning_rate": 2.9505154639175257e-05,
|
| 15 |
+
"loss": 0.5587,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2702702702702703,
|
| 20 |
+
"grad_norm": 10.904062271118164,
|
| 21 |
+
"learning_rate": 2.8474226804123712e-05,
|
| 22 |
+
"loss": 0.4622,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2702702702702703,
|
| 27 |
+
"eval_accuracy": 0.7640202702702703,
|
| 28 |
+
"eval_f1": 0.7591361843228651,
|
| 29 |
+
"eval_loss": 0.5017790198326111,
|
| 30 |
+
"eval_matthews_correlation": 0.553929575887497,
|
| 31 |
+
"eval_precision": 0.7895071132508147,
|
| 32 |
+
"eval_recall": 0.7649658341702583,
|
| 33 |
+
"eval_runtime": 1.2346,
|
| 34 |
+
"eval_samples_per_second": 4794.903,
|
| 35 |
+
"eval_steps_per_second": 75.325,
|
| 36 |
+
"step": 200
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.40540540540540543,
|
| 40 |
+
"grad_norm": 18.69785499572754,
|
| 41 |
+
"learning_rate": 2.7443298969072163e-05,
|
| 42 |
+
"loss": 0.4702,
|
| 43 |
+
"step": 300
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.5405405405405406,
|
| 47 |
+
"grad_norm": 9.501280784606934,
|
| 48 |
+
"learning_rate": 2.6412371134020618e-05,
|
| 49 |
+
"loss": 0.4564,
|
| 50 |
+
"step": 400
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.5405405405405406,
|
| 54 |
+
"eval_accuracy": 0.7927364864864865,
|
| 55 |
+
"eval_f1": 0.7925830768905244,
|
| 56 |
+
"eval_loss": 0.44070252776145935,
|
| 57 |
+
"eval_matthews_correlation": 0.5858516234344348,
|
| 58 |
+
"eval_precision": 0.7932574236086611,
|
| 59 |
+
"eval_recall": 0.792594574808426,
|
| 60 |
+
"eval_runtime": 1.2306,
|
| 61 |
+
"eval_samples_per_second": 4810.56,
|
| 62 |
+
"eval_steps_per_second": 75.571,
|
| 63 |
+
"step": 400
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.6756756756756757,
|
| 67 |
+
"grad_norm": 3.44538950920105,
|
| 68 |
+
"learning_rate": 2.5381443298969073e-05,
|
| 69 |
+
"loss": 0.4474,
|
| 70 |
+
"step": 500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.8108108108108109,
|
| 74 |
+
"grad_norm": 6.942621231079102,
|
| 75 |
+
"learning_rate": 2.4350515463917527e-05,
|
| 76 |
+
"loss": 0.4292,
|
| 77 |
+
"step": 600
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.8108108108108109,
|
| 81 |
+
"eval_accuracy": 0.8099662162162162,
|
| 82 |
+
"eval_f1": 0.8099642587283544,
|
| 83 |
+
"eval_loss": 0.435224324464798,
|
| 84 |
+
"eval_matthews_correlation": 0.6199452042163561,
|
| 85 |
+
"eval_precision": 0.8099662162162162,
|
| 86 |
+
"eval_recall": 0.8099789881317014,
|
| 87 |
+
"eval_runtime": 1.2285,
|
| 88 |
+
"eval_samples_per_second": 4818.922,
|
| 89 |
+
"eval_steps_per_second": 75.703,
|
| 90 |
+
"step": 600
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.9459459459459459,
|
| 94 |
+
"grad_norm": 9.121011734008789,
|
| 95 |
+
"learning_rate": 2.3319587628865982e-05,
|
| 96 |
+
"loss": 0.4311,
|
| 97 |
+
"step": 700
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.0810810810810811,
|
| 101 |
+
"grad_norm": 7.060180187225342,
|
| 102 |
+
"learning_rate": 2.2288659793814433e-05,
|
| 103 |
+
"loss": 0.3734,
|
| 104 |
+
"step": 800
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.0810810810810811,
|
| 108 |
+
"eval_accuracy": 0.8101351351351351,
|
| 109 |
+
"eval_f1": 0.8100787544330121,
|
| 110 |
+
"eval_loss": 0.44180622696876526,
|
| 111 |
+
"eval_matthews_correlation": 0.6210645788205953,
|
| 112 |
+
"eval_precision": 0.8107856684820405,
|
| 113 |
+
"eval_recall": 0.8102791169148564,
|
| 114 |
+
"eval_runtime": 1.2257,
|
| 115 |
+
"eval_samples_per_second": 4829.832,
|
| 116 |
+
"eval_steps_per_second": 75.874,
|
| 117 |
+
"step": 800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.2162162162162162,
|
| 121 |
+
"grad_norm": 7.786653995513916,
|
| 122 |
+
"learning_rate": 2.1257731958762888e-05,
|
| 123 |
+
"loss": 0.339,
|
| 124 |
+
"step": 900
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.3513513513513513,
|
| 128 |
+
"grad_norm": 8.293940544128418,
|
| 129 |
+
"learning_rate": 2.0226804123711342e-05,
|
| 130 |
+
"loss": 0.3401,
|
| 131 |
+
"step": 1000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.3513513513513513,
|
| 135 |
+
"eval_accuracy": 0.8038851351351352,
|
| 136 |
+
"eval_f1": 0.8034422824044964,
|
| 137 |
+
"eval_loss": 0.4509773850440979,
|
| 138 |
+
"eval_matthews_correlation": 0.6115825968659001,
|
| 139 |
+
"eval_precision": 0.807367729138798,
|
| 140 |
+
"eval_recall": 0.8042229529407885,
|
| 141 |
+
"eval_runtime": 1.2303,
|
| 142 |
+
"eval_samples_per_second": 4811.662,
|
| 143 |
+
"eval_steps_per_second": 75.589,
|
| 144 |
+
"step": 1000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.4864864864864864,
|
| 148 |
+
"grad_norm": 6.160437107086182,
|
| 149 |
+
"learning_rate": 1.9195876288659794e-05,
|
| 150 |
+
"loss": 0.3452,
|
| 151 |
+
"step": 1100
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.6216216216216215,
|
| 155 |
+
"grad_norm": 6.15946102142334,
|
| 156 |
+
"learning_rate": 1.8164948453608248e-05,
|
| 157 |
+
"loss": 0.3358,
|
| 158 |
+
"step": 1200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.6216216216216215,
|
| 162 |
+
"eval_accuracy": 0.8121621621621622,
|
| 163 |
+
"eval_f1": 0.8121611116570571,
|
| 164 |
+
"eval_loss": 0.43393442034721375,
|
| 165 |
+
"eval_matthews_correlation": 0.6244475585739949,
|
| 166 |
+
"eval_precision": 0.8122367519428947,
|
| 167 |
+
"eval_recall": 0.8122108071700818,
|
| 168 |
+
"eval_runtime": 1.2245,
|
| 169 |
+
"eval_samples_per_second": 4834.71,
|
| 170 |
+
"eval_steps_per_second": 75.951,
|
| 171 |
+
"step": 1200
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.7567567567567568,
|
| 175 |
+
"grad_norm": 9.554533004760742,
|
| 176 |
+
"learning_rate": 1.71340206185567e-05,
|
| 177 |
+
"loss": 0.3411,
|
| 178 |
+
"step": 1300
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.8918918918918919,
|
| 182 |
+
"grad_norm": 7.378434181213379,
|
| 183 |
+
"learning_rate": 1.6103092783505154e-05,
|
| 184 |
+
"loss": 0.3387,
|
| 185 |
+
"step": 1400
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.8918918918918919,
|
| 189 |
+
"eval_accuracy": 0.8138513513513513,
|
| 190 |
+
"eval_f1": 0.8138044071785355,
|
| 191 |
+
"eval_loss": 0.42440202832221985,
|
| 192 |
+
"eval_matthews_correlation": 0.6277545331414228,
|
| 193 |
+
"eval_precision": 0.8139716022487501,
|
| 194 |
+
"eval_recall": 0.8137829592367016,
|
| 195 |
+
"eval_runtime": 1.2287,
|
| 196 |
+
"eval_samples_per_second": 4818.127,
|
| 197 |
+
"eval_steps_per_second": 75.69,
|
| 198 |
+
"step": 1400
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.027027027027027,
|
| 202 |
+
"grad_norm": 7.731504440307617,
|
| 203 |
+
"learning_rate": 1.5072164948453609e-05,
|
| 204 |
+
"loss": 0.2999,
|
| 205 |
+
"step": 1500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.1621621621621623,
|
| 209 |
+
"grad_norm": 6.5144171714782715,
|
| 210 |
+
"learning_rate": 1.4041237113402062e-05,
|
| 211 |
+
"loss": 0.1876,
|
| 212 |
+
"step": 1600
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.1621621621621623,
|
| 216 |
+
"eval_accuracy": 0.8087837837837838,
|
| 217 |
+
"eval_f1": 0.8087488584474887,
|
| 218 |
+
"eval_loss": 0.49598315358161926,
|
| 219 |
+
"eval_matthews_correlation": 0.617579161176319,
|
| 220 |
+
"eval_precision": 0.8088488091694348,
|
| 221 |
+
"eval_recall": 0.8087303633652729,
|
| 222 |
+
"eval_runtime": 1.2259,
|
| 223 |
+
"eval_samples_per_second": 4829.218,
|
| 224 |
+
"eval_steps_per_second": 75.864,
|
| 225 |
+
"step": 1600
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.2972972972972974,
|
| 229 |
+
"grad_norm": 7.4392828941345215,
|
| 230 |
+
"learning_rate": 1.3010309278350516e-05,
|
| 231 |
+
"loss": 0.1799,
|
| 232 |
+
"step": 1700
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.4324324324324325,
|
| 236 |
+
"grad_norm": 10.97509765625,
|
| 237 |
+
"learning_rate": 1.197938144329897e-05,
|
| 238 |
+
"loss": 0.1938,
|
| 239 |
+
"step": 1800
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.4324324324324325,
|
| 243 |
+
"eval_accuracy": 0.810304054054054,
|
| 244 |
+
"eval_f1": 0.8102811826035342,
|
| 245 |
+
"eval_loss": 0.5354723334312439,
|
| 246 |
+
"eval_matthews_correlation": 0.6205960823961605,
|
| 247 |
+
"eval_precision": 0.8103291244096114,
|
| 248 |
+
"eval_recall": 0.8102669610999084,
|
| 249 |
+
"eval_runtime": 1.2215,
|
| 250 |
+
"eval_samples_per_second": 4846.477,
|
| 251 |
+
"eval_steps_per_second": 76.136,
|
| 252 |
+
"step": 1800
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.5675675675675675,
|
| 256 |
+
"grad_norm": 11.830049514770508,
|
| 257 |
+
"learning_rate": 1.0948453608247422e-05,
|
| 258 |
+
"loss": 0.1906,
|
| 259 |
+
"step": 1900
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.7027027027027026,
|
| 263 |
+
"grad_norm": 13.479290008544922,
|
| 264 |
+
"learning_rate": 9.917525773195877e-06,
|
| 265 |
+
"loss": 0.1834,
|
| 266 |
+
"step": 2000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.7027027027027026,
|
| 270 |
+
"eval_accuracy": 0.808277027027027,
|
| 271 |
+
"eval_f1": 0.8081915116065802,
|
| 272 |
+
"eval_loss": 0.6007954478263855,
|
| 273 |
+
"eval_matthews_correlation": 0.616732464901666,
|
| 274 |
+
"eval_precision": 0.8085577925672578,
|
| 275 |
+
"eval_recall": 0.8081747912595467,
|
| 276 |
+
"eval_runtime": 1.2278,
|
| 277 |
+
"eval_samples_per_second": 4821.694,
|
| 278 |
+
"eval_steps_per_second": 75.746,
|
| 279 |
+
"step": 2000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.8378378378378377,
|
| 283 |
+
"grad_norm": 12.72508716583252,
|
| 284 |
+
"learning_rate": 8.88659793814433e-06,
|
| 285 |
+
"loss": 0.1862,
|
| 286 |
+
"step": 2100
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.972972972972973,
|
| 290 |
+
"grad_norm": 10.600125312805176,
|
| 291 |
+
"learning_rate": 7.855670103092785e-06,
|
| 292 |
+
"loss": 0.182,
|
| 293 |
+
"step": 2200
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.972972972972973,
|
| 297 |
+
"eval_accuracy": 0.8099662162162162,
|
| 298 |
+
"eval_f1": 0.8095247628533248,
|
| 299 |
+
"eval_loss": 0.5430678129196167,
|
| 300 |
+
"eval_matthews_correlation": 0.6218845218242811,
|
| 301 |
+
"eval_precision": 0.8121990223274058,
|
| 302 |
+
"eval_recall": 0.8096905586070646,
|
| 303 |
+
"eval_runtime": 1.2235,
|
| 304 |
+
"eval_samples_per_second": 4838.563,
|
| 305 |
+
"eval_steps_per_second": 76.011,
|
| 306 |
+
"step": 2200
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.108108108108108,
|
| 310 |
+
"grad_norm": 7.155954837799072,
|
| 311 |
+
"learning_rate": 6.835051546391753e-06,
|
| 312 |
+
"loss": 0.0831,
|
| 313 |
+
"step": 2300
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.2432432432432434,
|
| 317 |
+
"grad_norm": 11.190349578857422,
|
| 318 |
+
"learning_rate": 5.804123711340207e-06,
|
| 319 |
+
"loss": 0.068,
|
| 320 |
+
"step": 2400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.2432432432432434,
|
| 324 |
+
"eval_accuracy": 0.8138513513513513,
|
| 325 |
+
"eval_f1": 0.8137798524725756,
|
| 326 |
+
"eval_loss": 0.8873556852340698,
|
| 327 |
+
"eval_matthews_correlation": 0.6278424881602821,
|
| 328 |
+
"eval_precision": 0.8140834677853808,
|
| 329 |
+
"eval_recall": 0.8137591041632354,
|
| 330 |
+
"eval_runtime": 1.2293,
|
| 331 |
+
"eval_samples_per_second": 4815.887,
|
| 332 |
+
"eval_steps_per_second": 75.655,
|
| 333 |
+
"step": 2400
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.3783783783783785,
|
| 337 |
+
"grad_norm": 3.9781887531280518,
|
| 338 |
+
"learning_rate": 4.77319587628866e-06,
|
| 339 |
+
"loss": 0.0566,
|
| 340 |
+
"step": 2500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.5135135135135136,
|
| 344 |
+
"grad_norm": 4.182361602783203,
|
| 345 |
+
"learning_rate": 3.752577319587629e-06,
|
| 346 |
+
"loss": 0.0682,
|
| 347 |
+
"step": 2600
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.5135135135135136,
|
| 351 |
+
"eval_accuracy": 0.8025337837837838,
|
| 352 |
+
"eval_f1": 0.8023449121382681,
|
| 353 |
+
"eval_loss": 1.001542568206787,
|
| 354 |
+
"eval_matthews_correlation": 0.6069330253978419,
|
| 355 |
+
"eval_precision": 0.8041693671082318,
|
| 356 |
+
"eval_recall": 0.8027652823989849,
|
| 357 |
+
"eval_runtime": 1.2241,
|
| 358 |
+
"eval_samples_per_second": 4836.041,
|
| 359 |
+
"eval_steps_per_second": 75.972,
|
| 360 |
+
"step": 2600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.6486486486486487,
|
| 364 |
+
"grad_norm": 19.823562622070312,
|
| 365 |
+
"learning_rate": 2.7216494845360823e-06,
|
| 366 |
+
"loss": 0.0576,
|
| 367 |
+
"step": 2700
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 3.7837837837837838,
|
| 371 |
+
"grad_norm": 33.46441650390625,
|
| 372 |
+
"learning_rate": 1.6907216494845361e-06,
|
| 373 |
+
"loss": 0.0627,
|
| 374 |
+
"step": 2800
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.7837837837837838,
|
| 378 |
+
"eval_accuracy": 0.808445945945946,
|
| 379 |
+
"eval_f1": 0.8084343797693228,
|
| 380 |
+
"eval_loss": 1.051027774810791,
|
| 381 |
+
"eval_matthews_correlation": 0.6171943889514601,
|
| 382 |
+
"eval_precision": 0.8086652678456729,
|
| 383 |
+
"eval_recall": 0.8085291361187612,
|
| 384 |
+
"eval_runtime": 1.2237,
|
| 385 |
+
"eval_samples_per_second": 4837.925,
|
| 386 |
+
"eval_steps_per_second": 76.001,
|
| 387 |
+
"step": 2800
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.918918918918919,
|
| 391 |
+
"grad_norm": 14.81698989868164,
|
| 392 |
+
"learning_rate": 6.597938144329897e-07,
|
| 393 |
+
"loss": 0.0608,
|
| 394 |
+
"step": 2900
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 4.0,
|
| 398 |
+
"step": 2960,
|
| 399 |
+
"total_flos": 2703390177632256.0,
|
| 400 |
+
"train_loss": 0.2621168656929119,
|
| 401 |
+
"train_runtime": 176.8137,
|
| 402 |
+
"train_samples_per_second": 1071.32,
|
| 403 |
+
"train_steps_per_second": 16.741
|
| 404 |
+
}
|
| 405 |
+
],
|
| 406 |
+
"logging_steps": 100,
|
| 407 |
+
"max_steps": 2960,
|
| 408 |
+
"num_input_tokens_seen": 0,
|
| 409 |
+
"num_train_epochs": 4,
|
| 410 |
+
"save_steps": 200,
|
| 411 |
+
"stateful_callbacks": {
|
| 412 |
+
"TrainerControl": {
|
| 413 |
+
"args": {
|
| 414 |
+
"should_epoch_stop": false,
|
| 415 |
+
"should_evaluate": false,
|
| 416 |
+
"should_log": false,
|
| 417 |
+
"should_save": true,
|
| 418 |
+
"should_training_stop": true
|
| 419 |
+
},
|
| 420 |
+
"attributes": {}
|
| 421 |
+
}
|
| 422 |
+
},
|
| 423 |
+
"total_flos": 2703390177632256.0,
|
| 424 |
+
"train_batch_size": 64,
|
| 425 |
+
"trial_name": null,
|
| 426 |
+
"trial_params": null
|
| 427 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce355f0cec4fee69d40e6620575774a7b22fc132319738968d6d3bbffe802cf2
|
| 3 |
+
size 5368
|