jjoecclark
commited on
Upload 7 files
Browse files- config.json +31 -0
- model-001.safetensors +3 -0
- optimizer-002.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +70 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/esm2_t33_650M_UR50D",
|
3 |
+
"architectures": [
|
4 |
+
"EsmForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_layer_norm_before": false,
|
9 |
+
"esmfold_config": null,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 1280,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5120,
|
15 |
+
"is_folding_model": false,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"mask_token_id": 32,
|
18 |
+
"max_position_embeddings": 1026,
|
19 |
+
"model_type": "esm",
|
20 |
+
"num_attention_heads": 20,
|
21 |
+
"num_hidden_layers": 33,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "rotary",
|
24 |
+
"problem_type": "single_label_classification",
|
25 |
+
"token_dropout": true,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.41.0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_list": null,
|
30 |
+
"vocab_size": 33
|
31 |
+
}
|
model-001.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32482f7fb050e13eb33319c50e5e689db36044fdb7164e4d5ec71cdb291b9c37
|
3 |
+
size 2609497900
|
optimizer-002.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4311b3d585abb86ed0b66c43930c840e5ff81bb20dd4f8663a805b0c5746c389
|
3 |
+
size 5208795055
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfb1e1a22acdb775b607e7afac32daec09267d6abee5854df0a11c80153a957a
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.016960136592388153,
|
3 |
+
"best_model_checkpoint": "./drive/MyDrive/Models/LazBF_ft/checkpoint-2441",
|
4 |
+
"epoch": 0.999795207864018,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2441,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.2047921359819783,
|
13 |
+
"grad_norm": 0.34956222772598267,
|
14 |
+
"learning_rate": 0.00015903318312167147,
|
15 |
+
"loss": 0.077,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.4095842719639566,
|
20 |
+
"grad_norm": 0.20318002998828888,
|
21 |
+
"learning_rate": 0.00011806636624334291,
|
22 |
+
"loss": 0.0315,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6143764079459348,
|
27 |
+
"grad_norm": 0.19855135679244995,
|
28 |
+
"learning_rate": 7.709954936501435e-05,
|
29 |
+
"loss": 0.0255,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.8191685439279132,
|
34 |
+
"grad_norm": 0.213591068983078,
|
35 |
+
"learning_rate": 3.613273248668579e-05,
|
36 |
+
"loss": 0.0219,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.999795207864018,
|
41 |
+
"eval_accuracy": 0.99414,
|
42 |
+
"eval_loss": 0.016960136592388153,
|
43 |
+
"eval_runtime": 42.6528,
|
44 |
+
"eval_samples_per_second": 1172.256,
|
45 |
+
"eval_steps_per_second": 4.595,
|
46 |
+
"step": 2441
|
47 |
+
}
|
48 |
+
],
|
49 |
+
"logging_steps": 500,
|
50 |
+
"max_steps": 2441,
|
51 |
+
"num_input_tokens_seen": 0,
|
52 |
+
"num_train_epochs": 1,
|
53 |
+
"save_steps": 500,
|
54 |
+
"stateful_callbacks": {
|
55 |
+
"TrainerControl": {
|
56 |
+
"args": {
|
57 |
+
"should_epoch_stop": false,
|
58 |
+
"should_evaluate": false,
|
59 |
+
"should_log": false,
|
60 |
+
"should_save": true,
|
61 |
+
"should_training_stop": true
|
62 |
+
},
|
63 |
+
"attributes": {}
|
64 |
+
}
|
65 |
+
},
|
66 |
+
"total_flos": 6.346203400255181e+16,
|
67 |
+
"train_batch_size": 256,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": null
|
70 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34815b98eda78634c8b76dc6e7e6870195ca95bb1e0d281b18a0c5bfc2c2fd79
|
3 |
+
size 5112
|