Training in progress, step 500, checkpoint
Browse files
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/esm2_t12_35M_UR50D",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"EsmForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.01,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"emb_layer_norm_before": false,
|
| 9 |
+
"esmfold_config": null,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.01,
|
| 12 |
+
"hidden_size": 480,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 1920,
|
| 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": 12,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "rotary",
|
| 24 |
+
"token_dropout": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.41.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_list": null,
|
| 29 |
+
"vocab_size": 33
|
| 30 |
+
}
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b791fbecb6b88664aa79f119dff8f288aa75b9b87dd0dd34e19411dbce854289
|
| 3 |
+
size 136000488
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ad68c170613ee4fb6dd9cc941512acc1d3c2e781098dbe881bd4cfe8efeecfc
|
| 3 |
+
size 268176506
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89d109ac320325ce5994a75dba2574533dce01656e0a672c348391e584969cd4
|
| 3 |
+
size 15006
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e63d039dcd74cce40e5b0ae616878e231197e581fdff19eeed08507ad6e3f131
|
| 3 |
+
size 1064
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.06022067112174173,
|
| 5 |
+
"eval_steps": 500,
|
| 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 |
+
"logging_steps": 1000,
|
| 12 |
+
"max_steps": 249060,
|
| 13 |
+
"num_input_tokens_seen": 0,
|
| 14 |
+
"num_train_epochs": 30,
|
| 15 |
+
"save_steps": 500,
|
| 16 |
+
"stateful_callbacks": {
|
| 17 |
+
"TrainerControl": {
|
| 18 |
+
"args": {
|
| 19 |
+
"should_epoch_stop": false,
|
| 20 |
+
"should_evaluate": false,
|
| 21 |
+
"should_log": false,
|
| 22 |
+
"should_save": true,
|
| 23 |
+
"should_training_stop": false
|
| 24 |
+
},
|
| 25 |
+
"attributes": {}
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"total_flos": 2500969120137216.0,
|
| 29 |
+
"train_batch_size": 1,
|
| 30 |
+
"trial_name": null,
|
| 31 |
+
"trial_params": null
|
| 32 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1276c4897e66e0421900646360e62771af8d4766b7f6bc7fb78bb043899c1eed
|
| 3 |
+
size 5112
|