Training in progress, epoch 0, checkpoint
Browse files- last-checkpoint/config.json +31 -0
- last-checkpoint/generation_config.json +7 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +48 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/opt-125m",
|
3 |
+
"_remove_final_layer_norm": false,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "relu",
|
6 |
+
"architectures": [
|
7 |
+
"OPTForCausalLM"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"bos_token_id": 2,
|
11 |
+
"do_layer_norm_before": true,
|
12 |
+
"dropout": 0.1,
|
13 |
+
"enable_bias": true,
|
14 |
+
"eos_token_id": 2,
|
15 |
+
"ffn_dim": 3072,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"init_std": 0.02,
|
18 |
+
"layer_norm_elementwise_affine": true,
|
19 |
+
"layerdrop": 0.0,
|
20 |
+
"max_position_embeddings": 2048,
|
21 |
+
"model_type": "opt",
|
22 |
+
"num_attention_heads": 12,
|
23 |
+
"num_hidden_layers": 12,
|
24 |
+
"pad_token_id": 1,
|
25 |
+
"prefix": "</s>",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.47.0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 50272,
|
30 |
+
"word_embed_proj_dim": 768
|
31 |
+
}
|
last-checkpoint/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.47.0"
|
7 |
+
}
|
last-checkpoint/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d503853e3752c1d2acfb70d8010c636331c5361b828446d3a72b4ef7e6e500cd
|
3 |
+
size 500979600
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7564b9dea97b53e6c8165c1f1f78ef564901bfd2a91265ff04d60b76344c60bb
|
3 |
+
size 1002078330
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dba13805ccab6ab361a19ec0b6ab90650597c58b4e25b4c574871d6ae4529d1
|
3 |
+
size 14244
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9dcc1d0e5adec204cacb9a61e6122f6644f24cb70ae169677431c21cadecba0
|
3 |
+
size 1064
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.013350248336792,
|
3 |
+
"best_model_checkpoint": "./opt_trained3/checkpoint-609",
|
4 |
+
"epoch": 0.998769987699877,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 609,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.8200082000820008,
|
13 |
+
"grad_norm": 3.336149215698242,
|
14 |
+
"learning_rate": 9.835913054681877e-05,
|
15 |
+
"loss": 1.0546,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.998769987699877,
|
20 |
+
"eval_loss": 1.013350248336792,
|
21 |
+
"eval_runtime": 259.9403,
|
22 |
+
"eval_samples_per_second": 50.035,
|
23 |
+
"eval_steps_per_second": 12.511,
|
24 |
+
"step": 609
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"logging_steps": 500,
|
28 |
+
"max_steps": 6090,
|
29 |
+
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 10,
|
31 |
+
"save_steps": 500,
|
32 |
+
"stateful_callbacks": {
|
33 |
+
"TrainerControl": {
|
34 |
+
"args": {
|
35 |
+
"should_epoch_stop": false,
|
36 |
+
"should_evaluate": false,
|
37 |
+
"should_log": false,
|
38 |
+
"should_save": true,
|
39 |
+
"should_training_stop": false
|
40 |
+
},
|
41 |
+
"attributes": {}
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"total_flos": 2.419219229184e+16,
|
45 |
+
"train_batch_size": 24,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": null
|
48 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:432b24e0a454c6ba118d533189ffa32a4ef3f0654798d68a647380ab38384532
|
3 |
+
size 5368
|