Francesco0101
commited on
Commit
•
438b307
1
Parent(s):
db4ebbe
Training in progress, step 6000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267835644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:989292e28f46dd6f0df4532e0dda10c72a82df895ad59806e1ad4eb0f00f3737
|
3 |
size 267835644
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535733434
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8f1f84bc456597fb5c2700b82cca9533a78045c18a462826756c01550f7ba36
|
3 |
size 535733434
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49210297757a71fde0369659ddff3f1ed351704ff09f7c069bf6fb7a6ca02751
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:196ac9dde7c4927b37b8bc53da35fc7da10f580fa77c1ee80824d56438d0a24c
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.6979166210878224,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-5000",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -102,6 +102,25 @@
|
|
102 |
"eval_samples_per_second": 88.162,
|
103 |
"eval_steps_per_second": 11.02,
|
104 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1000,
|
@@ -121,7 +140,7 @@
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
-
"total_flos":
|
125 |
"train_batch_size": 8,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.6979166210878224,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-5000",
|
4 |
+
"epoch": 0.6357952739217971,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 6000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_samples_per_second": 88.162,
|
103 |
"eval_steps_per_second": 11.02,
|
104 |
"step": 5000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.6357952739217971,
|
108 |
+
"grad_norm": 7.738587379455566,
|
109 |
+
"learning_rate": 9.414083306700758e-06,
|
110 |
+
"loss": 0.4964,
|
111 |
+
"step": 6000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.6357952739217971,
|
115 |
+
"eval_accuracy": 0.7106643356643356,
|
116 |
+
"eval_f1": 0.6933251320034988,
|
117 |
+
"eval_loss": 0.7791977524757385,
|
118 |
+
"eval_precision": 0.7149995516226468,
|
119 |
+
"eval_recall": 0.7106643356643356,
|
120 |
+
"eval_runtime": 26.0573,
|
121 |
+
"eval_samples_per_second": 87.806,
|
122 |
+
"eval_steps_per_second": 10.976,
|
123 |
+
"step": 6000
|
124 |
}
|
125 |
],
|
126 |
"logging_steps": 1000,
|
|
|
140 |
"attributes": {}
|
141 |
}
|
142 |
},
|
143 |
+
"total_flos": 5815153429751520.0,
|
144 |
"train_batch_size": 8,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|