Training in progress, epoch 6, 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 437961724
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfed2f23880a6745436dd2e9ca5359a30b7e69b4a8ed05e920fe077dee3d4a52
|
| 3 |
size 437961724
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 876044538
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ad55aa041e98ebb5239eb39e46a78e0263cc80f9b1605a5031ce1a463611210
|
| 3 |
size 876044538
|
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 sha256:0f206277921017c2986b0ce815257927da56c63993c40895b290bde8c3beb30e
|
| 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 sha256:1380500cb5ce47f6085ce18023f66434aacc2bfc3f43d387430fdbaa4c016dad
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "training_dir/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 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": 41.678,
|
| 103 |
"eval_steps_per_second": 5.21,
|
| 104 |
"step": 625
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
}
|
| 106 |
],
|
| 107 |
"logging_steps": 500,
|
|
@@ -116,12 +135,12 @@
|
|
| 116 |
"should_evaluate": false,
|
| 117 |
"should_log": false,
|
| 118 |
"should_save": true,
|
| 119 |
-
"should_training_stop":
|
| 120 |
},
|
| 121 |
"attributes": {}
|
| 122 |
}
|
| 123 |
},
|
| 124 |
-
"total_flos":
|
| 125 |
"train_batch_size": 16,
|
| 126 |
"trial_name": null,
|
| 127 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6644672849816395,
|
| 3 |
+
"best_model_checkpoint": "training_dir/checkpoint-750",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 750,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 102 |
"eval_samples_per_second": 41.678,
|
| 103 |
"eval_steps_per_second": 5.21,
|
| 104 |
"step": 625
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 0.03926132246851921,
|
| 109 |
+
"learning_rate": 0.0,
|
| 110 |
+
"loss": 0.087,
|
| 111 |
+
"step": 750
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.6748251748251748,
|
| 116 |
+
"eval_f1": 0.6644672849816395,
|
| 117 |
+
"eval_loss": 1.9058291912078857,
|
| 118 |
+
"eval_precision": 0.68431355761444,
|
| 119 |
+
"eval_recall": 0.6748251748251748,
|
| 120 |
+
"eval_runtime": 54.6284,
|
| 121 |
+
"eval_samples_per_second": 41.883,
|
| 122 |
+
"eval_steps_per_second": 5.235,
|
| 123 |
+
"step": 750
|
| 124 |
}
|
| 125 |
],
|
| 126 |
"logging_steps": 500,
|
|
|
|
| 135 |
"should_evaluate": false,
|
| 136 |
"should_log": false,
|
| 137 |
"should_save": true,
|
| 138 |
+
"should_training_stop": true
|
| 139 |
},
|
| 140 |
"attributes": {}
|
| 141 |
}
|
| 142 |
},
|
| 143 |
+
"total_flos": 2429687966832000.0,
|
| 144 |
"train_batch_size": 16,
|
| 145 |
"trial_name": null,
|
| 146 |
"trial_params": null
|