Training in progress, epoch 9, 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 1476713628
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5694a7255cc1234b09e13f63a12b42d96f34e32f40a5cbc560987864b913faf4
|
| 3 |
size 1476713628
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2953659629
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69d3ffe768c399a428e1319e382826c8136c7462cb28bde5e99a1d8d41b10757
|
| 3 |
size 2953659629
|
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 sha256:104accde398aea5178b47634f177e17064714f138801ca956369778c71ddfcaa
|
| 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:a66bc7346a88fe9fe198bcb7770fa48175a412d9d55edf8c37c58498b9538d78
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7364568081991215,
|
| 3 |
"best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-447",
|
| 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,
|
|
@@ -88,6 +88,15 @@
|
|
| 88 |
"eval_samples_per_second": 26.42,
|
| 89 |
"eval_steps_per_second": 3.307,
|
| 90 |
"step": 447
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
}
|
| 92 |
],
|
| 93 |
"logging_steps": 500,
|
|
@@ -102,12 +111,12 @@
|
|
| 102 |
"should_evaluate": false,
|
| 103 |
"should_log": false,
|
| 104 |
"should_save": true,
|
| 105 |
-
"should_training_stop":
|
| 106 |
},
|
| 107 |
"attributes": {}
|
| 108 |
}
|
| 109 |
},
|
| 110 |
-
"total_flos": 2.
|
| 111 |
"train_batch_size": 8,
|
| 112 |
"trial_name": null,
|
| 113 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7364568081991215,
|
| 3 |
"best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-447",
|
| 4 |
+
"epoch": 9.849246231155778,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 490,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 88 |
"eval_samples_per_second": 26.42,
|
| 89 |
"eval_steps_per_second": 3.307,
|
| 90 |
"step": 447
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 9.849246231155778,
|
| 94 |
+
"eval_accuracy": 0.7306002928257687,
|
| 95 |
+
"eval_loss": 0.6873601675033569,
|
| 96 |
+
"eval_runtime": 51.5519,
|
| 97 |
+
"eval_samples_per_second": 26.498,
|
| 98 |
+
"eval_steps_per_second": 3.317,
|
| 99 |
+
"step": 490
|
| 100 |
}
|
| 101 |
],
|
| 102 |
"logging_steps": 500,
|
|
|
|
| 111 |
"should_evaluate": false,
|
| 112 |
"should_log": false,
|
| 113 |
"should_save": true,
|
| 114 |
+
"should_training_stop": true
|
| 115 |
},
|
| 116 |
"attributes": {}
|
| 117 |
}
|
| 118 |
},
|
| 119 |
+
"total_flos": 2.91113043225984e+16,
|
| 120 |
"train_batch_size": 8,
|
| 121 |
"trial_name": null,
|
| 122 |
"trial_params": null
|