Training in progress, epoch 7, 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 2239622772
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcb7c732da4b2a52d9ab572e9f0256aaa611d1c3c4749adeef14c3a01acff708
|
| 3 |
size 2239622772
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4479480977
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a32fae39eb24dd15598de7ef11da03c2ace5a69c6609c9b987d43c80b6f005d
|
| 3 |
size 4479480977
|
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 sha256:104c6f000557e8d1a5b1d392bc5868658285737e2ecb2da709ed8e19e45715d0
|
| 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:ee805eb4c7ef2b7ea2677b099655b11650eb14c11114d04fa36fb582d9b02f63
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7774524158125915,
|
| 3 |
"best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
|
| 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,
|
|
@@ -75,6 +75,15 @@
|
|
| 75 |
"eval_samples_per_second": 12.213,
|
| 76 |
"eval_steps_per_second": 6.107,
|
| 77 |
"step": 1194
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
}
|
| 79 |
],
|
| 80 |
"logging_steps": 500,
|
|
@@ -94,7 +103,7 @@
|
|
| 94 |
"attributes": {}
|
| 95 |
}
|
| 96 |
},
|
| 97 |
-
"total_flos":
|
| 98 |
"train_batch_size": 2,
|
| 99 |
"trial_name": null,
|
| 100 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7774524158125915,
|
| 3 |
"best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1393,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 75 |
"eval_samples_per_second": 12.213,
|
| 76 |
"eval_steps_per_second": 6.107,
|
| 77 |
"step": 1194
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 7.0,
|
| 81 |
+
"eval_accuracy": 0.7723279648609077,
|
| 82 |
+
"eval_loss": 1.2653732299804688,
|
| 83 |
+
"eval_runtime": 110.9037,
|
| 84 |
+
"eval_samples_per_second": 12.317,
|
| 85 |
+
"eval_steps_per_second": 6.158,
|
| 86 |
+
"step": 1393
|
| 87 |
}
|
| 88 |
],
|
| 89 |
"logging_steps": 500,
|
|
|
|
| 103 |
"attributes": {}
|
| 104 |
}
|
| 105 |
},
|
| 106 |
+
"total_flos": 2.068981985784672e+16,
|
| 107 |
"train_batch_size": 2,
|
| 108 |
"trial_name": null,
|
| 109 |
"trial_params": null
|