Training in progress, epoch 11, 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 500979600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c408f993022d87ffeadd2365ed7494f1b456c5c1291f2bb376a18c621f77183
|
| 3 |
size 500979600
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1002078330
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ee0ac80c40130b527841f63c414015f68ceaac0e29ef5ad311b003d0f378d6d
|
| 3 |
size 1002078330
|
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 sha256:379dad426960eae5c3c9028ee1b85f1d5429a4e2331d6e3a1f81cd737e000d07
|
| 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 sha256:6b4eac702da66c6639da79428ff8df52283f3e77ca66f222977d4fe4ff13ca1f
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "./opt_trained/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,
|
|
@@ -87,6 +87,14 @@
|
|
| 87 |
"eval_samples_per_second": 37.274,
|
| 88 |
"eval_steps_per_second": 9.318,
|
| 89 |
"step": 220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
}
|
| 91 |
],
|
| 92 |
"logging_steps": 500,
|
|
@@ -106,7 +114,7 @@
|
|
| 106 |
"attributes": {}
|
| 107 |
}
|
| 108 |
},
|
| 109 |
-
"total_flos":
|
| 110 |
"train_batch_size": 16,
|
| 111 |
"trial_name": null,
|
| 112 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3360599279403687,
|
| 3 |
+
"best_model_checkpoint": "./opt_trained/checkpoint-242",
|
| 4 |
+
"epoch": 11.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 242,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 87 |
"eval_samples_per_second": 37.274,
|
| 88 |
"eval_steps_per_second": 9.318,
|
| 89 |
"step": 220
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 11.0,
|
| 93 |
+
"eval_loss": 1.3360599279403687,
|
| 94 |
+
"eval_runtime": 8.0639,
|
| 95 |
+
"eval_samples_per_second": 37.203,
|
| 96 |
+
"eval_steps_per_second": 9.301,
|
| 97 |
+
"step": 242
|
| 98 |
}
|
| 99 |
],
|
| 100 |
"logging_steps": 500,
|
|
|
|
| 114 |
"attributes": {}
|
| 115 |
}
|
| 116 |
},
|
| 117 |
+
"total_flos": 7803621264384000.0,
|
| 118 |
"train_batch_size": 16,
|
| 119 |
"trial_name": null,
|
| 120 |
"trial_params": null
|