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 500979600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73cb1de9795f9244798c81b10664a1864adbac5c3c1f1c93d95c4a7fc35b7e7e
|
| 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 sha256:1820385896fc929ffa814e08788db90c78c1c1e63e828c4412a6a4c41629f04f
|
| 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 sha256:546a738b86213b333d2782e837ecccc14f5a096cc06a03cbcc48c59eac1b89b4
|
| 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 sha256:7169933c93dad80ba74233ec4e9ff102caa4da23f9c8ede354de3ba84986efd5
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.354698896408081,
|
| 3 |
"best_model_checkpoint": "./opt_trained/checkpoint-110",
|
| 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,
|
|
@@ -47,6 +47,14 @@
|
|
| 47 |
"eval_samples_per_second": 37.23,
|
| 48 |
"eval_steps_per_second": 9.307,
|
| 49 |
"step": 110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
}
|
| 51 |
],
|
| 52 |
"logging_steps": 500,
|
|
@@ -66,7 +74,7 @@
|
|
| 66 |
"attributes": {}
|
| 67 |
}
|
| 68 |
},
|
| 69 |
-
"total_flos":
|
| 70 |
"train_batch_size": 16,
|
| 71 |
"trial_name": null,
|
| 72 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 1.354698896408081,
|
| 3 |
"best_model_checkpoint": "./opt_trained/checkpoint-110",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 132,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 47 |
"eval_samples_per_second": 37.23,
|
| 48 |
"eval_steps_per_second": 9.307,
|
| 49 |
"step": 110
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 6.0,
|
| 53 |
+
"eval_loss": 1.3555606603622437,
|
| 54 |
+
"eval_runtime": 8.0406,
|
| 55 |
+
"eval_samples_per_second": 37.311,
|
| 56 |
+
"eval_steps_per_second": 9.328,
|
| 57 |
+
"step": 132
|
| 58 |
}
|
| 59 |
],
|
| 60 |
"logging_steps": 500,
|
|
|
|
| 74 |
"attributes": {}
|
| 75 |
}
|
| 76 |
},
|
| 77 |
+
"total_flos": 4256520689664000.0,
|
| 78 |
"train_batch_size": 16,
|
| 79 |
"trial_name": null,
|
| 80 |
"trial_params": null
|