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:acc7efc5ac731fed0225a95e6a6619debcf2385b4b55b86cd89af40df519b46e
|
| 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 sha256:8642788ff9b15322c67b31af5c83e47538f0e8734eb5c8110ac94b13c19fc8eb
|
| 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:c66de8aeca130c769d7a7748933024a1db68486c88d7a55d3b6364277d7e51f2
|
| 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 sha256:38c770930cf4a784f6f3c687a772f7b0f7e7c1fc226d92e5bdca2a293d724a84
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.6301519274711609,
|
| 3 |
"best_model_checkpoint": "./opt_trained3/checkpoint-60",
|
| 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": 50.08,
|
| 48 |
"eval_steps_per_second": 12.52,
|
| 49 |
"step": 75
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
}
|
| 51 |
],
|
| 52 |
"logging_steps": 500,
|
|
@@ -66,7 +74,7 @@
|
|
| 66 |
"attributes": {}
|
| 67 |
}
|
| 68 |
},
|
| 69 |
-
"total_flos":
|
| 70 |
"train_batch_size": 24,
|
| 71 |
"trial_name": null,
|
| 72 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.6301519274711609,
|
| 3 |
"best_model_checkpoint": "./opt_trained3/checkpoint-60",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 90,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 47 |
"eval_samples_per_second": 50.08,
|
| 48 |
"eval_steps_per_second": 12.52,
|
| 49 |
"step": 75
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 6.0,
|
| 53 |
+
"eval_loss": 0.6304347515106201,
|
| 54 |
+
"eval_runtime": 5.9839,
|
| 55 |
+
"eval_samples_per_second": 50.134,
|
| 56 |
+
"eval_steps_per_second": 12.534,
|
| 57 |
+
"step": 90
|
| 58 |
}
|
| 59 |
],
|
| 60 |
"logging_steps": 500,
|
|
|
|
| 74 |
"attributes": {}
|
| 75 |
}
|
| 76 |
},
|
| 77 |
+
"total_flos": 3339633680640000.0,
|
| 78 |
"train_batch_size": 24,
|
| 79 |
"trial_name": null,
|
| 80 |
"trial_params": null
|