Training in progress, step 1200, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 250422888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ed0c4bb9dd03fb2841edef7fec79acdf89a39acc89bb68d9baba6780d7be5be
|
| 3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 126034975
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e04ef4d45ffebe04d4d0fd11cde8a62cce0132cb5d9feaeab9e756c94a4c20e
|
| 3 |
size 126034975
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e55efe442c59217c9ef0163794cec37755315549abf3750a9e6f3a07556785d3
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 3.
|
| 5 |
"eval_steps": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -72,13 +72,26 @@
|
|
| 72 |
"eval_samples_per_second": 4.007,
|
| 73 |
"eval_steps_per_second": 0.132,
|
| 74 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
}
|
| 76 |
],
|
| 77 |
"logging_steps": 200,
|
| 78 |
"max_steps": 1535,
|
| 79 |
"num_train_epochs": 5,
|
| 80 |
"save_steps": 200,
|
| 81 |
-
"total_flos": 1.
|
| 82 |
"trial_name": null,
|
| 83 |
"trial_params": null
|
| 84 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.9087947882736156,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 1200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 72 |
"eval_samples_per_second": 4.007,
|
| 73 |
"eval_steps_per_second": 0.132,
|
| 74 |
"step": 1000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 3.91,
|
| 78 |
+
"learning_rate": 0.0002,
|
| 79 |
+
"loss": 0.0858,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.91,
|
| 84 |
+
"eval_runtime": 128.986,
|
| 85 |
+
"eval_samples_per_second": 4.0,
|
| 86 |
+
"eval_steps_per_second": 0.132,
|
| 87 |
+
"step": 1200
|
| 88 |
}
|
| 89 |
],
|
| 90 |
"logging_steps": 200,
|
| 91 |
"max_steps": 1535,
|
| 92 |
"num_train_epochs": 5,
|
| 93 |
"save_steps": 200,
|
| 94 |
+
"total_flos": 1.52049400086528e+18,
|
| 95 |
"trial_name": null,
|
| 96 |
"trial_params": null
|
| 97 |
}
|