Training in progress, step 510, 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 2969089584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:521dbfcbe8aeba598eef61643e7eb8774004be7f266f5633e8ffa93a5197a2d1
|
| 3 |
size 2969089584
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1487821532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b3044a95292282a6c1cbc88505f24191169b77db6ee98e29c8cc5aa4bfb6501
|
| 3 |
size 1487821532
|
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 sha256:8fddb80c0d247164da65156fb1e7d443609ccc0a653e90df9922c7b8b469e8a1
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 29.
|
| 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,
|
|
@@ -70,6 +70,13 @@
|
|
| 70 |
"learning_rate": 1.2725963752426379e-06,
|
| 71 |
"loss": 0.0258,
|
| 72 |
"step": 459
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
}
|
| 74 |
],
|
| 75 |
"logging_steps": 51,
|
|
@@ -84,12 +91,12 @@
|
|
| 84 |
"should_evaluate": false,
|
| 85 |
"should_log": false,
|
| 86 |
"should_save": true,
|
| 87 |
-
"should_training_stop":
|
| 88 |
},
|
| 89 |
"attributes": {}
|
| 90 |
}
|
| 91 |
},
|
| 92 |
-
"total_flos": 3.
|
| 93 |
"train_batch_size": 2,
|
| 94 |
"trial_name": null,
|
| 95 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 29.299820466786354,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 510,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 70 |
"learning_rate": 1.2725963752426379e-06,
|
| 71 |
"loss": 0.0258,
|
| 72 |
"step": 459
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 29.299820466786354,
|
| 76 |
+
"grad_norm": 0.2776833474636078,
|
| 77 |
+
"learning_rate": 0.0,
|
| 78 |
+
"loss": 0.0242,
|
| 79 |
+
"step": 510
|
| 80 |
}
|
| 81 |
],
|
| 82 |
"logging_steps": 51,
|
|
|
|
| 91 |
"should_evaluate": false,
|
| 92 |
"should_log": false,
|
| 93 |
"should_save": true,
|
| 94 |
+
"should_training_stop": true
|
| 95 |
},
|
| 96 |
"attributes": {}
|
| 97 |
}
|
| 98 |
},
|
| 99 |
+
"total_flos": 3.4841996401198694e+17,
|
| 100 |
"train_batch_size": 2,
|
| 101 |
"trial_name": null,
|
| 102 |
"trial_params": null
|