Training in progress, step 39, 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 80792096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b669ce6778e978f18bfc835dc112f5d29cffef557762c00261248441a0763696
|
| 3 |
size 80792096
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 41459700
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:144cd98085a035e9437b9b2b183fb8612de14e097457bba2e252305c7a4c3148
|
| 3 |
size 41459700
|
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:a63f420b9e7de84bbc3c5a80fdd9facfc42c1cda1e04aef6966e66fbe6f161f1
|
| 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 sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
|
| 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": 0.
|
| 5 |
"eval_steps": 10,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -66,6 +66,28 @@
|
|
| 66 |
"learning_rate": 6.91341716182545e-05,
|
| 67 |
"loss": 1.9288,
|
| 68 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
}
|
| 70 |
],
|
| 71 |
"logging_steps": 5,
|
|
@@ -85,7 +107,7 @@
|
|
| 85 |
"attributes": {}
|
| 86 |
}
|
| 87 |
},
|
| 88 |
-
"total_flos":
|
| 89 |
"train_batch_size": 2,
|
| 90 |
"trial_name": null,
|
| 91 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.048795746011886146,
|
| 5 |
"eval_steps": 10,
|
| 6 |
+
"global_step": 39,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 66 |
"learning_rate": 6.91341716182545e-05,
|
| 67 |
"loss": 1.9288,
|
| 68 |
"step": 25
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.03753518923991242,
|
| 72 |
+
"grad_norm": 3.5155556201934814,
|
| 73 |
+
"learning_rate": 5e-05,
|
| 74 |
+
"loss": 1.8595,
|
| 75 |
+
"step": 30
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.03753518923991242,
|
| 79 |
+
"eval_loss": 1.6997840404510498,
|
| 80 |
+
"eval_runtime": 21.0783,
|
| 81 |
+
"eval_samples_per_second": 15.988,
|
| 82 |
+
"eval_steps_per_second": 8.018,
|
| 83 |
+
"step": 30
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.043791054113231156,
|
| 87 |
+
"grad_norm": 2.9763023853302,
|
| 88 |
+
"learning_rate": 3.086582838174551e-05,
|
| 89 |
+
"loss": 1.4677,
|
| 90 |
+
"step": 35
|
| 91 |
}
|
| 92 |
],
|
| 93 |
"logging_steps": 5,
|
|
|
|
| 107 |
"attributes": {}
|
| 108 |
}
|
| 109 |
},
|
| 110 |
+
"total_flos": 6796280579751936.0,
|
| 111 |
"train_batch_size": 2,
|
| 112 |
"trial_name": null,
|
| 113 |
"trial_params": null
|