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 48679352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf4b57037cc242fba57750a24dac34ffdae3bf14b1964090cfbc19125cad0a10
|
| 3 |
size 48679352
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 25152500
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:595320d94c4684b2204967470bf29e633b9a996020b6fa4b82207ea45adf4f04
|
| 3 |
size 25152500
|
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 sha256:2199ce5e05ee91e4aa3d52568ad0d6eafbca4bbe86b1ebc03789afca0f7ed010
|
| 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": 1.7503,
|
| 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": 0.035286134358742366,
|
| 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": 1.7503,
|
| 68 |
"step": 25
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.027143180275955667,
|
| 72 |
+
"grad_norm": 1.8646595478057861,
|
| 73 |
+
"learning_rate": 5e-05,
|
| 74 |
+
"loss": 1.8562,
|
| 75 |
+
"step": 30
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.027143180275955667,
|
| 79 |
+
"eval_loss": 1.7833797931671143,
|
| 80 |
+
"eval_runtime": 26.9697,
|
| 81 |
+
"eval_samples_per_second": 17.279,
|
| 82 |
+
"eval_steps_per_second": 8.639,
|
| 83 |
+
"step": 30
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.03166704365528161,
|
| 87 |
+
"grad_norm": 1.6002821922302246,
|
| 88 |
+
"learning_rate": 3.086582838174551e-05,
|
| 89 |
+
"loss": 1.7892,
|
| 90 |
+
"step": 35
|
| 91 |
}
|
| 92 |
],
|
| 93 |
"logging_steps": 5,
|
|
|
|
| 107 |
"attributes": {}
|
| 108 |
}
|
| 109 |
},
|
| 110 |
+
"total_flos": 4174338274099200.0,
|
| 111 |
"train_batch_size": 2,
|
| 112 |
"trial_name": null,
|
| 113 |
"trial_params": null
|