Training in progress, step 4390, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a93ca27c93bb18118dc8faf2e9e6f8dd528574415ecd725b43e22e5bed162969
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1087e683ebd568a145ddfabb7d2efe7d820451cbb4ec74cd3bab8abd48801ea
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3240f0aebc4d6a296fd2d5c3d89b0dfb51f76d5bee9087d1bdcb98f947fcc35d
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13a20148b8ca05863768cad01be7d695bc69f08669f517b5f3fd3a6d6e738c47
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -4398,6 +4398,16 @@
|
|
| 4398 |
"mean_token_accuracy": 0.7675649732351303,
|
| 4399 |
"num_tokens": 20384687.0,
|
| 4400 |
"step": 4380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4401 |
}
|
| 4402 |
],
|
| 4403 |
"logging_steps": 10,
|
|
@@ -4417,7 +4427,7 @@
|
|
| 4417 |
"attributes": {}
|
| 4418 |
}
|
| 4419 |
},
|
| 4420 |
-
"total_flos": 9.
|
| 4421 |
"train_batch_size": 4,
|
| 4422 |
"trial_name": null,
|
| 4423 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9365333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4398 |
"mean_token_accuracy": 0.7675649732351303,
|
| 4399 |
"num_tokens": 20384687.0,
|
| 4400 |
"step": 4380
|
| 4401 |
+
},
|
| 4402 |
+
{
|
| 4403 |
+
"entropy": 0.9403703153133393,
|
| 4404 |
+
"epoch": 0.9365333333333333,
|
| 4405 |
+
"grad_norm": 0.23416976630687714,
|
| 4406 |
+
"learning_rate": 5.773966098814579e-05,
|
| 4407 |
+
"loss": 1.0653534889221192,
|
| 4408 |
+
"mean_token_accuracy": 0.764773941040039,
|
| 4409 |
+
"num_tokens": 20432372.0,
|
| 4410 |
+
"step": 4390
|
| 4411 |
}
|
| 4412 |
],
|
| 4413 |
"logging_steps": 10,
|
|
|
|
| 4427 |
"attributes": {}
|
| 4428 |
}
|
| 4429 |
},
|
| 4430 |
+
"total_flos": 9.673928307549082e+16,
|
| 4431 |
"train_batch_size": 4,
|
| 4432 |
"trial_name": null,
|
| 4433 |
"trial_params": null
|