Training in progress, step 4270, 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:f89da48a68fcc55e3d138692cbeb28e6b4f96d3f71a659a578517d55144d4d3a
|
| 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:d1cbe1676c2ef867fa5de11325371bf92dda3e274c31cf8003b52d3620847b0d
|
| 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 sha256:7e4681240597c52c68411aa0b9a3792bc73cc13d2ccca7e73b8fbee2aaa4429e
|
| 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 sha256:61b3d2f18fddb8935455b715f83e0fd5895fd8d87e763702cffb720f2517cd02
|
| 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,
|
|
@@ -4278,6 +4278,16 @@
|
|
| 4278 |
"mean_token_accuracy": 0.7473356157541275,
|
| 4279 |
"num_tokens": 19839462.0,
|
| 4280 |
"step": 4260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4281 |
}
|
| 4282 |
],
|
| 4283 |
"logging_steps": 10,
|
|
@@ -4297,7 +4307,7 @@
|
|
| 4297 |
"attributes": {}
|
| 4298 |
}
|
| 4299 |
},
|
| 4300 |
-
"total_flos": 9.
|
| 4301 |
"train_batch_size": 4,
|
| 4302 |
"trial_name": null,
|
| 4303 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9109333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4278 |
"mean_token_accuracy": 0.7473356157541275,
|
| 4279 |
"num_tokens": 19839462.0,
|
| 4280 |
"step": 4260
|
| 4281 |
+
},
|
| 4282 |
+
{
|
| 4283 |
+
"entropy": 1.0092505671083927,
|
| 4284 |
+
"epoch": 0.9109333333333334,
|
| 4285 |
+
"grad_norm": 0.23689568042755127,
|
| 4286 |
+
"learning_rate": 5.978421984431959e-05,
|
| 4287 |
+
"loss": 1.110377597808838,
|
| 4288 |
+
"mean_token_accuracy": 0.7536325603723526,
|
| 4289 |
+
"num_tokens": 19888786.0,
|
| 4290 |
+
"step": 4270
|
| 4291 |
}
|
| 4292 |
],
|
| 4293 |
"logging_steps": 10,
|
|
|
|
| 4307 |
"attributes": {}
|
| 4308 |
}
|
| 4309 |
},
|
| 4310 |
+
"total_flos": 9.412431815480525e+16,
|
| 4311 |
"train_batch_size": 4,
|
| 4312 |
"trial_name": null,
|
| 4313 |
"trial_params": null
|