Training in progress, step 4290, 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 sha256:8729848129124fd7df10fe8b2f53a7ac95042ef3410a87b5272d2982e4f87041
|
| 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 sha256:0fba7853b9413e3390a68b2721b7d668fc193c344fb0ec5d4905fe9a87fb0dc7
|
| 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:a0536823bc1731f9854ecdf2f38a02f1943789b983928940075948e0e0decccf
|
| 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:e5cbb02e6da60e945034aeb0d892189c86d83f5f2606a0f897fe49a894d7c804
|
| 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,
|
|
@@ -4298,6 +4298,16 @@
|
|
| 4298 |
"mean_token_accuracy": 0.7762529909610748,
|
| 4299 |
"num_tokens": 19931094.0,
|
| 4300 |
"step": 4280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4301 |
}
|
| 4302 |
],
|
| 4303 |
"logging_steps": 10,
|
|
@@ -4317,7 +4327,7 @@
|
|
| 4317 |
"attributes": {}
|
| 4318 |
}
|
| 4319 |
},
|
| 4320 |
-
"total_flos": 9.
|
| 4321 |
"train_batch_size": 4,
|
| 4322 |
"trial_name": null,
|
| 4323 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9152,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4298 |
"mean_token_accuracy": 0.7762529909610748,
|
| 4299 |
"num_tokens": 19931094.0,
|
| 4300 |
"step": 4280
|
| 4301 |
+
},
|
| 4302 |
+
{
|
| 4303 |
+
"entropy": 0.9774221003055572,
|
| 4304 |
+
"epoch": 0.9152,
|
| 4305 |
+
"grad_norm": 0.23440679907798767,
|
| 4306 |
+
"learning_rate": 5.944453723760367e-05,
|
| 4307 |
+
"loss": 1.0834471702575683,
|
| 4308 |
+
"mean_token_accuracy": 0.7571895673871041,
|
| 4309 |
+
"num_tokens": 19976730.0,
|
| 4310 |
+
"step": 4290
|
| 4311 |
}
|
| 4312 |
],
|
| 4313 |
"logging_steps": 10,
|
|
|
|
| 4327 |
"attributes": {}
|
| 4328 |
}
|
| 4329 |
},
|
| 4330 |
+
"total_flos": 9.45454427778478e+16,
|
| 4331 |
"train_batch_size": 4,
|
| 4332 |
"trial_name": null,
|
| 4333 |
"trial_params": null
|