Training in progress, step 2210, 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 sha256:0d5162650ef45a19ce4311a20a25d704ce2f83c7282f2aa471fdfffd0698c67d
|
| 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 sha256:880d74736d5c7a8ea85372bd7ae85d6bb032081b54b3d9f04ff15bdafec32656
|
| 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 sha256:7ec598c9c8d8e3b226c23664d2edd7627d15beedca92bf128bfb3c6a9df6ac5d
|
| 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:b174922a9ba45399bf26235083b2592855c68081131934eae05bd9f4a752bb77
|
| 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,
|
|
@@ -2218,6 +2218,16 @@
|
|
| 2218 |
"mean_token_accuracy": 0.755839766561985,
|
| 2219 |
"num_tokens": 10210375.0,
|
| 2220 |
"step": 2200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2221 |
}
|
| 2222 |
],
|
| 2223 |
"logging_steps": 10,
|
|
@@ -2237,7 +2247,7 @@
|
|
| 2237 |
"attributes": {}
|
| 2238 |
}
|
| 2239 |
},
|
| 2240 |
-
"total_flos": 4.
|
| 2241 |
"train_batch_size": 4,
|
| 2242 |
"trial_name": null,
|
| 2243 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.47146666666666665,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2218 |
"mean_token_accuracy": 0.755839766561985,
|
| 2219 |
"num_tokens": 10210375.0,
|
| 2220 |
"step": 2200
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"entropy": 0.9833620935678482,
|
| 2224 |
+
"epoch": 0.47146666666666665,
|
| 2225 |
+
"grad_norm": 0.31400638818740845,
|
| 2226 |
+
"learning_rate": 8.947548143419437e-05,
|
| 2227 |
+
"loss": 1.0525406837463378,
|
| 2228 |
+
"mean_token_accuracy": 0.7570377990603447,
|
| 2229 |
+
"num_tokens": 10258067.0,
|
| 2230 |
+
"step": 2210
|
| 2231 |
}
|
| 2232 |
],
|
| 2233 |
"logging_steps": 10,
|
|
|
|
| 2247 |
"attributes": {}
|
| 2248 |
}
|
| 2249 |
},
|
| 2250 |
+
"total_flos": 4.863279260890214e+16,
|
| 2251 |
"train_batch_size": 4,
|
| 2252 |
"trial_name": null,
|
| 2253 |
"trial_params": null
|