Training in progress, step 1220, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2497385b4742e349abf8df0b08fd4c377c00a7d9032a11ea8650cba44007046a
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2d0e8513a3b02a65d0194f8c110e74d9e30041a09a6c03f8a3d9760a0fd98be
|
| 3 |
size 14709
|
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 sha256:901df7a6692bd414cc152f3101dc9f9099c57746acbb00382f205c0cafb1af3a
|
| 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": 9.
|
| 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,
|
|
@@ -2186,6 +2186,24 @@
|
|
| 2186 |
"mean_token_accuracy": 0.6541574269533157,
|
| 2187 |
"num_tokens": 4413886.0,
|
| 2188 |
"step": 1210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2189 |
}
|
| 2190 |
],
|
| 2191 |
"logging_steps": 5,
|
|
@@ -2205,7 +2223,7 @@
|
|
| 2205 |
"attributes": {}
|
| 2206 |
}
|
| 2207 |
},
|
| 2208 |
-
"total_flos": 2.
|
| 2209 |
"train_batch_size": 4,
|
| 2210 |
"trial_name": null,
|
| 2211 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.384615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2186 |
"mean_token_accuracy": 0.6541574269533157,
|
| 2187 |
"num_tokens": 4413886.0,
|
| 2188 |
"step": 1210
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 9.346153846153847,
|
| 2192 |
+
"grad_norm": 0.0,
|
| 2193 |
+
"learning_rate": 4.393e-05,
|
| 2194 |
+
"loss": 1.6822,
|
| 2195 |
+
"mean_token_accuracy": 0.6630573570728302,
|
| 2196 |
+
"num_tokens": 4432735.0,
|
| 2197 |
+
"step": 1215
|
| 2198 |
+
},
|
| 2199 |
+
{
|
| 2200 |
+
"epoch": 9.384615384615385,
|
| 2201 |
+
"grad_norm": 0.0,
|
| 2202 |
+
"learning_rate": 4.3905e-05,
|
| 2203 |
+
"loss": 1.7395,
|
| 2204 |
+
"mean_token_accuracy": 0.6511468648910522,
|
| 2205 |
+
"num_tokens": 4450737.0,
|
| 2206 |
+
"step": 1220
|
| 2207 |
}
|
| 2208 |
],
|
| 2209 |
"logging_steps": 5,
|
|
|
|
| 2223 |
"attributes": {}
|
| 2224 |
}
|
| 2225 |
},
|
| 2226 |
+
"total_flos": 2.2564358518800384e+17,
|
| 2227 |
"train_batch_size": 4,
|
| 2228 |
"trial_name": null,
|
| 2229 |
"trial_params": null
|