Training in progress, step 2170, 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 sha256:24244e6a7998c6a6d8fd08a63899b0a99ff0229df4a93b899a4402fb6966618f
|
| 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 sha256:47c85605483e24b33e7e913cdff9000f6465fbb2ce4da1e8b99361c7b546bad7
|
| 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 sha256:10a84bf02e9924e461173db74a7b02d3634cfeec860a3b21ebe7269a82110440
|
| 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 sha256:30abea7aa4d270d5dc2f5fc53ff4372a7dbbff73e412e7ba6dafe81e53a93542
|
| 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,
|
|
@@ -2178,6 +2178,16 @@
|
|
| 2178 |
"mean_token_accuracy": 0.7566891044378281,
|
| 2179 |
"num_tokens": 10020194.0,
|
| 2180 |
"step": 2160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2181 |
}
|
| 2182 |
],
|
| 2183 |
"logging_steps": 10,
|
|
@@ -2197,7 +2207,7 @@
|
|
| 2197 |
"attributes": {}
|
| 2198 |
}
|
| 2199 |
},
|
| 2200 |
-
"total_flos": 4.
|
| 2201 |
"train_batch_size": 4,
|
| 2202 |
"trial_name": null,
|
| 2203 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.4629333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2170,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2178 |
"mean_token_accuracy": 0.7566891044378281,
|
| 2179 |
"num_tokens": 10020194.0,
|
| 2180 |
"step": 2160
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"entropy": 0.961787448823452,
|
| 2184 |
+
"epoch": 0.4629333333333333,
|
| 2185 |
+
"grad_norm": 0.2845711410045624,
|
| 2186 |
+
"learning_rate": 8.98965663006169e-05,
|
| 2187 |
+
"loss": 1.0939053535461425,
|
| 2188 |
+
"mean_token_accuracy": 0.7606314912438392,
|
| 2189 |
+
"num_tokens": 10067865.0,
|
| 2190 |
+
"step": 2170
|
| 2191 |
}
|
| 2192 |
],
|
| 2193 |
"logging_steps": 10,
|
|
|
|
| 2207 |
"attributes": {}
|
| 2208 |
}
|
| 2209 |
},
|
| 2210 |
+
"total_flos": 4.775840703913267e+16,
|
| 2211 |
"train_batch_size": 4,
|
| 2212 |
"trial_name": null,
|
| 2213 |
"trial_params": null
|