Training in progress, step 2230, 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 sha256:5657f80fa063ef8a4721b6a2d8db638ad6be08c50dc919e1441dba2bbb203f65
|
| 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 sha256:2ff9e3265ace9be5f45a411677838751fb1200b8af5fd443588d53c940be2ce6
|
| 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 sha256:0b5f328766db583fba371e0415dbbaf7414b513386fd9df34c85bd8d9d250bdb
|
| 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 sha256:80f6540b2aaaca9347789bc6a0e908aeaabc37b24d92ae859626332091dfe801
|
| 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,
|
|
@@ -2238,6 +2238,16 @@
|
|
| 2238 |
"mean_token_accuracy": 0.7476231440901756,
|
| 2239 |
"num_tokens": 10308406.0,
|
| 2240 |
"step": 2220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2241 |
}
|
| 2242 |
],
|
| 2243 |
"logging_steps": 10,
|
|
@@ -2257,7 +2267,7 @@
|
|
| 2257 |
"attributes": {}
|
| 2258 |
}
|
| 2259 |
},
|
| 2260 |
-
"total_flos": 4.
|
| 2261 |
"train_batch_size": 4,
|
| 2262 |
"trial_name": null,
|
| 2263 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.47573333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2238 |
"mean_token_accuracy": 0.7476231440901756,
|
| 2239 |
"num_tokens": 10308406.0,
|
| 2240 |
"step": 2220
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"entropy": 1.0317844092845916,
|
| 2244 |
+
"epoch": 0.47573333333333334,
|
| 2245 |
+
"grad_norm": 0.23253889381885529,
|
| 2246 |
+
"learning_rate": 8.926209609419165e-05,
|
| 2247 |
+
"loss": 1.1079911231994628,
|
| 2248 |
+
"mean_token_accuracy": 0.7472389042377472,
|
| 2249 |
+
"num_tokens": 10361473.0,
|
| 2250 |
+
"step": 2230
|
| 2251 |
}
|
| 2252 |
],
|
| 2253 |
"logging_steps": 10,
|
|
|
|
| 2267 |
"attributes": {}
|
| 2268 |
}
|
| 2269 |
},
|
| 2270 |
+
"total_flos": 4.912710261743002e+16,
|
| 2271 |
"train_batch_size": 4,
|
| 2272 |
"trial_name": null,
|
| 2273 |
"trial_params": null
|