Training in progress, step 2180, 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 sha256:7a39fb275b783bc5452fdcfdea48eaf5078ba4a25a5087f3acc2973d817ab4d8
|
| 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 sha256:80b111dbf15da74fe616e6afc0e3b74c096802276d01a15d115a66182e756c9f
|
| 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:f90bdee1749f591dfc70db1ad36d11093e7d4fd24288bb105a84234dd0c04894
|
| 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:a0666b25813a2805dfea98332b3af2e5d220b64c251c9e75bc0ea2e42bb3696d
|
| 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,
|
|
@@ -2188,6 +2188,16 @@
|
|
| 2188 |
"mean_token_accuracy": 0.7606314912438392,
|
| 2189 |
"num_tokens": 10067865.0,
|
| 2190 |
"step": 2170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2191 |
}
|
| 2192 |
],
|
| 2193 |
"logging_steps": 10,
|
|
@@ -2207,7 +2217,7 @@
|
|
| 2207 |
"attributes": {}
|
| 2208 |
}
|
| 2209 |
},
|
| 2210 |
-
"total_flos": 4.
|
| 2211 |
"train_batch_size": 4,
|
| 2212 |
"trial_name": null,
|
| 2213 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.4650666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2180,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2188 |
"mean_token_accuracy": 0.7606314912438392,
|
| 2189 |
"num_tokens": 10067865.0,
|
| 2190 |
"step": 2170
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"entropy": 0.8467822209000587,
|
| 2194 |
+
"epoch": 0.4650666666666667,
|
| 2195 |
+
"grad_norm": 0.26253893971443176,
|
| 2196 |
+
"learning_rate": 8.979200897464921e-05,
|
| 2197 |
+
"loss": 0.9104162216186523,
|
| 2198 |
+
"mean_token_accuracy": 0.7799090445041656,
|
| 2199 |
+
"num_tokens": 10112591.0,
|
| 2200 |
+
"step": 2180
|
| 2201 |
}
|
| 2202 |
],
|
| 2203 |
"logging_steps": 10,
|
|
|
|
| 2217 |
"attributes": {}
|
| 2218 |
}
|
| 2219 |
},
|
| 2220 |
+
"total_flos": 4.79722046115072e+16,
|
| 2221 |
"train_batch_size": 4,
|
| 2222 |
"trial_name": null,
|
| 2223 |
"trial_params": null
|