Training in progress, step 3140, 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 sha256:4325c83eeaaab353f576a0884a71791cc1d10d022f7ce5df9bc7909f2b326b7c
|
| 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:f1ae5f00c354813d470dc5d2652f42b52bc5fd547433d7a4f128eb30bb49a691
|
| 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:e3dbf16553ca10ca422c033d8d9e4b9a17b9a6eb512c4a659d5e962c9f59e34a
|
| 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 sha256:5388f4e8040f2763e3ad91c567cc7c5a914c75d4a7373057013d5cb7818a95b7
|
| 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,
|
|
@@ -3148,6 +3148,16 @@
|
|
| 3148 |
"mean_token_accuracy": 0.7852855637669564,
|
| 3149 |
"num_tokens": 14566458.0,
|
| 3150 |
"step": 3130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3151 |
}
|
| 3152 |
],
|
| 3153 |
"logging_steps": 10,
|
|
@@ -3167,7 +3177,7 @@
|
|
| 3167 |
"attributes": {}
|
| 3168 |
}
|
| 3169 |
},
|
| 3170 |
-
"total_flos": 6.
|
| 3171 |
"train_batch_size": 4,
|
| 3172 |
"trial_name": null,
|
| 3173 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6698666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3140,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3148 |
"mean_token_accuracy": 0.7852855637669564,
|
| 3149 |
"num_tokens": 14566458.0,
|
| 3150 |
"step": 3130
|
| 3151 |
+
},
|
| 3152 |
+
{
|
| 3153 |
+
"entropy": 1.002537302672863,
|
| 3154 |
+
"epoch": 0.6698666666666667,
|
| 3155 |
+
"grad_norm": 0.21786057949066162,
|
| 3156 |
+
"learning_rate": 7.773892557162274e-05,
|
| 3157 |
+
"loss": 1.063007640838623,
|
| 3158 |
+
"mean_token_accuracy": 0.7521986544132233,
|
| 3159 |
+
"num_tokens": 14620140.0,
|
| 3160 |
+
"step": 3140
|
| 3161 |
}
|
| 3162 |
],
|
| 3163 |
"logging_steps": 10,
|
|
|
|
| 3177 |
"attributes": {}
|
| 3178 |
}
|
| 3179 |
},
|
| 3180 |
+
"total_flos": 6.922965276734362e+16,
|
| 3181 |
"train_batch_size": 4,
|
| 3182 |
"trial_name": null,
|
| 3183 |
"trial_params": null
|