Training in progress, step 2200, 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 sha256:438f1b85e775f9e14db91d33aef57bceed98b4eb02d4610a459abebeee5b8135
|
| 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 sha256:64b5ee38f74bd6a0b39ad70ed414f5fcf3911df9add14197c37d1fd9aeaf0650
|
| 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 sha256:675feaa56f6e6458f6d12a8760ab03628bfa72d997dee2fef99ec1c6e9455b67
|
| 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 sha256:64c4d71e5cf8e2a30f4aa098b6b5f83acde56be61c2ac9ddff5603346452afe3
|
| 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,
|
|
@@ -2208,6 +2208,16 @@
|
|
| 2208 |
"mean_token_accuracy": 0.7760828763246537,
|
| 2209 |
"num_tokens": 10159849.0,
|
| 2210 |
"step": 2190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2211 |
}
|
| 2212 |
],
|
| 2213 |
"logging_steps": 10,
|
|
@@ -2227,7 +2237,7 @@
|
|
| 2227 |
"attributes": {}
|
| 2228 |
}
|
| 2229 |
},
|
| 2230 |
-
"total_flos": 4.
|
| 2231 |
"train_batch_size": 4,
|
| 2232 |
"trial_name": null,
|
| 2233 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.4693333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2208 |
"mean_token_accuracy": 0.7760828763246537,
|
| 2209 |
"num_tokens": 10159849.0,
|
| 2210 |
"step": 2190
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"entropy": 0.9931552834808827,
|
| 2214 |
+
"epoch": 0.4693333333333333,
|
| 2215 |
+
"grad_norm": 0.2644927501678467,
|
| 2216 |
+
"learning_rate": 8.95814652801258e-05,
|
| 2217 |
+
"loss": 1.1035637855529785,
|
| 2218 |
+
"mean_token_accuracy": 0.755839766561985,
|
| 2219 |
+
"num_tokens": 10210375.0,
|
| 2220 |
+
"step": 2200
|
| 2221 |
}
|
| 2222 |
],
|
| 2223 |
"logging_steps": 10,
|
|
|
|
| 2237 |
"attributes": {}
|
| 2238 |
}
|
| 2239 |
},
|
| 2240 |
+
"total_flos": 4.841430886481818e+16,
|
| 2241 |
"train_batch_size": 4,
|
| 2242 |
"trial_name": null,
|
| 2243 |
"trial_params": null
|