Training in progress, step 4210, 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 sha256:0f76044f18c223ade6e0fa98827c1ee3fd8843220ef256b4189991516d30afa6
|
| 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 sha256:749ba94639232768bdd2dba4ae808c1113ca59603ed07c1773a96a9af17872b1
|
| 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 sha256:973af0dae2e3133743e5d6f9d49088be79977f1e1f02b5e8c8bbef892f7c475f
|
| 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 sha256:2dde91e0a99ac4899f68ba4f8e0db73bdbf3d3d25f129208822aef8780406c09
|
| 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,
|
|
@@ -4218,6 +4218,16 @@
|
|
| 4218 |
"mean_token_accuracy": 0.7868136927485466,
|
| 4219 |
"num_tokens": 19564324.0,
|
| 4220 |
"step": 4200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4221 |
}
|
| 4222 |
],
|
| 4223 |
"logging_steps": 10,
|
|
@@ -4237,7 +4247,7 @@
|
|
| 4237 |
"attributes": {}
|
| 4238 |
}
|
| 4239 |
},
|
| 4240 |
-
"total_flos": 9.
|
| 4241 |
"train_batch_size": 4,
|
| 4242 |
"trial_name": null,
|
| 4243 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8981333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4218 |
"mean_token_accuracy": 0.7868136927485466,
|
| 4219 |
"num_tokens": 19564324.0,
|
| 4220 |
"step": 4200
|
| 4221 |
+
},
|
| 4222 |
+
{
|
| 4223 |
+
"entropy": 0.9676721416413784,
|
| 4224 |
+
"epoch": 0.8981333333333333,
|
| 4225 |
+
"grad_norm": 0.3115193843841553,
|
| 4226 |
+
"learning_rate": 6.080038916226436e-05,
|
| 4227 |
+
"loss": 1.0527458190917969,
|
| 4228 |
+
"mean_token_accuracy": 0.7573085993528366,
|
| 4229 |
+
"num_tokens": 19606557.0,
|
| 4230 |
+
"step": 4210
|
| 4231 |
}
|
| 4232 |
],
|
| 4233 |
"logging_steps": 10,
|
|
|
|
| 4247 |
"attributes": {}
|
| 4248 |
}
|
| 4249 |
},
|
| 4250 |
+
"total_flos": 9.27818561262121e+16,
|
| 4251 |
"train_batch_size": 4,
|
| 4252 |
"trial_name": null,
|
| 4253 |
"trial_params": null
|