Training in progress, step 4060, 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 sha256:6f007c2221c1bc301388b79145c614ed983d2542e94080ed22a4b624f9ff1ece
|
| 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 sha256:5da227aa50919d031077db1df0297f7d33c7033e8961040c77fdece9e0c94738
|
| 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 sha256:8b85c092cde13764b6b5711f763d019caf021e33539e4cb4643c1c9318c4c4cc
|
| 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 sha256:14d979ac4950e19d80df1fe5bad94fbbd83051f665822fc85373fc81da166d74
|
| 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,
|
|
@@ -4068,6 +4068,16 @@
|
|
| 4068 |
"mean_token_accuracy": 0.7608293548226357,
|
| 4069 |
"num_tokens": 18891900.0,
|
| 4070 |
"step": 4050
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4071 |
}
|
| 4072 |
],
|
| 4073 |
"logging_steps": 10,
|
|
@@ -4087,7 +4097,7 @@
|
|
| 4087 |
"attributes": {}
|
| 4088 |
}
|
| 4089 |
},
|
| 4090 |
-
"total_flos": 8.
|
| 4091 |
"train_batch_size": 4,
|
| 4092 |
"trial_name": null,
|
| 4093 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8661333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4060,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4068 |
"mean_token_accuracy": 0.7608293548226357,
|
| 4069 |
"num_tokens": 18891900.0,
|
| 4070 |
"step": 4050
|
| 4071 |
+
},
|
| 4072 |
+
{
|
| 4073 |
+
"entropy": 0.9185742639005184,
|
| 4074 |
+
"epoch": 0.8661333333333333,
|
| 4075 |
+
"grad_norm": 0.2510085701942444,
|
| 4076 |
+
"learning_rate": 6.331947817038367e-05,
|
| 4077 |
+
"loss": 0.9962324142456055,
|
| 4078 |
+
"mean_token_accuracy": 0.7723157353699207,
|
| 4079 |
+
"num_tokens": 18938986.0,
|
| 4080 |
+
"step": 4060
|
| 4081 |
}
|
| 4082 |
],
|
| 4083 |
"logging_steps": 10,
|
|
|
|
| 4097 |
"attributes": {}
|
| 4098 |
}
|
| 4099 |
},
|
| 4100 |
+
"total_flos": 8.96706706808402e+16,
|
| 4101 |
"train_batch_size": 4,
|
| 4102 |
"trial_name": null,
|
| 4103 |
"trial_params": null
|