Training in progress, step 3130, 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 sha256:3bbfe00c1ba1c09c4d04368deaf63404868c1f4870af7814d7f420fa3e7adff7
|
| 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 sha256:07bbeb4c05c5dba10d049492552ad0b3686827c29d53626a81aabe093340f41b
|
| 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 sha256:1d70ee58499f6c87ec78098e4c8bebf10e921da4016edd9194284849f517bd96
|
| 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 sha256:2e7450676e9219efb4cdb0d6b5ddd5da561820d0ad1621a7a5c5769cbb9c7dc6
|
| 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,
|
|
@@ -3138,6 +3138,16 @@
|
|
| 3138 |
"mean_token_accuracy": 0.7467011958360672,
|
| 3139 |
"num_tokens": 14526227.0,
|
| 3140 |
"step": 3120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3141 |
}
|
| 3142 |
],
|
| 3143 |
"logging_steps": 10,
|
|
@@ -3157,7 +3167,7 @@
|
|
| 3157 |
"attributes": {}
|
| 3158 |
}
|
| 3159 |
},
|
| 3160 |
-
"total_flos": 6.
|
| 3161 |
"train_batch_size": 4,
|
| 3162 |
"trial_name": null,
|
| 3163 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6677333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3130,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3138 |
"mean_token_accuracy": 0.7467011958360672,
|
| 3139 |
"num_tokens": 14526227.0,
|
| 3140 |
"step": 3120
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"entropy": 0.850496319681406,
|
| 3144 |
+
"epoch": 0.6677333333333333,
|
| 3145 |
+
"grad_norm": 0.37918779253959656,
|
| 3146 |
+
"learning_rate": 7.788275420728123e-05,
|
| 3147 |
+
"loss": 0.914525032043457,
|
| 3148 |
+
"mean_token_accuracy": 0.7852855637669564,
|
| 3149 |
+
"num_tokens": 14566458.0,
|
| 3150 |
+
"step": 3130
|
| 3151 |
}
|
| 3152 |
],
|
| 3153 |
"logging_steps": 10,
|
|
|
|
| 3167 |
"attributes": {}
|
| 3168 |
}
|
| 3169 |
},
|
| 3170 |
+
"total_flos": 6.897869926043443e+16,
|
| 3171 |
"train_batch_size": 4,
|
| 3172 |
"trial_name": null,
|
| 3173 |
"trial_params": null
|