Training in progress, step 19, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7488f0927a619d71fcdc7ef48d17867c228b7f050bb1b04298efc3a366b2ef97
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45336037841d60cac82e8fafd770016496f6474365602c546c49818675aeec47
|
3 |
size 37430836
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1780254ad6b89550dd7fa94f3166d2d9a30a74d6eb2d0debf230c27d48c34f2b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -119,6 +119,27 @@
|
|
119 |
"learning_rate": 3.2000000000000005e-05,
|
120 |
"loss": 1.8729,
|
121 |
"step": 16
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
122 |
}
|
123 |
],
|
124 |
"logging_steps": 1,
|
@@ -138,7 +159,7 @@
|
|
138 |
"attributes": {}
|
139 |
}
|
140 |
},
|
141 |
-
"total_flos": 2.
|
142 |
"train_batch_size": 4,
|
143 |
"trial_name": null,
|
144 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.05212620027434842,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 19,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
119 |
"learning_rate": 3.2000000000000005e-05,
|
120 |
"loss": 1.8729,
|
121 |
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.04663923182441701,
|
125 |
+
"grad_norm": 0.3689568340778351,
|
126 |
+
"learning_rate": 3.4000000000000007e-05,
|
127 |
+
"loss": 1.8186,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.04938271604938271,
|
132 |
+
"grad_norm": 0.3991197645664215,
|
133 |
+
"learning_rate": 3.6e-05,
|
134 |
+
"loss": 1.8485,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.05212620027434842,
|
139 |
+
"grad_norm": 0.3603827655315399,
|
140 |
+
"learning_rate": 3.8e-05,
|
141 |
+
"loss": 1.8081,
|
142 |
+
"step": 19
|
143 |
}
|
144 |
],
|
145 |
"logging_steps": 1,
|
|
|
159 |
"attributes": {}
|
160 |
}
|
161 |
},
|
162 |
+
"total_flos": 2.379021263113421e+16,
|
163 |
"train_batch_size": 4,
|
164 |
"trial_name": null,
|
165 |
"trial_params": null
|