Training in progress, step 45, 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 15156512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02dd83fe678360832db72d49ab942c66ffeba880f16a5eb53422a0e4d8c77c92
|
3 |
size 15156512
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7825914
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53e1cfebd8ab909e2e0acaa183b57be6dafcd955f3690daf2028cc710981e39b
|
3 |
size 7825914
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60011aba49a65dca3988560527defa4dc19d0ad21df74f6e66309136a9e5bda0
|
3 |
size 14244
|
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 sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
|
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": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -131,6 +131,35 @@
|
|
131 |
"eval_samples_per_second": 151.551,
|
132 |
"eval_steps_per_second": 19.0,
|
133 |
"step": 36
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 3,
|
@@ -150,7 +179,7 @@
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
-
"total_flos":
|
154 |
"train_batch_size": 8,
|
155 |
"trial_name": null,
|
156 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.04524886877828054,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 45,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
131 |
"eval_samples_per_second": 151.551,
|
132 |
"eval_steps_per_second": 19.0,
|
133 |
"step": 36
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 0.0392156862745098,
|
137 |
+
"grad_norm": 6.453060626983643,
|
138 |
+
"learning_rate": 3.824798160583012e-05,
|
139 |
+
"loss": 6.5399,
|
140 |
+
"step": 39
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.042232277526395176,
|
144 |
+
"grad_norm": 5.792873859405518,
|
145 |
+
"learning_rate": 3.5959278669726935e-05,
|
146 |
+
"loss": 6.2014,
|
147 |
+
"step": 42
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.04524886877828054,
|
151 |
+
"grad_norm": 5.358177661895752,
|
152 |
+
"learning_rate": 3.355050358314172e-05,
|
153 |
+
"loss": 6.046,
|
154 |
+
"step": 45
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.04524886877828054,
|
158 |
+
"eval_loss": 5.793038845062256,
|
159 |
+
"eval_runtime": 11.0914,
|
160 |
+
"eval_samples_per_second": 151.018,
|
161 |
+
"eval_steps_per_second": 18.934,
|
162 |
+
"step": 45
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 3,
|
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
+
"total_flos": 3857061657968640.0,
|
183 |
"train_batch_size": 8,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|