Training in progress, step 1000, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a9811c564d05ce9bdc5089524781408a52c7660ae4334f7cee79d741d60c98c
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60f74b5b9b5294e572143555dccde954f1736ae900471ee6be94bc5700ef138f
|
3 |
size 18902665
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3587699f49f930b2c0cd17b5071fff6f2cf9326eebadb8adb2db8be4db4ec081
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -133,13 +133,27 @@
|
|
133 |
"eval_samples_per_second": 30.333,
|
134 |
"eval_steps_per_second": 3.795,
|
135 |
"step": 900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 100,
|
139 |
"max_steps": 4116,
|
140 |
"num_train_epochs": 3,
|
141 |
"save_steps": 100,
|
142 |
-
"total_flos": 2.
|
143 |
"trial_name": null,
|
144 |
"trial_params": null
|
145 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.3908660411834717,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1000",
|
4 |
+
"epoch": 0.7285974499089253,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
133 |
"eval_samples_per_second": 30.333,
|
134 |
"eval_steps_per_second": 3.795,
|
135 |
"step": 900
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.73,
|
139 |
+
"learning_rate": 0.0002,
|
140 |
+
"loss": 2.3898,
|
141 |
+
"step": 1000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.73,
|
145 |
+
"eval_loss": 2.3908660411834717,
|
146 |
+
"eval_runtime": 206.8251,
|
147 |
+
"eval_samples_per_second": 30.335,
|
148 |
+
"eval_steps_per_second": 3.795,
|
149 |
+
"step": 1000
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 100,
|
153 |
"max_steps": 4116,
|
154 |
"num_train_epochs": 3,
|
155 |
"save_steps": 100,
|
156 |
+
"total_flos": 2.917579599470592e+16,
|
157 |
"trial_name": null,
|
158 |
"trial_params": null
|
159 |
}
|