Training in progress, step 380, 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 4725640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac7c7b067ce43a0be0be0f92ea01066fe8ed60f6f5f80359ee347257fbaa14a6
|
3 |
size 4725640
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2423802
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a76102b6fc4e10f811ee1edf543de76c09456828bc9f6d9f8e1b936ec810e71
|
3 |
size 2423802
|
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 sha256:5b91ead1bc4475814472ed6c199136a17cbef66ddbeed94488d3061d1183ec5d
|
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:d73ec88250c78a08053b936383d3830db79e459629e27383da2e03ffab044694
|
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,
|
@@ -133,6 +133,13 @@
|
|
133 |
"learning_rate": 4.9995435879539254e-05,
|
134 |
"loss": 2.7863,
|
135 |
"step": 360
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 20,
|
@@ -140,7 +147,7 @@
|
|
140 |
"num_input_tokens_seen": 0,
|
141 |
"num_train_epochs": 1,
|
142 |
"save_steps": 20,
|
143 |
-
"total_flos":
|
144 |
"train_batch_size": 1,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0002957359544877931,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 380,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
133 |
"learning_rate": 4.9995435879539254e-05,
|
134 |
"loss": 2.7863,
|
135 |
"step": 360
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.0,
|
139 |
+
"grad_norm": 7.647037506103516,
|
140 |
+
"learning_rate": 4.999181729716214e-05,
|
141 |
+
"loss": 2.6197,
|
142 |
+
"step": 380
|
143 |
}
|
144 |
],
|
145 |
"logging_steps": 20,
|
|
|
147 |
"num_input_tokens_seen": 0,
|
148 |
"num_train_epochs": 1,
|
149 |
"save_steps": 20,
|
150 |
+
"total_flos": 1740689046355968.0,
|
151 |
"train_batch_size": 1,
|
152 |
"trial_name": null,
|
153 |
"trial_params": null
|