Training in progress, step 42, 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 556856304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31e69d955ce30f7deef431bdec2f1b7bf55a4610626c1a9f7b794b620b66a959
|
3 |
size 556856304
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21599060
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eda1dcfc8eb772124e87098c6a615c3228d72c98faa057647bf6b5484b68c063
|
3 |
size 21599060
|
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 sha256:38249d6e4a57e3fd4ee877ad54d211d5729babc26051b7f8671884608c9e097b
|
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 sha256:1d29324a0d5877763002861a44f469da99d01dae7b8684c45bb1b74d6def2b49
|
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":
|
5 |
"eval_steps": 11,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -81,6 +81,20 @@
|
|
81 |
"eval_samples_per_second": 21.768,
|
82 |
"eval_steps_per_second": 10.884,
|
83 |
"step": 33
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 5,
|
@@ -95,12 +109,12 @@
|
|
95 |
"should_evaluate": false,
|
96 |
"should_log": false,
|
97 |
"should_save": true,
|
98 |
-
"should_training_stop":
|
99 |
},
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
-
"total_flos":
|
104 |
"train_batch_size": 2,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0120481927710843,
|
5 |
"eval_steps": 11,
|
6 |
+
"global_step": 42,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
81 |
"eval_samples_per_second": 21.768,
|
82 |
"eval_steps_per_second": 10.884,
|
83 |
"step": 33
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.8433734939759037,
|
87 |
+
"grad_norm": 4.781399726867676,
|
88 |
+
"learning_rate": 1.134947733186315e-05,
|
89 |
+
"loss": 7.6683,
|
90 |
+
"step": 35
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.963855421686747,
|
94 |
+
"grad_norm": 7.088382720947266,
|
95 |
+
"learning_rate": 9.607359798384785e-07,
|
96 |
+
"loss": 7.8901,
|
97 |
+
"step": 40
|
98 |
}
|
99 |
],
|
100 |
"logging_steps": 5,
|
|
|
109 |
"should_evaluate": false,
|
110 |
"should_log": false,
|
111 |
"should_save": true,
|
112 |
+
"should_training_stop": true
|
113 |
},
|
114 |
"attributes": {}
|
115 |
}
|
116 |
},
|
117 |
+
"total_flos": 5974486312550400.0,
|
118 |
"train_batch_size": 2,
|
119 |
"trial_name": null,
|
120 |
"trial_params": null
|