Training in progress, step 10, 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 45118424
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac35dd25f66a71eb8039c6ac871b2894025b57c3d252a6918ebe0fad5e2ac530
|
3 |
size 45118424
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 90310010
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d426c46b676f023356b58e9cd8b14796c80cabb09c3ec996d9efd8b5bee27db0
|
3 |
size 90310010
|
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:dc48e4d5526310737e4a42163d856911d80e0f15c794153955c2fcf5e865ef9d
|
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:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -103,6 +103,28 @@
|
|
103 |
"eval_samples_per_second": 16.105,
|
104 |
"eval_steps_per_second": 16.105,
|
105 |
"step": 8
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
}
|
107 |
],
|
108 |
"logging_steps": 1,
|
@@ -117,12 +139,12 @@
|
|
117 |
"should_evaluate": false,
|
118 |
"should_log": false,
|
119 |
"should_save": true,
|
120 |
-
"should_training_stop":
|
121 |
},
|
122 |
"attributes": {}
|
123 |
}
|
124 |
},
|
125 |
-
"total_flos":
|
126 |
"train_batch_size": 1,
|
127 |
"trial_name": null,
|
128 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0003260913871112379,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
103 |
"eval_samples_per_second": 16.105,
|
104 |
"eval_steps_per_second": 16.105,
|
105 |
"step": 8
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.00029348224840011414,
|
109 |
+
"grad_norm": 3.5420632362365723,
|
110 |
+
"learning_rate": 0.00018,
|
111 |
+
"loss": 2.6092,
|
112 |
+
"step": 9
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.0003260913871112379,
|
116 |
+
"grad_norm": 3.2168703079223633,
|
117 |
+
"learning_rate": 0.0002,
|
118 |
+
"loss": 2.1234,
|
119 |
+
"step": 10
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.0003260913871112379,
|
123 |
+
"eval_loss": 2.3552844524383545,
|
124 |
+
"eval_runtime": 400.4535,
|
125 |
+
"eval_samples_per_second": 16.124,
|
126 |
+
"eval_steps_per_second": 16.124,
|
127 |
+
"step": 10
|
128 |
}
|
129 |
],
|
130 |
"logging_steps": 1,
|
|
|
139 |
"should_evaluate": false,
|
140 |
"should_log": false,
|
141 |
"should_save": true,
|
142 |
+
"should_training_stop": true
|
143 |
},
|
144 |
"attributes": {}
|
145 |
}
|
146 |
},
|
147 |
+
"total_flos": 967722569564160.0,
|
148 |
"train_batch_size": 1,
|
149 |
"trial_name": null,
|
150 |
"trial_params": null
|