Training in progress, step 32, 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 97728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:446704d171909fe1b90ebb16e3107050b0a85e3467f5f3c73077d0c6783e132b
|
3 |
size 97728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 212298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffcf1c68b31bc14c84a25b4361564f95d31085e478b3396745e9e7887925d1fd
|
3 |
size 212298
|
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:faa450476dbd198dc4484447171d2b13c39e0fa316de67fcc41765245207305d
|
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:c32f0c34d941772d95b11e82ac22de22e969c9c470a009499eff8dbdf7ec5a86
|
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": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -95,6 +95,28 @@
|
|
95 |
"eval_samples_per_second": 134.583,
|
96 |
"eval_steps_per_second": 67.985,
|
97 |
"step": 24
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
}
|
99 |
],
|
100 |
"logging_steps": 3,
|
@@ -114,7 +136,7 @@
|
|
114 |
"attributes": {}
|
115 |
}
|
116 |
},
|
117 |
-
"total_flos":
|
118 |
"train_batch_size": 2,
|
119 |
"trial_name": null,
|
120 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.136761487964989,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 32,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
95 |
"eval_samples_per_second": 134.583,
|
96 |
"eval_steps_per_second": 67.985,
|
97 |
"step": 24
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.9452954048140044,
|
101 |
+
"grad_norm": 0.15795904397964478,
|
102 |
+
"learning_rate": 0.00019450008187146684,
|
103 |
+
"loss": 10.3562,
|
104 |
+
"step": 27
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.0667396061269148,
|
108 |
+
"grad_norm": 0.22537720203399658,
|
109 |
+
"learning_rate": 0.00018888354486549237,
|
110 |
+
"loss": 13.5544,
|
111 |
+
"step": 30
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 1.136761487964989,
|
115 |
+
"eval_loss": 10.337327003479004,
|
116 |
+
"eval_runtime": 0.7182,
|
117 |
+
"eval_samples_per_second": 135.057,
|
118 |
+
"eval_steps_per_second": 68.225,
|
119 |
+
"step": 32
|
120 |
}
|
121 |
],
|
122 |
"logging_steps": 3,
|
|
|
136 |
"attributes": {}
|
137 |
}
|
138 |
},
|
139 |
+
"total_flos": 13752604164096.0,
|
140 |
"train_batch_size": 2,
|
141 |
"trial_name": null,
|
142 |
"trial_params": null
|