Training in progress, step 50, 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 4731640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de2d0eff1d240b8dfc993360c8dc2d3d420310c9710257f5210588b3e1a1d7c5
|
3 |
size 4731640
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2505722
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e64128f9bcce4c5f40656efc2f779a2add7ffb219d5f5145bea1529779e0d6f2
|
3 |
size 2505722
|
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 sha256:8a42d21cfc86e07d4c5d1016dabd7e4e45e77e288ae73dcf2b10bb612d76cac9
|
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:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -88,6 +88,43 @@
|
|
88 |
"learning_rate": 3.086582838174551e-05,
|
89 |
"loss": 13.2348,
|
90 |
"step": 35
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 5,
|
@@ -102,12 +139,12 @@
|
|
102 |
"should_evaluate": false,
|
103 |
"should_log": false,
|
104 |
"should_save": true,
|
105 |
-
"should_training_stop":
|
106 |
},
|
107 |
"attributes": {}
|
108 |
}
|
109 |
},
|
110 |
-
"total_flos":
|
111 |
"train_batch_size": 2,
|
112 |
"trial_name": null,
|
113 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.008137689709891361,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
88 |
"learning_rate": 3.086582838174551e-05,
|
89 |
"loss": 13.2348,
|
90 |
"step": 35
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.0065101517679130895,
|
94 |
+
"grad_norm": 271.3753356933594,
|
95 |
+
"learning_rate": 1.4644660940672627e-05,
|
96 |
+
"loss": 12.7656,
|
97 |
+
"step": 40
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.0065101517679130895,
|
101 |
+
"eval_loss": 3.079690456390381,
|
102 |
+
"eval_runtime": 30.0586,
|
103 |
+
"eval_samples_per_second": 86.099,
|
104 |
+
"eval_steps_per_second": 43.049,
|
105 |
+
"step": 40
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.007323920738902225,
|
109 |
+
"grad_norm": 589.4432373046875,
|
110 |
+
"learning_rate": 3.8060233744356633e-06,
|
111 |
+
"loss": 11.9012,
|
112 |
+
"step": 45
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.008137689709891361,
|
116 |
+
"grad_norm": 212.29518127441406,
|
117 |
+
"learning_rate": 0.0,
|
118 |
+
"loss": 11.9955,
|
119 |
+
"step": 50
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.008137689709891361,
|
123 |
+
"eval_loss": 3.072233200073242,
|
124 |
+
"eval_runtime": 29.2644,
|
125 |
+
"eval_samples_per_second": 88.435,
|
126 |
+
"eval_steps_per_second": 44.218,
|
127 |
+
"step": 50
|
128 |
}
|
129 |
],
|
130 |
"logging_steps": 5,
|
|
|
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": 154973566402560.0,
|
148 |
"train_batch_size": 2,
|
149 |
"trial_name": null,
|
150 |
"trial_params": null
|