Training in progress, step 39, 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 78480072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25ed013e89e606d0decbdf3a9eec943d505ea4bda2daeb80161d039fb4221bed
|
3 |
size 78480072
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 157104826
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b31c6ed5ca16df7320632858b14c5573aba5a7dcc042fe5b48f73ce9ca207c77
|
3 |
size 157104826
|
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:cf00b78ce5f0b943b280eef62705ae21cd61e8587d64dc2038685c6a9c7af23d
|
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 sha256:5256258c422cade61a05f9b7acf2463558d18db9447187b4d8690b3bca3e867f
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -96,6 +96,72 @@
|
|
96 |
"learning_rate": 0.0002,
|
97 |
"loss": 1.1285,
|
98 |
"step": 21
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
99 |
}
|
100 |
],
|
101 |
"logging_steps": 3,
|
@@ -110,12 +176,12 @@
|
|
110 |
"should_evaluate": false,
|
111 |
"should_log": false,
|
112 |
"should_save": true,
|
113 |
-
"should_training_stop":
|
114 |
},
|
115 |
"attributes": {}
|
116 |
}
|
117 |
},
|
118 |
-
"total_flos":
|
119 |
"train_batch_size": 2,
|
120 |
"trial_name": null,
|
121 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.045151953690303906,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 39,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
96 |
"learning_rate": 0.0002,
|
97 |
"loss": 1.1285,
|
98 |
"step": 21
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.027785817655571636,
|
102 |
+
"grad_norm": 0.6639531850814819,
|
103 |
+
"learning_rate": 0.00018660254037844388,
|
104 |
+
"loss": 0.8674,
|
105 |
+
"step": 24
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.02894356005788712,
|
109 |
+
"eval_loss": 0.8585013151168823,
|
110 |
+
"eval_runtime": 13.7257,
|
111 |
+
"eval_samples_per_second": 26.52,
|
112 |
+
"eval_steps_per_second": 13.26,
|
113 |
+
"step": 25
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.03125904486251809,
|
117 |
+
"grad_norm": 0.6188398003578186,
|
118 |
+
"learning_rate": 0.00015000000000000001,
|
119 |
+
"loss": 0.8325,
|
120 |
+
"step": 27
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 0.03473227206946455,
|
124 |
+
"grad_norm": 0.6061347723007202,
|
125 |
+
"learning_rate": 0.0001,
|
126 |
+
"loss": 0.875,
|
127 |
+
"step": 30
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 0.03473227206946455,
|
131 |
+
"eval_loss": 0.8159210681915283,
|
132 |
+
"eval_runtime": 13.7559,
|
133 |
+
"eval_samples_per_second": 26.461,
|
134 |
+
"eval_steps_per_second": 13.231,
|
135 |
+
"step": 30
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.038205499276410995,
|
139 |
+
"grad_norm": 0.7855627536773682,
|
140 |
+
"learning_rate": 5.000000000000002e-05,
|
141 |
+
"loss": 0.9123,
|
142 |
+
"step": 33
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.04052098408104197,
|
146 |
+
"eval_loss": 0.7978764772415161,
|
147 |
+
"eval_runtime": 13.7548,
|
148 |
+
"eval_samples_per_second": 26.464,
|
149 |
+
"eval_steps_per_second": 13.232,
|
150 |
+
"step": 35
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.04167872648335745,
|
154 |
+
"grad_norm": 0.7127139568328857,
|
155 |
+
"learning_rate": 1.339745962155613e-05,
|
156 |
+
"loss": 0.8154,
|
157 |
+
"step": 36
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.045151953690303906,
|
161 |
+
"grad_norm": 0.5367171764373779,
|
162 |
+
"learning_rate": 0.0,
|
163 |
+
"loss": 0.7702,
|
164 |
+
"step": 39
|
165 |
}
|
166 |
],
|
167 |
"logging_steps": 3,
|
|
|
176 |
"should_evaluate": false,
|
177 |
"should_log": false,
|
178 |
"should_save": true,
|
179 |
+
"should_training_stop": true
|
180 |
},
|
181 |
"attributes": {}
|
182 |
}
|
183 |
},
|
184 |
+
"total_flos": 3836723846971392.0,
|
185 |
"train_batch_size": 2,
|
186 |
"trial_name": null,
|
187 |
"trial_params": null
|