mikhail-panzo
commited on
Commit
•
29a26aa
1
Parent(s):
d38a38f
Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abff6a3b395393232e5710d40106174e0677d0142a41784b9fb51f8489bb77ef
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9713c93771d1f6a6b574d01f234f860c1f651482faa1aaf4ab1ff6ee0fc8fbca
|
3 |
size 1155772233
|
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 sha256:17cf673186ae01f2692ea8b747e0fc3505fbc3d1d22ec482b81a3eae6d5672a0
|
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 sha256:2599834a5bb25566393aaf9a393926be754987442fa6dd0ec6e936958ebe0844
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -85,6 +85,84 @@
|
|
85 |
"eval_samples_per_second": 23.927,
|
86 |
"eval_steps_per_second": 3.01,
|
87 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 50,
|
@@ -104,7 +182,7 @@
|
|
104 |
"attributes": {}
|
105 |
}
|
106 |
},
|
107 |
-
"total_flos":
|
108 |
"train_batch_size": 64,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.4506620466709137,
|
3 |
+
"best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-1000",
|
4 |
+
"epoch": 43.47826086956522,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
85 |
"eval_samples_per_second": 23.927,
|
86 |
"eval_steps_per_second": 3.01,
|
87 |
"step": 500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 23.91304347826087,
|
91 |
+
"grad_norm": 1.9992552995681763,
|
92 |
+
"learning_rate": 2.7400000000000004e-06,
|
93 |
+
"loss": 0.5759,
|
94 |
+
"step": 550
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 26.08695652173913,
|
98 |
+
"grad_norm": 1.2594470977783203,
|
99 |
+
"learning_rate": 2.99e-06,
|
100 |
+
"loss": 0.56,
|
101 |
+
"step": 600
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 28.26086956521739,
|
105 |
+
"grad_norm": 1.0602363348007202,
|
106 |
+
"learning_rate": 3.2400000000000003e-06,
|
107 |
+
"loss": 0.5709,
|
108 |
+
"step": 650
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 30.434782608695652,
|
112 |
+
"grad_norm": 1.116231083869934,
|
113 |
+
"learning_rate": 3.49e-06,
|
114 |
+
"loss": 0.5322,
|
115 |
+
"step": 700
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 32.608695652173914,
|
119 |
+
"grad_norm": 1.5203620195388794,
|
120 |
+
"learning_rate": 3.74e-06,
|
121 |
+
"loss": 0.5264,
|
122 |
+
"step": 750
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 34.78260869565217,
|
126 |
+
"grad_norm": 1.6139357089996338,
|
127 |
+
"learning_rate": 3.990000000000001e-06,
|
128 |
+
"loss": 0.5191,
|
129 |
+
"step": 800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 36.95652173913044,
|
133 |
+
"grad_norm": 1.436273217201233,
|
134 |
+
"learning_rate": 4.24e-06,
|
135 |
+
"loss": 0.5272,
|
136 |
+
"step": 850
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 39.130434782608695,
|
140 |
+
"grad_norm": 1.757323145866394,
|
141 |
+
"learning_rate": 4.49e-06,
|
142 |
+
"loss": 0.5016,
|
143 |
+
"step": 900
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 41.30434782608695,
|
147 |
+
"grad_norm": 0.9879368543624878,
|
148 |
+
"learning_rate": 4.74e-06,
|
149 |
+
"loss": 0.4975,
|
150 |
+
"step": 950
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 43.47826086956522,
|
154 |
+
"grad_norm": 1.3402222394943237,
|
155 |
+
"learning_rate": 4.9900000000000005e-06,
|
156 |
+
"loss": 0.5126,
|
157 |
+
"step": 1000
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 43.47826086956522,
|
161 |
+
"eval_loss": 0.4506620466709137,
|
162 |
+
"eval_runtime": 6.4644,
|
163 |
+
"eval_samples_per_second": 24.596,
|
164 |
+
"eval_steps_per_second": 3.094,
|
165 |
+
"step": 1000
|
166 |
}
|
167 |
],
|
168 |
"logging_steps": 50,
|
|
|
182 |
"attributes": {}
|
183 |
}
|
184 |
},
|
185 |
+
"total_flos": 1.484313588256752e+16,
|
186 |
"train_batch_size": 64,
|
187 |
"trial_name": null,
|
188 |
"trial_params": null
|