Commit
•
dba7c57
1
Parent(s):
d6e7906
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:ec22c3d9bcd6353319973a9b948e015bf2b55e5b016dd4a047ac623b8d75a936
|
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:bc8ad9821b5b1d9d37cd3a4a43587f5f9ffc47c277706630426b4c035c536e57
|
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 sha256:2a010ad19aaaa343fbfbf6d1ce05dfd1e56fb0ac07188b993fc06e025d81ccc1
|
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 sha256:8210f8e2249c280ac4965b4cc059199e79e619c33beb58bb250012029c0aaadf
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_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": 32.024,
|
86 |
"eval_steps_per_second": 4.006,
|
87 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 50,
|
@@ -104,7 +182,7 @@
|
|
104 |
"attributes": {}
|
105 |
}
|
106 |
},
|
107 |
-
"total_flos":
|
108 |
"train_batch_size": 16,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.402164101600647,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-1000",
|
4 |
+
"epoch": 1.675392670157068,
|
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": 32.024,
|
86 |
"eval_steps_per_second": 4.006,
|
87 |
"step": 500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.9214659685863874,
|
91 |
+
"grad_norm": 2.2309463024139404,
|
92 |
+
"learning_rate": 2.7450000000000003e-05,
|
93 |
+
"loss": 0.5084,
|
94 |
+
"step": 550
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 1.0052356020942408,
|
98 |
+
"grad_norm": 1.8079086542129517,
|
99 |
+
"learning_rate": 2.995e-05,
|
100 |
+
"loss": 0.4954,
|
101 |
+
"step": 600
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.0890052356020943,
|
105 |
+
"grad_norm": 6.239879608154297,
|
106 |
+
"learning_rate": 3.245e-05,
|
107 |
+
"loss": 0.4954,
|
108 |
+
"step": 650
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.1727748691099475,
|
112 |
+
"grad_norm": 12.593622207641602,
|
113 |
+
"learning_rate": 3.495e-05,
|
114 |
+
"loss": 0.4946,
|
115 |
+
"step": 700
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.256544502617801,
|
119 |
+
"grad_norm": 3.1568186283111572,
|
120 |
+
"learning_rate": 3.745e-05,
|
121 |
+
"loss": 0.4768,
|
122 |
+
"step": 750
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.3403141361256545,
|
126 |
+
"grad_norm": 3.9486255645751953,
|
127 |
+
"learning_rate": 3.995e-05,
|
128 |
+
"loss": 0.4737,
|
129 |
+
"step": 800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 1.4240837696335078,
|
133 |
+
"grad_norm": 2.641502618789673,
|
134 |
+
"learning_rate": 4.245e-05,
|
135 |
+
"loss": 0.4706,
|
136 |
+
"step": 850
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 1.5078534031413613,
|
140 |
+
"grad_norm": 1.9798855781555176,
|
141 |
+
"learning_rate": 4.495e-05,
|
142 |
+
"loss": 0.4605,
|
143 |
+
"step": 900
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 1.5916230366492146,
|
147 |
+
"grad_norm": 2.691363573074341,
|
148 |
+
"learning_rate": 4.745e-05,
|
149 |
+
"loss": 0.4554,
|
150 |
+
"step": 950
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 1.675392670157068,
|
154 |
+
"grad_norm": 3.704902410507202,
|
155 |
+
"learning_rate": 4.995e-05,
|
156 |
+
"loss": 0.4561,
|
157 |
+
"step": 1000
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 1.675392670157068,
|
161 |
+
"eval_loss": 0.402164101600647,
|
162 |
+
"eval_runtime": 265.618,
|
163 |
+
"eval_samples_per_second": 31.959,
|
164 |
+
"eval_steps_per_second": 3.998,
|
165 |
+
"step": 1000
|
166 |
}
|
167 |
],
|
168 |
"logging_steps": 50,
|
|
|
182 |
"attributes": {}
|
183 |
}
|
184 |
},
|
185 |
+
"total_flos": 1.791435708710208e+16,
|
186 |
"train_batch_size": 16,
|
187 |
"trial_name": null,
|
188 |
"trial_params": null
|