marinone94
commited on
Commit
β’
9736d24
1
Parent(s):
186a2f5
Training in progress, step 500
Browse files- {checkpoint-200 β checkpoint-500}/config.json +0 -0
- {checkpoint-200 β checkpoint-500}/optimizer.pt +2 -2
- {checkpoint-200 β checkpoint-500}/preprocessor_config.json +0 -0
- {checkpoint-200 β checkpoint-500}/pytorch_model.bin +1 -1
- {checkpoint-200 β checkpoint-500}/rng_state.pth +1 -1
- {checkpoint-200 β checkpoint-500}/scaler.pt +1 -1
- {checkpoint-200 β checkpoint-500}/scheduler.pt +1 -1
- {checkpoint-200 β checkpoint-500}/trainer_state.json +120 -3
- {checkpoint-200 β checkpoint-500}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-200 β checkpoint-500}/config.json
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-500}/optimizer.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:048f968ba8a4f235f039cc2a3b8618f0d55f48973016df5fcaae601d0b92d784
|
3 |
+
size 2490337809
|
{checkpoint-200 β checkpoint-500}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-200 β checkpoint-500}/pytorch_model.bin
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70e8ab1267a52eb4fa82e60a245e4f97d45dfb9f9c4616b7da2a301c9311b7f7
|
3 |
size 1262063089
|
{checkpoint-200 β checkpoint-500}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:158b5fc43024b846c58cb1ec5967d7e3d1635ecc454a7b9dd1aac7d9ccc8d61e
|
3 |
size 14503
|
{checkpoint-200 β checkpoint-500}/scaler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c304e72bfea7592d4ddcc6e3b3b1a9bcab2965ed75957d798b3560c75dbe7d8
|
3 |
size 559
|
{checkpoint-200 β checkpoint-500}/scheduler.pt
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f844f4edb8fac739b919057d71649ad3c5a779b3699b7f57247e1a115c338a4
|
3 |
size 623
|
{checkpoint-200 β checkpoint-500}/trainer_state.json
RENAMED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -84,11 +84,128 @@
|
|
84 |
"eval_steps_per_second": 0.781,
|
85 |
"eval_wer": 1.0,
|
86 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
87 |
}
|
88 |
],
|
89 |
"max_steps": 6516,
|
90 |
"num_train_epochs": 3,
|
91 |
-
"total_flos":
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|
94 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.23012311586698883,
|
5 |
+
"global_step": 500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
84 |
"eval_steps_per_second": 0.781,
|
85 |
"eval_wer": 1.0,
|
86 |
"step": 200
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.1,
|
90 |
+
"learning_rate": 7.403680501174628e-05,
|
91 |
+
"loss": 3.1517,
|
92 |
+
"step": 220
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.11,
|
96 |
+
"learning_rate": 7.380187940485512e-05,
|
97 |
+
"loss": 3.1617,
|
98 |
+
"step": 240
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.12,
|
102 |
+
"learning_rate": 7.357870007830852e-05,
|
103 |
+
"loss": 3.2971,
|
104 |
+
"step": 260
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.13,
|
108 |
+
"learning_rate": 7.334377447141738e-05,
|
109 |
+
"loss": 3.022,
|
110 |
+
"step": 280
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.14,
|
114 |
+
"learning_rate": 7.312059514487078e-05,
|
115 |
+
"loss": 3.3322,
|
116 |
+
"step": 300
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.14,
|
120 |
+
"eval_loss": 3.0716073513031006,
|
121 |
+
"eval_runtime": 196.1674,
|
122 |
+
"eval_samples_per_second": 24.688,
|
123 |
+
"eval_steps_per_second": 0.775,
|
124 |
+
"eval_wer": 1.0,
|
125 |
+
"step": 300
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.15,
|
129 |
+
"learning_rate": 7.288566953797964e-05,
|
130 |
+
"loss": 2.9964,
|
131 |
+
"step": 320
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.16,
|
135 |
+
"learning_rate": 7.265074393108849e-05,
|
136 |
+
"loss": 3.0777,
|
137 |
+
"step": 340
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.17,
|
141 |
+
"learning_rate": 7.242756460454189e-05,
|
142 |
+
"loss": 3.2703,
|
143 |
+
"step": 360
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.17,
|
147 |
+
"learning_rate": 7.219263899765073e-05,
|
148 |
+
"loss": 3.1161,
|
149 |
+
"step": 380
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.18,
|
153 |
+
"learning_rate": 7.195771339075958e-05,
|
154 |
+
"loss": 3.2435,
|
155 |
+
"step": 400
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.18,
|
159 |
+
"eval_loss": 3.063333034515381,
|
160 |
+
"eval_runtime": 190.5938,
|
161 |
+
"eval_samples_per_second": 25.41,
|
162 |
+
"eval_steps_per_second": 0.798,
|
163 |
+
"eval_wer": 1.0,
|
164 |
+
"step": 400
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.19,
|
168 |
+
"learning_rate": 7.172278778386843e-05,
|
169 |
+
"loss": 2.9993,
|
170 |
+
"step": 420
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.2,
|
174 |
+
"learning_rate": 7.148786217697727e-05,
|
175 |
+
"loss": 3.0555,
|
176 |
+
"step": 440
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.21,
|
180 |
+
"learning_rate": 7.126468285043069e-05,
|
181 |
+
"loss": 3.1879,
|
182 |
+
"step": 460
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.22,
|
186 |
+
"learning_rate": 7.102975724353953e-05,
|
187 |
+
"loss": 2.9861,
|
188 |
+
"step": 480
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.23,
|
192 |
+
"learning_rate": 7.080657791699295e-05,
|
193 |
+
"loss": 3.0833,
|
194 |
+
"step": 500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.23,
|
198 |
+
"eval_loss": 2.9769718647003174,
|
199 |
+
"eval_runtime": 195.2639,
|
200 |
+
"eval_samples_per_second": 24.802,
|
201 |
+
"eval_steps_per_second": 0.778,
|
202 |
+
"eval_wer": 1.0,
|
203 |
+
"step": 500
|
204 |
}
|
205 |
],
|
206 |
"max_steps": 6516,
|
207 |
"num_train_epochs": 3,
|
208 |
+
"total_flos": 9.523798230150083e+18,
|
209 |
"trial_name": null,
|
210 |
"trial_params": null
|
211 |
}
|
{checkpoint-200 β checkpoint-500}/training_args.bin
RENAMED
File without changes
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262063089
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70e8ab1267a52eb4fa82e60a245e4f97d45dfb9f9c4616b7da2a301c9311b7f7
|
3 |
size 1262063089
|