marinone94
commited on
Commit
β’
186a2f5
1
Parent(s):
ba4c3e9
Training in progress, step 400
Browse files- {checkpoint-100 β checkpoint-400}/config.json +0 -0
- {checkpoint-100 β checkpoint-400}/optimizer.pt +2 -2
- {checkpoint-100 β checkpoint-400}/preprocessor_config.json +0 -0
- {checkpoint-100 β checkpoint-400}/pytorch_model.bin +1 -1
- {checkpoint-100 β checkpoint-400}/rng_state.pth +1 -1
- {checkpoint-100 β checkpoint-400}/scaler.pt +1 -1
- {checkpoint-100 β checkpoint-400}/scheduler.pt +1 -1
- {checkpoint-100 β checkpoint-400}/trainer_state.json +120 -3
- {checkpoint-100 β checkpoint-400}/training_args.bin +0 -0
- pytorch_model.bin +1 -1
{checkpoint-100 β checkpoint-400}/config.json
RENAMED
File without changes
|
{checkpoint-100 β checkpoint-400}/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 sha256:6bc139501a46b0e5da3e9988467c4b0aef78d4ce38267337c5b0939b4f554645
|
3 |
+
size 2490337809
|
{checkpoint-100 β checkpoint-400}/preprocessor_config.json
RENAMED
File without changes
|
{checkpoint-100 β checkpoint-400}/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 sha256:61b6883c6e02239e2f9a600d8b7a77e2e4821e4fd6b9635280a33cee15944b9e
|
3 |
size 1262063089
|
{checkpoint-100 β checkpoint-400}/rng_state.pth
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32dd70acb7307594400dadf64117d5d484d83652c730621271e760304adf2397
|
3 |
size 14567
|
{checkpoint-100 β checkpoint-400}/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:b5e8219f6c4643e0de09787b07a2c15c2c50002ef0c531660b4d5d8538c2293d
|
3 |
size 559
|
{checkpoint-100 β checkpoint-400}/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:a0e7e58c36f0b8ee2c8c1ebaf9ae91bddf330fc34687e7cf8ab86283634768c5
|
3 |
size 623
|
{checkpoint-100 β checkpoint-400}/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,
|
@@ -45,11 +45,128 @@
|
|
45 |
"eval_steps_per_second": 0.78,
|
46 |
"eval_wer": 1.0,
|
47 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"max_steps": 6516,
|
51 |
"num_train_epochs": 3,
|
52 |
-
"total_flos":
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.18409849269359108,
|
5 |
+
"global_step": 400,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
45 |
"eval_steps_per_second": 0.78,
|
46 |
"eval_wer": 1.0,
|
47 |
"step": 100
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.06,
|
51 |
+
"learning_rate": 6.583969465648854e-05,
|
52 |
+
"loss": 3.281,
|
53 |
+
"step": 120
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.06,
|
57 |
+
"learning_rate": 7.495301487862176e-05,
|
58 |
+
"loss": 3.3442,
|
59 |
+
"step": 140
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.07,
|
63 |
+
"learning_rate": 7.472983555207517e-05,
|
64 |
+
"loss": 3.5229,
|
65 |
+
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.08,
|
69 |
+
"learning_rate": 7.449490994518402e-05,
|
70 |
+
"loss": 3.089,
|
71 |
+
"step": 180
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.09,
|
75 |
+
"learning_rate": 7.427173061863743e-05,
|
76 |
+
"loss": 3.482,
|
77 |
+
"step": 200
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.09,
|
81 |
+
"eval_loss": 3.274627923965454,
|
82 |
+
"eval_runtime": 194.5649,
|
83 |
+
"eval_samples_per_second": 24.891,
|
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 |
"max_steps": 6516,
|
168 |
"num_train_epochs": 3,
|
169 |
+
"total_flos": 7.629907237154058e+18,
|
170 |
"trial_name": null,
|
171 |
"trial_params": null
|
172 |
}
|
{checkpoint-100 β checkpoint-400}/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 sha256:61b6883c6e02239e2f9a600d8b7a77e2e4821e4fd6b9635280a33cee15944b9e
|
3 |
size 1262063089
|