DeepDream2045 commited on
Commit
a724513
·
verified ·
1 Parent(s): a49a5bf

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -20,12 +20,12 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "up_proj",
24
- "v_proj",
25
  "down_proj",
 
26
  "k_proj",
27
- "q_proj",
28
  "gate_proj",
 
29
  "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "down_proj",
24
+ "up_proj",
25
  "k_proj",
26
+ "v_proj",
27
  "gate_proj",
28
+ "q_proj",
29
  "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:211736f17bd22202efc1932db5b9ab6041d73031af69563bead1889c3025e6d2
3
  size 156926880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:362214819e787620e90e6dec1b015b3acc65d7d11cf6862ba3aa7109e65b0a9d
3
  size 156926880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8ce844fbf952b8d7255e8f5c0432cca45f3c10d36f7592f196a669d17c891b2
3
  size 313998650
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e82af3282e5e2658f506067696578be50c8bc57ef41b9eca1f99178bcc99b3
3
  size 313998650
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec8497e2dfd6cdd94b957fa367bbb0fb1e5a205de32951a2d6b92b38d3709d06
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898f43b066fdbe3bfd6f517a46381f9c6a35006091bba02bc49e7641fe022adc
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02c855a970e911d5a2884c6d5b13fde78de630b71faaf3f49bfbdc0c11c72c3a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d80e1ac448cbdc2ec9bbd5a0f208c9a73136674888818820496c826c86b9fc8e
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8961ee511f8374e5a892d115f056e0316f707d650a2635d68c3a08ba6148a829
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c109fc573ae379e95c2c91fd6a89a8829b17cf63d199d9614b233041e0175e90
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f174f9c9b73218734eceb55a4c0af3b35a7f2b2ed56b3af27b2d3a9469f1b796
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a85f60443b94f9237bf37095f04a4e5e5407c04803d1b9906e0aa837a7025bdc
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "best_metric": 0.8200458288192749,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.02767208578346593,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0011068834313386372,
13
- "grad_norm": 36.721168518066406,
14
  "learning_rate": 5e-05,
15
  "loss": 14.1912,
16
  "step": 1
@@ -18,186 +18,369 @@
18
  {
19
  "epoch": 0.0011068834313386372,
20
  "eval_loss": 13.724494934082031,
21
- "eval_runtime": 91.0519,
22
- "eval_samples_per_second": 66.852,
23
- "eval_steps_per_second": 8.358,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.0022137668626772745,
28
- "grad_norm": 45.76126480102539,
29
  "learning_rate": 0.0001,
30
  "loss": 13.95,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.0033206502940159115,
35
- "grad_norm": 44.33281707763672,
36
  "learning_rate": 9.989294616193017e-05,
37
- "loss": 12.4936,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.004427533725354549,
42
- "grad_norm": 41.054508209228516,
43
  "learning_rate": 9.957224306869053e-05,
44
- "loss": 7.0168,
45
  "step": 4
46
  },
47
  {
48
  "epoch": 0.005534417156693186,
49
- "grad_norm": 22.34103012084961,
50
  "learning_rate": 9.903926402016153e-05,
51
- "loss": 3.5822,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.006641300588031823,
56
- "grad_norm": 25.822521209716797,
57
  "learning_rate": 9.829629131445342e-05,
58
- "loss": 2.2788,
59
  "step": 6
60
  },
61
  {
62
  "epoch": 0.00774818401937046,
63
- "grad_norm": 10.615482330322266,
64
  "learning_rate": 9.73465064747553e-05,
65
- "loss": 1.4014,
66
  "step": 7
67
  },
68
  {
69
  "epoch": 0.008855067450709098,
70
- "grad_norm": 6.933248519897461,
71
  "learning_rate": 9.619397662556435e-05,
72
- "loss": 1.0412,
73
  "step": 8
74
  },
75
  {
76
  "epoch": 0.009961950882047734,
77
- "grad_norm": 2.6085708141326904,
78
  "learning_rate": 9.484363707663442e-05,
79
- "loss": 0.8551,
80
  "step": 9
81
  },
82
  {
83
  "epoch": 0.011068834313386372,
84
- "grad_norm": 3.8146591186523438,
85
  "learning_rate": 9.330127018922194e-05,
86
- "loss": 0.8501,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 0.012175717744725008,
91
- "grad_norm": 7.357889175415039,
92
  "learning_rate": 9.157348061512727e-05,
93
- "loss": 0.8831,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 0.013282601176063646,
98
- "grad_norm": 4.156259059906006,
99
  "learning_rate": 8.966766701456177e-05,
100
- "loss": 0.8321,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 0.014389484607402282,
105
- "grad_norm": 13.24997615814209,
106
  "learning_rate": 8.759199037394887e-05,
107
- "loss": 1.0533,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 0.01549636803874092,
112
- "grad_norm": 4.824550628662109,
113
  "learning_rate": 8.535533905932738e-05,
114
- "loss": 0.8486,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 0.016603251470079558,
119
- "grad_norm": 2.509622097015381,
120
  "learning_rate": 8.296729075500344e-05,
121
- "loss": 0.7962,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 0.017710134901418196,
126
- "grad_norm": 3.590033769607544,
127
  "learning_rate": 8.043807145043604e-05,
128
- "loss": 0.8333,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 0.01881701833275683,
133
- "grad_norm": 6.873021125793457,
134
  "learning_rate": 7.777851165098012e-05,
135
- "loss": 0.8969,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 0.019923901764095468,
140
- "grad_norm": 5.084534645080566,
141
  "learning_rate": 7.500000000000001e-05,
142
- "loss": 0.8647,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 0.021030785195434106,
147
- "grad_norm": 2.3888447284698486,
148
  "learning_rate": 7.211443451095007e-05,
149
- "loss": 0.8115,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 0.022137668626772744,
154
- "grad_norm": 1.8158559799194336,
155
  "learning_rate": 6.91341716182545e-05,
156
- "loss": 0.8075,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 0.02324455205811138,
161
- "grad_norm": 2.9052810668945312,
162
  "learning_rate": 6.607197326515808e-05,
163
- "loss": 0.8259,
164
  "step": 21
165
  },
166
  {
167
  "epoch": 0.024351435489450016,
168
- "grad_norm": 2.515951156616211,
169
  "learning_rate": 6.294095225512603e-05,
170
- "loss": 0.8207,
171
  "step": 22
172
  },
173
  {
174
  "epoch": 0.025458318920788654,
175
- "grad_norm": 3.8959262371063232,
176
  "learning_rate": 5.9754516100806423e-05,
177
- "loss": 0.8512,
178
  "step": 23
179
  },
180
  {
181
  "epoch": 0.026565202352127292,
182
- "grad_norm": 2.965120792388916,
183
  "learning_rate": 5.6526309611002594e-05,
184
- "loss": 0.8395,
185
  "step": 24
186
  },
187
  {
188
  "epoch": 0.02767208578346593,
189
- "grad_norm": 1.2737544775009155,
190
  "learning_rate": 5.327015646150716e-05,
191
- "loss": 0.8124,
192
  "step": 25
193
  },
194
  {
195
  "epoch": 0.02767208578346593,
196
- "eval_loss": 0.8200458288192749,
197
- "eval_runtime": 90.9598,
198
- "eval_samples_per_second": 66.92,
199
- "eval_steps_per_second": 8.366,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +404,12 @@
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
- "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 8.280112884822835e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.8100725412368774,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.05534417156693186,
5
  "eval_steps": 25,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 0.0011068834313386372,
13
+ "grad_norm": 38.15006637573242,
14
  "learning_rate": 5e-05,
15
  "loss": 14.1912,
16
  "step": 1
 
18
  {
19
  "epoch": 0.0011068834313386372,
20
  "eval_loss": 13.724494934082031,
21
+ "eval_runtime": 89.4628,
22
+ "eval_samples_per_second": 68.039,
23
+ "eval_steps_per_second": 8.506,
24
  "step": 1
25
  },
26
  {
27
  "epoch": 0.0022137668626772745,
28
+ "grad_norm": 48.19376754760742,
29
  "learning_rate": 0.0001,
30
  "loss": 13.95,
31
  "step": 2
32
  },
33
  {
34
  "epoch": 0.0033206502940159115,
35
+ "grad_norm": 46.14555740356445,
36
  "learning_rate": 9.989294616193017e-05,
37
+ "loss": 12.3983,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.004427533725354549,
42
+ "grad_norm": 40.98630142211914,
43
  "learning_rate": 9.957224306869053e-05,
44
+ "loss": 6.8294,
45
  "step": 4
46
  },
47
  {
48
  "epoch": 0.005534417156693186,
49
+ "grad_norm": 22.246063232421875,
50
  "learning_rate": 9.903926402016153e-05,
51
+ "loss": 3.4894,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.006641300588031823,
56
+ "grad_norm": 24.718996047973633,
57
  "learning_rate": 9.829629131445342e-05,
58
+ "loss": 2.1612,
59
  "step": 6
60
  },
61
  {
62
  "epoch": 0.00774818401937046,
63
+ "grad_norm": 10.347333908081055,
64
  "learning_rate": 9.73465064747553e-05,
65
+ "loss": 1.3505,
66
  "step": 7
67
  },
68
  {
69
  "epoch": 0.008855067450709098,
70
+ "grad_norm": 6.6109466552734375,
71
  "learning_rate": 9.619397662556435e-05,
72
+ "loss": 1.0209,
73
  "step": 8
74
  },
75
  {
76
  "epoch": 0.009961950882047734,
77
+ "grad_norm": 3.112464427947998,
78
  "learning_rate": 9.484363707663442e-05,
79
+ "loss": 0.8508,
80
  "step": 9
81
  },
82
  {
83
  "epoch": 0.011068834313386372,
84
+ "grad_norm": 2.803030014038086,
85
  "learning_rate": 9.330127018922194e-05,
86
+ "loss": 0.8355,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 0.012175717744725008,
91
+ "grad_norm": 6.542176246643066,
92
  "learning_rate": 9.157348061512727e-05,
93
+ "loss": 0.8611,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 0.013282601176063646,
98
+ "grad_norm": 5.868016719818115,
99
  "learning_rate": 8.966766701456177e-05,
100
+ "loss": 0.8652,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 0.014389484607402282,
105
+ "grad_norm": 9.959766387939453,
106
  "learning_rate": 8.759199037394887e-05,
107
+ "loss": 0.9816,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 0.01549636803874092,
112
+ "grad_norm": 4.880505084991455,
113
  "learning_rate": 8.535533905932738e-05,
114
+ "loss": 0.8503,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 0.016603251470079558,
119
+ "grad_norm": 2.4961485862731934,
120
  "learning_rate": 8.296729075500344e-05,
121
+ "loss": 0.798,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 0.017710134901418196,
126
+ "grad_norm": 4.091599941253662,
127
  "learning_rate": 8.043807145043604e-05,
128
+ "loss": 0.838,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 0.01881701833275683,
133
+ "grad_norm": 7.446221351623535,
134
  "learning_rate": 7.777851165098012e-05,
135
+ "loss": 0.9007,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 0.019923901764095468,
140
+ "grad_norm": 5.7058281898498535,
141
  "learning_rate": 7.500000000000001e-05,
142
+ "loss": 0.8773,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 0.021030785195434106,
147
+ "grad_norm": 1.7850654125213623,
148
  "learning_rate": 7.211443451095007e-05,
149
+ "loss": 0.8126,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 0.022137668626772744,
154
+ "grad_norm": 2.6662025451660156,
155
  "learning_rate": 6.91341716182545e-05,
156
+ "loss": 0.8211,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 0.02324455205811138,
161
+ "grad_norm": 3.7465245723724365,
162
  "learning_rate": 6.607197326515808e-05,
163
+ "loss": 0.8285,
164
  "step": 21
165
  },
166
  {
167
  "epoch": 0.024351435489450016,
168
+ "grad_norm": 2.968583106994629,
169
  "learning_rate": 6.294095225512603e-05,
170
+ "loss": 0.8277,
171
  "step": 22
172
  },
173
  {
174
  "epoch": 0.025458318920788654,
175
+ "grad_norm": 3.757707118988037,
176
  "learning_rate": 5.9754516100806423e-05,
177
+ "loss": 0.837,
178
  "step": 23
179
  },
180
  {
181
  "epoch": 0.026565202352127292,
182
+ "grad_norm": 2.685856819152832,
183
  "learning_rate": 5.6526309611002594e-05,
184
+ "loss": 0.8252,
185
  "step": 24
186
  },
187
  {
188
  "epoch": 0.02767208578346593,
189
+ "grad_norm": 1.0243080854415894,
190
  "learning_rate": 5.327015646150716e-05,
191
+ "loss": 0.8141,
192
  "step": 25
193
  },
194
  {
195
  "epoch": 0.02767208578346593,
196
+ "eval_loss": 0.8222277760505676,
197
+ "eval_runtime": 89.3598,
198
+ "eval_samples_per_second": 68.118,
199
+ "eval_steps_per_second": 8.516,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.028778969214804564,
204
+ "grad_norm": 3.0080807209014893,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.9145,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.029885852646143202,
211
+ "grad_norm": 2.8045029640197754,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.8326,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.03099273607748184,
218
+ "grad_norm": 3.050093650817871,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.837,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.032099619508820475,
225
+ "grad_norm": 1.8100552558898926,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.8148,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.033206502940159116,
232
+ "grad_norm": 0.6173565983772278,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.8092,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.03431338637149775,
239
+ "grad_norm": 2.0464441776275635,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.8168,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.03542026980283639,
246
+ "grad_norm": 1.4440017938613892,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.8162,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.036527153234175026,
253
+ "grad_norm": 2.4262752532958984,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.8163,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.03763403666551366,
260
+ "grad_norm": 2.298917770385742,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.8168,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.0387409200968523,
267
+ "grad_norm": 1.1494072675704956,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.8033,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.039847803528190937,
274
+ "grad_norm": 1.958591103553772,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.816,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.04095468695952958,
281
+ "grad_norm": 1.2668371200561523,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.8166,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.04206157039086821,
288
+ "grad_norm": 8.448751449584961,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.9111,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.04316845382220685,
295
+ "grad_norm": 1.2192939519882202,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.8169,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.04427533725354549,
302
+ "grad_norm": 1.0346091985702515,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.8078,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.04538222068488412,
309
+ "grad_norm": 1.4591094255447388,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.8157,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.04648910411622276,
316
+ "grad_norm": 1.394374966621399,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.8201,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.0475959875475614,
323
+ "grad_norm": 0.9946521520614624,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.7994,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.04870287097890003,
330
+ "grad_norm": 2.7818994522094727,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.8094,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.049809754410238674,
337
+ "grad_norm": 1.1283369064331055,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.8056,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.05091663784157731,
344
+ "grad_norm": 2.364039897918701,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.8047,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.05202352127291594,
351
+ "grad_norm": 1.2310731410980225,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.8056,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.053130404704254584,
358
+ "grad_norm": 1.6164497137069702,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.8095,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.05423728813559322,
365
+ "grad_norm": 1.5398378372192383,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.8131,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.05534417156693186,
372
+ "grad_norm": 1.5684233903884888,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.8126,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.05534417156693186,
379
+ "eval_loss": 0.8100725412368774,
380
+ "eval_runtime": 89.7914,
381
+ "eval_samples_per_second": 67.79,
382
+ "eval_steps_per_second": 8.475,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
404
  "should_evaluate": false,
405
  "should_log": false,
406
  "should_save": true,
407
+ "should_training_stop": true
408
  },
409
  "attributes": {}
410
  }
411
  },
412
+ "total_flos": 1.6535390389692006e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7585702810afab1a596eec3bf36188145c60d08d63b6a9e1c02b97bf5d9db974
3
  size 6776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:577d01dc374f8e5a2514555d4a0c92393ef3eeefc10650a2c95324a56f7d94b6
3
  size 6776