Hugging Face's logo

nkasmanoff
/
picard-smol-ft

Safetensors
llama
Model card Files Community
nkasmanoff commited on
Commit
00daf7d
·
verified ·
1 Parent(s): cc0cb6f

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. all_results.json +8 -0
  2. model.safetensors +1 -1
  3. tokenizer.json +1 -6
  4. train_results.json +8 -0
  5. trainer_state.json +203 -0
  6. training_args.bin +1 -1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 8.16978613968e+16,
4
+ "train_loss": 0.9628061628611074,
5
+ "train_runtime": 7816.2612,
6
+ "train_samples_per_second": 3.621,
7
+ "train_steps_per_second": 0.453
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8703ca60897cfd6583e828b0c78c325ce598e323b4cba10be1853bfde34bf16f
3
  size 723674912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4dd84078e75a87e330a36d75a9de3853f1cbba8f49b2dbddcd395599cf4276
3
  size 723674912
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 2048,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 8.16978613968e+16,
4
+ "train_loss": 0.9628061628611074,
5
+ "train_runtime": 7816.2612,
6
+ "train_samples_per_second": 3.621,
7
+ "train_steps_per_second": 0.453
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3540,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.211864406779661,
13
+ "grad_norm": 0.7578125,
14
+ "learning_rate": 0.00016949152542372882,
15
+ "loss": 1.4882,
16
+ "step": 150
17
+ },
18
+ {
19
+ "epoch": 0.423728813559322,
20
+ "grad_norm": 1.0703125,
21
+ "learning_rate": 0.00019934060086830688,
22
+ "loss": 1.1689,
23
+ "step": 300
24
+ },
25
+ {
26
+ "epoch": 0.635593220338983,
27
+ "grad_norm": 1.09375,
28
+ "learning_rate": 0.00019676565602164643,
29
+ "loss": 1.1984,
30
+ "step": 450
31
+ },
32
+ {
33
+ "epoch": 0.847457627118644,
34
+ "grad_norm": 0.9140625,
35
+ "learning_rate": 0.00019229383471353536,
36
+ "loss": 1.1429,
37
+ "step": 600
38
+ },
39
+ {
40
+ "epoch": 1.0593220338983051,
41
+ "grad_norm": 1.0703125,
42
+ "learning_rate": 0.00018601279710076812,
43
+ "loss": 1.1166,
44
+ "step": 750
45
+ },
46
+ {
47
+ "epoch": 1.271186440677966,
48
+ "grad_norm": 1.0,
49
+ "learning_rate": 0.00017804566902045448,
50
+ "loss": 1.0057,
51
+ "step": 900
52
+ },
53
+ {
54
+ "epoch": 1.4830508474576272,
55
+ "grad_norm": 0.796875,
56
+ "learning_rate": 0.00016854862838056546,
57
+ "loss": 1.003,
58
+ "step": 1050
59
+ },
60
+ {
61
+ "epoch": 1.694915254237288,
62
+ "grad_norm": 0.68359375,
63
+ "learning_rate": 0.0001577078436378025,
64
+ "loss": 0.9752,
65
+ "step": 1200
66
+ },
67
+ {
68
+ "epoch": 1.9067796610169492,
69
+ "grad_norm": 0.8125,
70
+ "learning_rate": 0.00014573582437715308,
71
+ "loss": 1.0262,
72
+ "step": 1350
73
+ },
74
+ {
75
+ "epoch": 2.1186440677966103,
76
+ "grad_norm": 0.85546875,
77
+ "learning_rate": 0.00013286725553194177,
78
+ "loss": 0.9129,
79
+ "step": 1500
80
+ },
81
+ {
82
+ "epoch": 2.330508474576271,
83
+ "grad_norm": 1.453125,
84
+ "learning_rate": 0.00011935439690527049,
85
+ "loss": 0.8845,
86
+ "step": 1650
87
+ },
88
+ {
89
+ "epoch": 2.542372881355932,
90
+ "grad_norm": 0.78515625,
91
+ "learning_rate": 0.0001054621381750442,
92
+ "loss": 0.883,
93
+ "step": 1800
94
+ },
95
+ {
96
+ "epoch": 2.7542372881355934,
97
+ "grad_norm": 0.9296875,
98
+ "learning_rate": 9.146280631826239e-05,
99
+ "loss": 0.8786,
100
+ "step": 1950
101
+ },
102
+ {
103
+ "epoch": 2.9661016949152543,
104
+ "grad_norm": 1.125,
105
+ "learning_rate": 7.763082724352662e-05,
106
+ "loss": 0.9204,
107
+ "step": 2100
108
+ },
109
+ {
110
+ "epoch": 3.1779661016949152,
111
+ "grad_norm": 1.046875,
112
+ "learning_rate": 6.423734627864077e-05,
113
+ "loss": 0.8706,
114
+ "step": 2250
115
+ },
116
+ {
117
+ "epoch": 3.389830508474576,
118
+ "grad_norm": 0.671875,
119
+ "learning_rate": 5.1544912966734994e-05,
120
+ "loss": 0.8667,
121
+ "step": 2400
122
+ },
123
+ {
124
+ "epoch": 3.601694915254237,
125
+ "grad_norm": 0.92578125,
126
+ "learning_rate": 3.980233436371869e-05,
127
+ "loss": 0.8416,
128
+ "step": 2550
129
+ },
130
+ {
131
+ "epoch": 3.8135593220338984,
132
+ "grad_norm": 0.7890625,
133
+ "learning_rate": 2.9239797726771324e-05,
134
+ "loss": 0.8213,
135
+ "step": 2700
136
+ },
137
+ {
138
+ "epoch": 4.02542372881356,
139
+ "grad_norm": 0.734375,
140
+ "learning_rate": 2.006435820276602e-05,
141
+ "loss": 0.8559,
142
+ "step": 2850
143
+ },
144
+ {
145
+ "epoch": 4.237288135593221,
146
+ "grad_norm": 0.953125,
147
+ "learning_rate": 1.2455879970504569e-05,
148
+ "loss": 0.8274,
149
+ "step": 3000
150
+ },
151
+ {
152
+ "epoch": 4.4491525423728815,
153
+ "grad_norm": 0.84375,
154
+ "learning_rate": 6.563510401684669e-06,
155
+ "loss": 0.831,
156
+ "step": 3150
157
+ },
158
+ {
159
+ "epoch": 4.661016949152542,
160
+ "grad_norm": 1.0859375,
161
+ "learning_rate": 2.50275635686813e-06,
162
+ "loss": 0.831,
163
+ "step": 3300
164
+ },
165
+ {
166
+ "epoch": 4.872881355932203,
167
+ "grad_norm": 0.7265625,
168
+ "learning_rate": 3.5321992919458146e-07,
169
+ "loss": 0.8406,
170
+ "step": 3450
171
+ },
172
+ {
173
+ "epoch": 5.0,
174
+ "step": 3540,
175
+ "total_flos": 8.16978613968e+16,
176
+ "train_loss": 0.9628061628611074,
177
+ "train_runtime": 7816.2612,
178
+ "train_samples_per_second": 3.621,
179
+ "train_steps_per_second": 0.453
180
+ }
181
+ ],
182
+ "logging_steps": 150,
183
+ "max_steps": 3540,
184
+ "num_input_tokens_seen": 0,
185
+ "num_train_epochs": 5,
186
+ "save_steps": 500,
187
+ "stateful_callbacks": {
188
+ "TrainerControl": {
189
+ "args": {
190
+ "should_epoch_stop": false,
191
+ "should_evaluate": false,
192
+ "should_log": false,
193
+ "should_save": true,
194
+ "should_training_stop": true
195
+ },
196
+ "attributes": {}
197
+ }
198
+ },
199
+ "total_flos": 8.16978613968e+16,
200
+ "train_batch_size": 8,
201
+ "trial_name": null,
202
+ "trial_params": null
203
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a733449092e57c7196eae211a7ee2c3a25984a61f13adcf9035cf1ef25f2bc1
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a886935d7e40c0037c9472e880dc93982f057a05cd837f074ad319508215f7d
3
  size 5432