zanesmit29 commited on
Commit
8b279c0
·
verified ·
1 Parent(s): 7b8f3ab

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - text-classification
7
+ - emotion-classification
8
+ - roberta
9
+ - the-founder
10
+ datasets:
11
+ - dair-ai/emotion
12
+ metrics:
13
+ - accuracy
14
+ base_model: FacebookAI/roberta-base
15
+ pipeline_tag: text-classification
16
+ model-index:
17
+ - name: founder-roberta-emotion-v1
18
+ results:
19
+ - task:
20
+ type: text-classification
21
+ name: Text Classification
22
+ dataset:
23
+ name: dair-ai/emotion
24
+ type: dair-ai/emotion
25
+ split: validation
26
+ metrics:
27
+ - type: accuracy
28
+ value: 0.9395
29
+ name: Accuracy
30
+ - type: loss
31
+ value: 0.2677
32
+ name: Eval Loss
33
+ ---
34
+
35
+ # founder-roberta-emotion-v1
36
+
37
+ Fine-tuned by **The Founder** — an autonomous ML orchestration superagent.
38
+
39
+ ## Model Description
40
+
41
+ Fine-tuned `roberta-base` on `dair-ai/emotion` for 6-class emotion classification (sadness, joy, love, anger, fear, surprise).
42
+
43
+ ## Model Details
44
+
45
+ | Property | Value |
46
+ |---|---|
47
+ | Base model | roberta-base |
48
+ | Dataset | dair-ai/emotion |
49
+ | Epochs | 4 |
50
+ | Batch size | 32 |
51
+ | Learning rate | 2e-05 |
52
+ | GPU | Tesla T4 (Kaggle) |
53
+ | Train loss | 0.7915 |
54
+ | Eval loss | 0.2677 |
55
+ | Eval accuracy | 0.9395 |
56
+ | Duration | 12.3 min |
57
+
58
+ ## How to Get Started
59
+
60
+ ```python
61
+ from transformers import pipeline
62
+ clf = pipeline("text-classification", model="zanesmit29/founder-roberta-emotion-v1")
63
+ clf("I am so happy today!")
64
+ ```
65
+
66
+ ## Uses
67
+
68
+ Emotion detection across sadness, joy, love, anger, fear, surprise.
69
+
70
+ ## Training Details
71
+
72
+ ### Data
73
+ Trained on `dair-ai/emotion` — 4 epochs.
74
+
75
+ ### Hyperparameters
76
+
77
+ | Param | Value |
78
+ |---|---|
79
+ | LR | 2e-05 |
80
+ | Batch | 32 |
81
+ | Epochs | 4 |
82
+ | fp16 | true |
83
+
84
+ ## Results
85
+
86
+ | Metric | Value |
87
+ |---|---|
88
+ | Train loss | 0.7915 |
89
+ | Eval loss | 0.2677 |
90
+ | Eval accuracy | 0.9395 |
91
+ | Verdict | CONFIRMED |
92
+
93
+ ## Experiment Tracking
94
+
95
+ [W&B Run](https://wandb.ai/zane-ml/the-founder/runs/32nqzsks)
96
+
97
+ ## Infrastructure
98
+
99
+ | Component | Tool |
100
+ |---|---|
101
+ | Compute | Tesla T4 (Kaggle) |
102
+ | Tracking | Weights & Biases |
103
+ | Artifacts | HuggingFace Hub |
104
+ | Orchestration | The Founder |
checkpoint-1000/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "sadness",
16
+ "1": "joy",
17
+ "2": "love",
18
+ "3": "anger",
19
+ "4": "fear",
20
+ "5": "surprise"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "is_decoder": false,
25
+ "label2id": {
26
+ "anger": 3,
27
+ "fear": 4,
28
+ "joy": 1,
29
+ "love": 2,
30
+ "sadness": 0,
31
+ "surprise": 5
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "roberta",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 1,
39
+ "problem_type": "single_label_classification",
40
+ "tie_word_embeddings": true,
41
+ "transformers_version": "5.0.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": false,
44
+ "vocab_size": 50265
45
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d97d727d8f86ac1a57e249bbe375f2c64a918e405bf280ea9585ac85b96b39
3
+ size 498625104
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4d5abea116817e80e7a052f6967a9945f76e9cb59fa6312a019c32fa1b1dad
3
+ size 997373323
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed2fbd09ddcd3434c2368a9fde9b26015b50b16e54ac48dc68cd51b3311ceaf
3
+ size 14645
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
3
+ size 1383
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61361c878721548392539ed308adea82ec21fc99e9c9e2512a2e560c5477b77c
3
+ size 1465
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,359 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1000,
3
+ "best_metric": 0.9395,
4
+ "best_model_checkpoint": "./output/checkpoint-1000",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1,
14
+ "grad_norm": 4.507571697235107,
15
+ "learning_rate": 2.4000000000000003e-06,
16
+ "loss": 3.6814801025390627,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.2,
21
+ "grad_norm": 5.898707389831543,
22
+ "learning_rate": 4.9000000000000005e-06,
23
+ "loss": 3.506214599609375,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.3,
28
+ "grad_norm": 8.463967323303223,
29
+ "learning_rate": 7.4e-06,
30
+ "loss": 3.1335317993164065,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.4,
35
+ "grad_norm": 12.804802894592285,
36
+ "learning_rate": 9.9e-06,
37
+ "loss": 2.86414794921875,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.5,
42
+ "grad_norm": 17.248327255249023,
43
+ "learning_rate": 1.2400000000000002e-05,
44
+ "loss": 2.2183343505859376,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.6,
49
+ "grad_norm": 26.214523315429688,
50
+ "learning_rate": 1.4900000000000001e-05,
51
+ "loss": 1.6969413757324219,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.7,
56
+ "grad_norm": 25.541751861572266,
57
+ "learning_rate": 1.7400000000000003e-05,
58
+ "loss": 1.355454559326172,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 0.8,
63
+ "grad_norm": 29.073373794555664,
64
+ "learning_rate": 1.9900000000000003e-05,
65
+ "loss": 1.1928968811035157,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 0.9,
70
+ "grad_norm": 20.221284866333008,
71
+ "learning_rate": 1.94e-05,
72
+ "loss": 0.8974443054199219,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 1.0,
77
+ "grad_norm": 16.163564682006836,
78
+ "learning_rate": 1.8775000000000002e-05,
79
+ "loss": 0.8238192749023437,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 1.0,
84
+ "eval_accuracy": 0.903,
85
+ "eval_loss": 0.5729588866233826,
86
+ "eval_runtime": 6.6811,
87
+ "eval_samples_per_second": 299.352,
88
+ "eval_steps_per_second": 2.395,
89
+ "step": 250
90
+ },
91
+ {
92
+ "epoch": 1.1,
93
+ "grad_norm": 23.14790916442871,
94
+ "learning_rate": 1.815e-05,
95
+ "loss": 0.5758992385864258,
96
+ "step": 275
97
+ },
98
+ {
99
+ "epoch": 1.2,
100
+ "grad_norm": 26.1975040435791,
101
+ "learning_rate": 1.7525000000000002e-05,
102
+ "loss": 0.589322738647461,
103
+ "step": 300
104
+ },
105
+ {
106
+ "epoch": 1.3,
107
+ "grad_norm": 21.341732025146484,
108
+ "learning_rate": 1.69e-05,
109
+ "loss": 0.5247846984863281,
110
+ "step": 325
111
+ },
112
+ {
113
+ "epoch": 1.4,
114
+ "grad_norm": 25.669605255126953,
115
+ "learning_rate": 1.6275e-05,
116
+ "loss": 0.542167854309082,
117
+ "step": 350
118
+ },
119
+ {
120
+ "epoch": 1.5,
121
+ "grad_norm": 20.174819946289062,
122
+ "learning_rate": 1.565e-05,
123
+ "loss": 0.5534855651855469,
124
+ "step": 375
125
+ },
126
+ {
127
+ "epoch": 1.6,
128
+ "grad_norm": 21.812488555908203,
129
+ "learning_rate": 1.5025000000000001e-05,
130
+ "loss": 0.4083445739746094,
131
+ "step": 400
132
+ },
133
+ {
134
+ "epoch": 1.7,
135
+ "grad_norm": 12.833174705505371,
136
+ "learning_rate": 1.4400000000000001e-05,
137
+ "loss": 0.4940061187744141,
138
+ "step": 425
139
+ },
140
+ {
141
+ "epoch": 1.8,
142
+ "grad_norm": 18.026479721069336,
143
+ "learning_rate": 1.3775000000000001e-05,
144
+ "loss": 0.4515077590942383,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 1.9,
149
+ "grad_norm": 11.27204704284668,
150
+ "learning_rate": 1.3150000000000001e-05,
151
+ "loss": 0.5152847671508789,
152
+ "step": 475
153
+ },
154
+ {
155
+ "epoch": 2.0,
156
+ "grad_norm": 14.681392669677734,
157
+ "learning_rate": 1.2525000000000001e-05,
158
+ "loss": 0.37565738677978516,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 2.0,
163
+ "eval_accuracy": 0.934,
164
+ "eval_loss": 0.3546564280986786,
165
+ "eval_runtime": 6.7021,
166
+ "eval_samples_per_second": 298.415,
167
+ "eval_steps_per_second": 2.387,
168
+ "step": 500
169
+ },
170
+ {
171
+ "epoch": 2.1,
172
+ "grad_norm": 10.114750862121582,
173
+ "learning_rate": 1.1900000000000001e-05,
174
+ "loss": 0.3353092575073242,
175
+ "step": 525
176
+ },
177
+ {
178
+ "epoch": 2.2,
179
+ "grad_norm": 15.374469757080078,
180
+ "learning_rate": 1.1275e-05,
181
+ "loss": 0.3263074493408203,
182
+ "step": 550
183
+ },
184
+ {
185
+ "epoch": 2.3,
186
+ "grad_norm": 15.985736846923828,
187
+ "learning_rate": 1.065e-05,
188
+ "loss": 0.29777233123779295,
189
+ "step": 575
190
+ },
191
+ {
192
+ "epoch": 2.4,
193
+ "grad_norm": 3.142488956451416,
194
+ "learning_rate": 1.0025e-05,
195
+ "loss": 0.3357927703857422,
196
+ "step": 600
197
+ },
198
+ {
199
+ "epoch": 2.5,
200
+ "grad_norm": 18.786211013793945,
201
+ "learning_rate": 9.4e-06,
202
+ "loss": 0.3292089462280273,
203
+ "step": 625
204
+ },
205
+ {
206
+ "epoch": 2.6,
207
+ "grad_norm": 15.298687934875488,
208
+ "learning_rate": 8.775e-06,
209
+ "loss": 0.2830336380004883,
210
+ "step": 650
211
+ },
212
+ {
213
+ "epoch": 2.7,
214
+ "grad_norm": 17.82750129699707,
215
+ "learning_rate": 8.15e-06,
216
+ "loss": 0.29575424194335936,
217
+ "step": 675
218
+ },
219
+ {
220
+ "epoch": 2.8,
221
+ "grad_norm": 12.27523422241211,
222
+ "learning_rate": 7.525e-06,
223
+ "loss": 0.25342252731323245,
224
+ "step": 700
225
+ },
226
+ {
227
+ "epoch": 2.9,
228
+ "grad_norm": 30.67465591430664,
229
+ "learning_rate": 6.9e-06,
230
+ "loss": 0.30169628143310545,
231
+ "step": 725
232
+ },
233
+ {
234
+ "epoch": 3.0,
235
+ "grad_norm": 9.317840576171875,
236
+ "learning_rate": 6.275e-06,
237
+ "loss": 0.24922727584838866,
238
+ "step": 750
239
+ },
240
+ {
241
+ "epoch": 3.0,
242
+ "eval_accuracy": 0.937,
243
+ "eval_loss": 0.30609381198883057,
244
+ "eval_runtime": 6.7042,
245
+ "eval_samples_per_second": 298.32,
246
+ "eval_steps_per_second": 2.387,
247
+ "step": 750
248
+ },
249
+ {
250
+ "epoch": 3.1,
251
+ "grad_norm": 9.412005424499512,
252
+ "learning_rate": 5.65e-06,
253
+ "loss": 0.2152678108215332,
254
+ "step": 775
255
+ },
256
+ {
257
+ "epoch": 3.2,
258
+ "grad_norm": 11.898369789123535,
259
+ "learning_rate": 5.025e-06,
260
+ "loss": 0.22839365005493165,
261
+ "step": 800
262
+ },
263
+ {
264
+ "epoch": 3.3,
265
+ "grad_norm": 6.509584903717041,
266
+ "learning_rate": 4.4e-06,
267
+ "loss": 0.17845321655273438,
268
+ "step": 825
269
+ },
270
+ {
271
+ "epoch": 3.4,
272
+ "grad_norm": 12.26495361328125,
273
+ "learning_rate": 3.7750000000000003e-06,
274
+ "loss": 0.2547836685180664,
275
+ "step": 850
276
+ },
277
+ {
278
+ "epoch": 3.5,
279
+ "grad_norm": 5.428549766540527,
280
+ "learning_rate": 3.1500000000000003e-06,
281
+ "loss": 0.2100139617919922,
282
+ "step": 875
283
+ },
284
+ {
285
+ "epoch": 3.6,
286
+ "grad_norm": 6.955765247344971,
287
+ "learning_rate": 2.5250000000000004e-06,
288
+ "loss": 0.23445463180541992,
289
+ "step": 900
290
+ },
291
+ {
292
+ "epoch": 3.7,
293
+ "grad_norm": 9.735920906066895,
294
+ "learning_rate": 1.9000000000000002e-06,
295
+ "loss": 0.27971372604370115,
296
+ "step": 925
297
+ },
298
+ {
299
+ "epoch": 3.8,
300
+ "grad_norm": 13.052578926086426,
301
+ "learning_rate": 1.275e-06,
302
+ "loss": 0.23261383056640625,
303
+ "step": 950
304
+ },
305
+ {
306
+ "epoch": 3.9,
307
+ "grad_norm": 11.387779235839844,
308
+ "learning_rate": 6.5e-07,
309
+ "loss": 0.21589536666870118,
310
+ "step": 975
311
+ },
312
+ {
313
+ "epoch": 4.0,
314
+ "grad_norm": 14.187065124511719,
315
+ "learning_rate": 2.5000000000000002e-08,
316
+ "loss": 0.2018463706970215,
317
+ "step": 1000
318
+ },
319
+ {
320
+ "epoch": 4.0,
321
+ "eval_accuracy": 0.9395,
322
+ "eval_loss": 0.26765453815460205,
323
+ "eval_runtime": 6.6779,
324
+ "eval_samples_per_second": 299.497,
325
+ "eval_steps_per_second": 2.396,
326
+ "step": 1000
327
+ }
328
+ ],
329
+ "logging_steps": 25,
330
+ "max_steps": 1000,
331
+ "num_input_tokens_seen": 0,
332
+ "num_train_epochs": 4,
333
+ "save_steps": 500,
334
+ "stateful_callbacks": {
335
+ "EarlyStoppingCallback": {
336
+ "args": {
337
+ "early_stopping_patience": 1,
338
+ "early_stopping_threshold": 0.0
339
+ },
340
+ "attributes": {
341
+ "early_stopping_patience_counter": 0
342
+ }
343
+ },
344
+ "TrainerControl": {
345
+ "args": {
346
+ "should_epoch_stop": false,
347
+ "should_evaluate": false,
348
+ "should_log": false,
349
+ "should_save": true,
350
+ "should_training_stop": true
351
+ },
352
+ "attributes": {}
353
+ }
354
+ },
355
+ "total_flos": 4209928077312000.0,
356
+ "train_batch_size": 64,
357
+ "trial_name": null,
358
+ "trial_params": null
359
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2210d162572ae3962ec86b93ca0b318e7ca63a1662ce34aa255ae4b9d996d978
3
+ size 5201
checkpoint-250/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "sadness",
16
+ "1": "joy",
17
+ "2": "love",
18
+ "3": "anger",
19
+ "4": "fear",
20
+ "5": "surprise"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "is_decoder": false,
25
+ "label2id": {
26
+ "anger": 3,
27
+ "fear": 4,
28
+ "joy": 1,
29
+ "love": 2,
30
+ "sadness": 0,
31
+ "surprise": 5
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "roberta",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 1,
39
+ "problem_type": "single_label_classification",
40
+ "tie_word_embeddings": true,
41
+ "transformers_version": "5.0.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": false,
44
+ "vocab_size": 50265
45
+ }
checkpoint-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42495cd53bcebc50a1bda3e0f3fc374072770c44fbce9a4eb69787fdc559deb
3
+ size 498625104
checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b1492df7cd45b6bb92f0576acf90f3a17a6dc2356cb0ece9013509bc249230
3
+ size 997373323
checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b6dbaa11f52d366d1c4dfbb986861dd4b88bf4faebe81ca72db035ba2a3f5b
3
+ size 14645
checkpoint-250/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d6fca631a6bcdfa2416587314d206a68f40e27a07bc674b76e72a93db4e5058
3
+ size 1383
checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:920c295af972e644a79ddbf265ba82b3c0ca353066926222320f2d10c02f9718
3
+ size 1465
checkpoint-250/trainer_state.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 250,
3
+ "best_metric": 0.903,
4
+ "best_model_checkpoint": "./output/checkpoint-250",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 250,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1,
14
+ "grad_norm": 4.507571697235107,
15
+ "learning_rate": 2.4000000000000003e-06,
16
+ "loss": 3.6814801025390627,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.2,
21
+ "grad_norm": 5.898707389831543,
22
+ "learning_rate": 4.9000000000000005e-06,
23
+ "loss": 3.506214599609375,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.3,
28
+ "grad_norm": 8.463967323303223,
29
+ "learning_rate": 7.4e-06,
30
+ "loss": 3.1335317993164065,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.4,
35
+ "grad_norm": 12.804802894592285,
36
+ "learning_rate": 9.9e-06,
37
+ "loss": 2.86414794921875,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.5,
42
+ "grad_norm": 17.248327255249023,
43
+ "learning_rate": 1.2400000000000002e-05,
44
+ "loss": 2.2183343505859376,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.6,
49
+ "grad_norm": 26.214523315429688,
50
+ "learning_rate": 1.4900000000000001e-05,
51
+ "loss": 1.6969413757324219,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.7,
56
+ "grad_norm": 25.541751861572266,
57
+ "learning_rate": 1.7400000000000003e-05,
58
+ "loss": 1.355454559326172,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 0.8,
63
+ "grad_norm": 29.073373794555664,
64
+ "learning_rate": 1.9900000000000003e-05,
65
+ "loss": 1.1928968811035157,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 0.9,
70
+ "grad_norm": 20.221284866333008,
71
+ "learning_rate": 1.94e-05,
72
+ "loss": 0.8974443054199219,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 1.0,
77
+ "grad_norm": 16.163564682006836,
78
+ "learning_rate": 1.8775000000000002e-05,
79
+ "loss": 0.8238192749023437,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 1.0,
84
+ "eval_accuracy": 0.903,
85
+ "eval_loss": 0.5729588866233826,
86
+ "eval_runtime": 6.6811,
87
+ "eval_samples_per_second": 299.352,
88
+ "eval_steps_per_second": 2.395,
89
+ "step": 250
90
+ }
91
+ ],
92
+ "logging_steps": 25,
93
+ "max_steps": 1000,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 4,
96
+ "save_steps": 500,
97
+ "stateful_callbacks": {
98
+ "EarlyStoppingCallback": {
99
+ "args": {
100
+ "early_stopping_patience": 1,
101
+ "early_stopping_threshold": 0.0
102
+ },
103
+ "attributes": {
104
+ "early_stopping_patience_counter": 0
105
+ }
106
+ },
107
+ "TrainerControl": {
108
+ "args": {
109
+ "should_epoch_stop": false,
110
+ "should_evaluate": false,
111
+ "should_log": false,
112
+ "should_save": true,
113
+ "should_training_stop": false
114
+ },
115
+ "attributes": {}
116
+ }
117
+ },
118
+ "total_flos": 1052482019328000.0,
119
+ "train_batch_size": 64,
120
+ "trial_name": null,
121
+ "trial_params": null
122
+ }
checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2210d162572ae3962ec86b93ca0b318e7ca63a1662ce34aa255ae4b9d996d978
3
+ size 5201
checkpoint-500/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "sadness",
16
+ "1": "joy",
17
+ "2": "love",
18
+ "3": "anger",
19
+ "4": "fear",
20
+ "5": "surprise"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "is_decoder": false,
25
+ "label2id": {
26
+ "anger": 3,
27
+ "fear": 4,
28
+ "joy": 1,
29
+ "love": 2,
30
+ "sadness": 0,
31
+ "surprise": 5
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "roberta",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 1,
39
+ "problem_type": "single_label_classification",
40
+ "tie_word_embeddings": true,
41
+ "transformers_version": "5.0.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": false,
44
+ "vocab_size": 50265
45
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c04ff6a8621c743d53b17ddea8ad7825060cb758df47b0a87b45f3534ce0b9
3
+ size 498625104
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc60f683fae65d1789c9fe0c4e21e524d938aacfddea8437543774ade616298e
3
+ size 997373323
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c74e95a56cdb87f4944953dd780501a582be6d12a7fa54e9acd7424973c17ed
3
+ size 14645
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
3
+ size 1383
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb14a4220921b8ce709b2d94893f8fbd9a2aa160665bde70fdf907285125a339
3
+ size 1465
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 500,
3
+ "best_metric": 0.934,
4
+ "best_model_checkpoint": "./output/checkpoint-500",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1,
14
+ "grad_norm": 4.507571697235107,
15
+ "learning_rate": 2.4000000000000003e-06,
16
+ "loss": 3.6814801025390627,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.2,
21
+ "grad_norm": 5.898707389831543,
22
+ "learning_rate": 4.9000000000000005e-06,
23
+ "loss": 3.506214599609375,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.3,
28
+ "grad_norm": 8.463967323303223,
29
+ "learning_rate": 7.4e-06,
30
+ "loss": 3.1335317993164065,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.4,
35
+ "grad_norm": 12.804802894592285,
36
+ "learning_rate": 9.9e-06,
37
+ "loss": 2.86414794921875,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.5,
42
+ "grad_norm": 17.248327255249023,
43
+ "learning_rate": 1.2400000000000002e-05,
44
+ "loss": 2.2183343505859376,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.6,
49
+ "grad_norm": 26.214523315429688,
50
+ "learning_rate": 1.4900000000000001e-05,
51
+ "loss": 1.6969413757324219,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.7,
56
+ "grad_norm": 25.541751861572266,
57
+ "learning_rate": 1.7400000000000003e-05,
58
+ "loss": 1.355454559326172,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 0.8,
63
+ "grad_norm": 29.073373794555664,
64
+ "learning_rate": 1.9900000000000003e-05,
65
+ "loss": 1.1928968811035157,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 0.9,
70
+ "grad_norm": 20.221284866333008,
71
+ "learning_rate": 1.94e-05,
72
+ "loss": 0.8974443054199219,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 1.0,
77
+ "grad_norm": 16.163564682006836,
78
+ "learning_rate": 1.8775000000000002e-05,
79
+ "loss": 0.8238192749023437,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 1.0,
84
+ "eval_accuracy": 0.903,
85
+ "eval_loss": 0.5729588866233826,
86
+ "eval_runtime": 6.6811,
87
+ "eval_samples_per_second": 299.352,
88
+ "eval_steps_per_second": 2.395,
89
+ "step": 250
90
+ },
91
+ {
92
+ "epoch": 1.1,
93
+ "grad_norm": 23.14790916442871,
94
+ "learning_rate": 1.815e-05,
95
+ "loss": 0.5758992385864258,
96
+ "step": 275
97
+ },
98
+ {
99
+ "epoch": 1.2,
100
+ "grad_norm": 26.1975040435791,
101
+ "learning_rate": 1.7525000000000002e-05,
102
+ "loss": 0.589322738647461,
103
+ "step": 300
104
+ },
105
+ {
106
+ "epoch": 1.3,
107
+ "grad_norm": 21.341732025146484,
108
+ "learning_rate": 1.69e-05,
109
+ "loss": 0.5247846984863281,
110
+ "step": 325
111
+ },
112
+ {
113
+ "epoch": 1.4,
114
+ "grad_norm": 25.669605255126953,
115
+ "learning_rate": 1.6275e-05,
116
+ "loss": 0.542167854309082,
117
+ "step": 350
118
+ },
119
+ {
120
+ "epoch": 1.5,
121
+ "grad_norm": 20.174819946289062,
122
+ "learning_rate": 1.565e-05,
123
+ "loss": 0.5534855651855469,
124
+ "step": 375
125
+ },
126
+ {
127
+ "epoch": 1.6,
128
+ "grad_norm": 21.812488555908203,
129
+ "learning_rate": 1.5025000000000001e-05,
130
+ "loss": 0.4083445739746094,
131
+ "step": 400
132
+ },
133
+ {
134
+ "epoch": 1.7,
135
+ "grad_norm": 12.833174705505371,
136
+ "learning_rate": 1.4400000000000001e-05,
137
+ "loss": 0.4940061187744141,
138
+ "step": 425
139
+ },
140
+ {
141
+ "epoch": 1.8,
142
+ "grad_norm": 18.026479721069336,
143
+ "learning_rate": 1.3775000000000001e-05,
144
+ "loss": 0.4515077590942383,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 1.9,
149
+ "grad_norm": 11.27204704284668,
150
+ "learning_rate": 1.3150000000000001e-05,
151
+ "loss": 0.5152847671508789,
152
+ "step": 475
153
+ },
154
+ {
155
+ "epoch": 2.0,
156
+ "grad_norm": 14.681392669677734,
157
+ "learning_rate": 1.2525000000000001e-05,
158
+ "loss": 0.37565738677978516,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 2.0,
163
+ "eval_accuracy": 0.934,
164
+ "eval_loss": 0.3546564280986786,
165
+ "eval_runtime": 6.7021,
166
+ "eval_samples_per_second": 298.415,
167
+ "eval_steps_per_second": 2.387,
168
+ "step": 500
169
+ }
170
+ ],
171
+ "logging_steps": 25,
172
+ "max_steps": 1000,
173
+ "num_input_tokens_seen": 0,
174
+ "num_train_epochs": 4,
175
+ "save_steps": 500,
176
+ "stateful_callbacks": {
177
+ "EarlyStoppingCallback": {
178
+ "args": {
179
+ "early_stopping_patience": 1,
180
+ "early_stopping_threshold": 0.0
181
+ },
182
+ "attributes": {
183
+ "early_stopping_patience_counter": 0
184
+ }
185
+ },
186
+ "TrainerControl": {
187
+ "args": {
188
+ "should_epoch_stop": false,
189
+ "should_evaluate": false,
190
+ "should_log": false,
191
+ "should_save": true,
192
+ "should_training_stop": false
193
+ },
194
+ "attributes": {}
195
+ }
196
+ },
197
+ "total_flos": 2104964038656000.0,
198
+ "train_batch_size": 64,
199
+ "trial_name": null,
200
+ "trial_params": null
201
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2210d162572ae3962ec86b93ca0b318e7ca63a1662ce34aa255ae4b9d996d978
3
+ size 5201
checkpoint-750/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "sadness",
16
+ "1": "joy",
17
+ "2": "love",
18
+ "3": "anger",
19
+ "4": "fear",
20
+ "5": "surprise"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "is_decoder": false,
25
+ "label2id": {
26
+ "anger": 3,
27
+ "fear": 4,
28
+ "joy": 1,
29
+ "love": 2,
30
+ "sadness": 0,
31
+ "surprise": 5
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "roberta",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 1,
39
+ "problem_type": "single_label_classification",
40
+ "tie_word_embeddings": true,
41
+ "transformers_version": "5.0.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": false,
44
+ "vocab_size": 50265
45
+ }
checkpoint-750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f5e483dbb3519a9e3a49088977f174fcc8ec07d9e87316b3dc03612b1118bf7
3
+ size 498625104
checkpoint-750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:184933aa7ad81e401b2dbdc31380cfd0aef2bb545caaab42e480fc37fe987f07
3
+ size 997373323
checkpoint-750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a536234caa7b19234ab48fd8b5c45a3a6e051200b40108ebce9a97093280f9
3
+ size 14645
checkpoint-750/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca8377b2ea0b440a1b7c1913409d5ce08c05c7f94eb3857477a86af97a6ec03
3
+ size 1383
checkpoint-750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ec6f48fc5c7ebd34d4def68a5b9f88666196b21da5b95563dd9f5bdd9f5009
3
+ size 1465
checkpoint-750/trainer_state.json ADDED
@@ -0,0 +1,280 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 750,
3
+ "best_metric": 0.937,
4
+ "best_model_checkpoint": "./output/checkpoint-750",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 750,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1,
14
+ "grad_norm": 4.507571697235107,
15
+ "learning_rate": 2.4000000000000003e-06,
16
+ "loss": 3.6814801025390627,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.2,
21
+ "grad_norm": 5.898707389831543,
22
+ "learning_rate": 4.9000000000000005e-06,
23
+ "loss": 3.506214599609375,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.3,
28
+ "grad_norm": 8.463967323303223,
29
+ "learning_rate": 7.4e-06,
30
+ "loss": 3.1335317993164065,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.4,
35
+ "grad_norm": 12.804802894592285,
36
+ "learning_rate": 9.9e-06,
37
+ "loss": 2.86414794921875,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.5,
42
+ "grad_norm": 17.248327255249023,
43
+ "learning_rate": 1.2400000000000002e-05,
44
+ "loss": 2.2183343505859376,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.6,
49
+ "grad_norm": 26.214523315429688,
50
+ "learning_rate": 1.4900000000000001e-05,
51
+ "loss": 1.6969413757324219,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.7,
56
+ "grad_norm": 25.541751861572266,
57
+ "learning_rate": 1.7400000000000003e-05,
58
+ "loss": 1.355454559326172,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 0.8,
63
+ "grad_norm": 29.073373794555664,
64
+ "learning_rate": 1.9900000000000003e-05,
65
+ "loss": 1.1928968811035157,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 0.9,
70
+ "grad_norm": 20.221284866333008,
71
+ "learning_rate": 1.94e-05,
72
+ "loss": 0.8974443054199219,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 1.0,
77
+ "grad_norm": 16.163564682006836,
78
+ "learning_rate": 1.8775000000000002e-05,
79
+ "loss": 0.8238192749023437,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 1.0,
84
+ "eval_accuracy": 0.903,
85
+ "eval_loss": 0.5729588866233826,
86
+ "eval_runtime": 6.6811,
87
+ "eval_samples_per_second": 299.352,
88
+ "eval_steps_per_second": 2.395,
89
+ "step": 250
90
+ },
91
+ {
92
+ "epoch": 1.1,
93
+ "grad_norm": 23.14790916442871,
94
+ "learning_rate": 1.815e-05,
95
+ "loss": 0.5758992385864258,
96
+ "step": 275
97
+ },
98
+ {
99
+ "epoch": 1.2,
100
+ "grad_norm": 26.1975040435791,
101
+ "learning_rate": 1.7525000000000002e-05,
102
+ "loss": 0.589322738647461,
103
+ "step": 300
104
+ },
105
+ {
106
+ "epoch": 1.3,
107
+ "grad_norm": 21.341732025146484,
108
+ "learning_rate": 1.69e-05,
109
+ "loss": 0.5247846984863281,
110
+ "step": 325
111
+ },
112
+ {
113
+ "epoch": 1.4,
114
+ "grad_norm": 25.669605255126953,
115
+ "learning_rate": 1.6275e-05,
116
+ "loss": 0.542167854309082,
117
+ "step": 350
118
+ },
119
+ {
120
+ "epoch": 1.5,
121
+ "grad_norm": 20.174819946289062,
122
+ "learning_rate": 1.565e-05,
123
+ "loss": 0.5534855651855469,
124
+ "step": 375
125
+ },
126
+ {
127
+ "epoch": 1.6,
128
+ "grad_norm": 21.812488555908203,
129
+ "learning_rate": 1.5025000000000001e-05,
130
+ "loss": 0.4083445739746094,
131
+ "step": 400
132
+ },
133
+ {
134
+ "epoch": 1.7,
135
+ "grad_norm": 12.833174705505371,
136
+ "learning_rate": 1.4400000000000001e-05,
137
+ "loss": 0.4940061187744141,
138
+ "step": 425
139
+ },
140
+ {
141
+ "epoch": 1.8,
142
+ "grad_norm": 18.026479721069336,
143
+ "learning_rate": 1.3775000000000001e-05,
144
+ "loss": 0.4515077590942383,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 1.9,
149
+ "grad_norm": 11.27204704284668,
150
+ "learning_rate": 1.3150000000000001e-05,
151
+ "loss": 0.5152847671508789,
152
+ "step": 475
153
+ },
154
+ {
155
+ "epoch": 2.0,
156
+ "grad_norm": 14.681392669677734,
157
+ "learning_rate": 1.2525000000000001e-05,
158
+ "loss": 0.37565738677978516,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 2.0,
163
+ "eval_accuracy": 0.934,
164
+ "eval_loss": 0.3546564280986786,
165
+ "eval_runtime": 6.7021,
166
+ "eval_samples_per_second": 298.415,
167
+ "eval_steps_per_second": 2.387,
168
+ "step": 500
169
+ },
170
+ {
171
+ "epoch": 2.1,
172
+ "grad_norm": 10.114750862121582,
173
+ "learning_rate": 1.1900000000000001e-05,
174
+ "loss": 0.3353092575073242,
175
+ "step": 525
176
+ },
177
+ {
178
+ "epoch": 2.2,
179
+ "grad_norm": 15.374469757080078,
180
+ "learning_rate": 1.1275e-05,
181
+ "loss": 0.3263074493408203,
182
+ "step": 550
183
+ },
184
+ {
185
+ "epoch": 2.3,
186
+ "grad_norm": 15.985736846923828,
187
+ "learning_rate": 1.065e-05,
188
+ "loss": 0.29777233123779295,
189
+ "step": 575
190
+ },
191
+ {
192
+ "epoch": 2.4,
193
+ "grad_norm": 3.142488956451416,
194
+ "learning_rate": 1.0025e-05,
195
+ "loss": 0.3357927703857422,
196
+ "step": 600
197
+ },
198
+ {
199
+ "epoch": 2.5,
200
+ "grad_norm": 18.786211013793945,
201
+ "learning_rate": 9.4e-06,
202
+ "loss": 0.3292089462280273,
203
+ "step": 625
204
+ },
205
+ {
206
+ "epoch": 2.6,
207
+ "grad_norm": 15.298687934875488,
208
+ "learning_rate": 8.775e-06,
209
+ "loss": 0.2830336380004883,
210
+ "step": 650
211
+ },
212
+ {
213
+ "epoch": 2.7,
214
+ "grad_norm": 17.82750129699707,
215
+ "learning_rate": 8.15e-06,
216
+ "loss": 0.29575424194335936,
217
+ "step": 675
218
+ },
219
+ {
220
+ "epoch": 2.8,
221
+ "grad_norm": 12.27523422241211,
222
+ "learning_rate": 7.525e-06,
223
+ "loss": 0.25342252731323245,
224
+ "step": 700
225
+ },
226
+ {
227
+ "epoch": 2.9,
228
+ "grad_norm": 30.67465591430664,
229
+ "learning_rate": 6.9e-06,
230
+ "loss": 0.30169628143310545,
231
+ "step": 725
232
+ },
233
+ {
234
+ "epoch": 3.0,
235
+ "grad_norm": 9.317840576171875,
236
+ "learning_rate": 6.275e-06,
237
+ "loss": 0.24922727584838866,
238
+ "step": 750
239
+ },
240
+ {
241
+ "epoch": 3.0,
242
+ "eval_accuracy": 0.937,
243
+ "eval_loss": 0.30609381198883057,
244
+ "eval_runtime": 6.7042,
245
+ "eval_samples_per_second": 298.32,
246
+ "eval_steps_per_second": 2.387,
247
+ "step": 750
248
+ }
249
+ ],
250
+ "logging_steps": 25,
251
+ "max_steps": 1000,
252
+ "num_input_tokens_seen": 0,
253
+ "num_train_epochs": 4,
254
+ "save_steps": 500,
255
+ "stateful_callbacks": {
256
+ "EarlyStoppingCallback": {
257
+ "args": {
258
+ "early_stopping_patience": 1,
259
+ "early_stopping_threshold": 0.0
260
+ },
261
+ "attributes": {
262
+ "early_stopping_patience_counter": 0
263
+ }
264
+ },
265
+ "TrainerControl": {
266
+ "args": {
267
+ "should_epoch_stop": false,
268
+ "should_evaluate": false,
269
+ "should_log": false,
270
+ "should_save": true,
271
+ "should_training_stop": false
272
+ },
273
+ "attributes": {}
274
+ }
275
+ },
276
+ "total_flos": 3157446057984000.0,
277
+ "train_batch_size": 64,
278
+ "trial_name": null,
279
+ "trial_params": null
280
+ }
checkpoint-750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2210d162572ae3962ec86b93ca0b318e7ca63a1662ce34aa255ae4b9d996d978
3
+ size 5201
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "sadness",
16
+ "1": "joy",
17
+ "2": "love",
18
+ "3": "anger",
19
+ "4": "fear",
20
+ "5": "surprise"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "is_decoder": false,
25
+ "label2id": {
26
+ "anger": 3,
27
+ "fear": 4,
28
+ "joy": 1,
29
+ "love": 2,
30
+ "sadness": 0,
31
+ "surprise": 5
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "roberta",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 1,
39
+ "problem_type": "single_label_classification",
40
+ "tie_word_embeddings": true,
41
+ "transformers_version": "5.0.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": false,
44
+ "vocab_size": 50265
45
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d97d727d8f86ac1a57e249bbe375f2c64a918e405bf280ea9585ac85b96b39
3
+ size 498625104
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 512,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2210d162572ae3962ec86b93ca0b318e7ca63a1662ce34aa255ae4b9d996d978
3
+ size 5201