Hugging Face's logo

austindixson
/
gemma-4-21b-reap-harness-ready

Transformers
Safetensors
gemma-4
agent
tool-use
fine-tuned
claude-conversations
coding
autonomous-agent
Model card Files
xet
 Community
Austin Dixson commited on
Commit
38a9297
·
1 Parent(s): 2c12888

Add complete model with LFS

Browse files
Files changed (8) hide show
  1. .gitattributes +1 -0
  2. adapter_config.json +3 -53
  3. adapter_model.safetensors +3 -0
  4. rng_state.pth +3 -0
  5. tokenizer.json +3 -0
  6. tokenizer_config.json +3 -95
  7. trainer_state.json +3 -489
  8. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ *.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json CHANGED
@@ -1,53 +1,3 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": {
6
- "base_model_class": "Gemma4ForConditionalGeneration",
7
- "parent_library": "transformers.models.gemma4.modeling_gemma4",
8
- "unsloth_fixed": true
9
- },
10
- "base_model_name_or_path": "0xSero/gemma-4-21b-a4b-it-REAP",
11
- "bias": "none",
12
- "corda_config": null,
13
- "ensure_weight_tying": false,
14
- "eva_config": null,
15
- "exclude_modules": null,
16
- "fan_in_fan_out": false,
17
- "inference_mode": true,
18
- "init_lora_weights": true,
19
- "layer_replication": null,
20
- "layers_pattern": null,
21
- "layers_to_transform": null,
22
- "loftq_config": {},
23
- "lora_alpha": 64,
24
- "lora_bias": false,
25
- "lora_dropout": 0,
26
- "megatron_config": null,
27
- "megatron_core": "megatron.core",
28
- "modules_to_save": null,
29
- "peft_type": "LORA",
30
- "peft_version": "0.18.1",
31
- "qalora_group_size": 16,
32
- "r": 32,
33
- "rank_pattern": {},
34
- "revision": null,
35
- "target_modules": [
36
- "up_proj",
37
- "o_proj",
38
- "q_proj",
39
- "k_proj",
40
- "v_proj",
41
- "down_proj",
42
- "gate_proj"
43
- ],
44
- "target_parameters": [
45
- "mlp.experts.gate_up_proj",
46
- "mlp.experts.down_proj"
47
- ],
48
- "task_type": "CAUSAL_LM",
49
- "trainable_token_indices": null,
50
- "use_dora": false,
51
- "use_qalora": false,
52
- "use_rslora": false
53
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1431581c9d913f62c52cfb0c1c7b5398742cad9b9e9eab670818c85c8cbdf7bf
3
+ size 1272
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a207203dbc2efa5760e2408e2b65a9fb13a4b61dcaf2763584996d34fea9391
3
+ size 237225680
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
3
+ size 32169626
tokenizer_config.json CHANGED
@@ -1,95 +1,3 @@
1
- {
2
- "audio_token": "<|audio|>",
3
- "backend": "tokenizers",
4
- "boa_token": "<|audio>",
5
- "boi_token": "<|image>",
6
- "bos_token": "<bos>",
7
- "eoa_token": "<audio|>",
8
- "eoc_token": "<channel|>",
9
- "eoi_token": "<image|>",
10
- "eos_token": "<eos>",
11
- "eot_token": "<turn|>",
12
- "escape_token": "<|\"|>",
13
- "etc_token": "<tool_call|>",
14
- "etd_token": "<tool|>",
15
- "etr_token": "<tool_response|>",
16
- "extra_special_tokens": [
17
- "<|video|>"
18
- ],
19
- "image_token": "<|image|>",
20
- "is_local": false,
21
- "mask_token": "<mask>",
22
- "model_max_length": 1000000000000000019884624838656,
23
- "model_specific_special_tokens": {
24
- "audio_token": "<|audio|>",
25
- "boa_token": "<|audio>",
26
- "boi_token": "<|image>",
27
- "eoa_token": "<audio|>",
28
- "eoc_token": "<channel|>",
29
- "eoi_token": "<image|>",
30
- "eot_token": "<turn|>",
31
- "escape_token": "<|\"|>",
32
- "etc_token": "<tool_call|>",
33
- "etd_token": "<tool|>",
34
- "etr_token": "<tool_response|>",
35
- "image_token": "<|image|>",
36
- "soc_token": "<|channel>",
37
- "sot_token": "<|turn>",
38
- "stc_token": "<|tool_call>",
39
- "std_token": "<|tool>",
40
- "str_token": "<|tool_response>",
41
- "think_token": "<|think|>"
42
- },
43
- "pad_token": "<pad>",
44
- "padding_side": "left",
45
- "processor_class": "Gemma4Processor",
46
- "response_schema": {
47
- "properties": {
48
- "content": {
49
- "type": "string"
50
- },
51
- "role": {
52
- "const": "assistant"
53
- },
54
- "thinking": {
55
- "type": "string"
56
- },
57
- "tool_calls": {
58
- "items": {
59
- "properties": {
60
- "function": {
61
- "properties": {
62
- "arguments": {
63
- "additionalProperties": {},
64
- "type": "object",
65
- "x-parser": "gemma4-tool-call"
66
- },
67
- "name": {
68
- "type": "string"
69
- }
70
- },
71
- "type": "object",
72
- "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
73
- },
74
- "type": {
75
- "const": "function"
76
- }
77
- },
78
- "type": "object"
79
- },
80
- "type": "array",
81
- "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
82
- }
83
- },
84
- "type": "object",
85
- "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
86
- },
87
- "soc_token": "<|channel>",
88
- "sot_token": "<|turn>",
89
- "stc_token": "<|tool_call>",
90
- "std_token": "<|tool>",
91
- "str_token": "<|tool_response>",
92
- "think_token": "<|think|>",
93
- "tokenizer_class": "GemmaTokenizer",
94
- "unk_token": "<unk>"
95
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:820ad481cb4152f8df6061f4ae6ae20255777c39b77a9970f1e3cbd427b21511
3
+ size 2686
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
trainer_state.json CHANGED
@@ -1,489 +1,3 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.6845708267509215,
6
- "eval_steps": 500,
7
- "global_step": 325,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.010531858873091101,
14
- "grad_norm": 7.945572853088379,
15
- "learning_rate": 4.4444444444444447e-05,
16
- "loss": 13.0722412109375,
17
- "step": 5
18
- },
19
- {
20
- "epoch": 0.021063717746182202,
21
- "grad_norm": 2.1900172233581543,
22
- "learning_rate": 0.0001,
23
- "loss": 8.607737731933593,
24
- "step": 10
25
- },
26
- {
27
- "epoch": 0.0315955766192733,
28
- "grad_norm": 1.9897981882095337,
29
- "learning_rate": 0.00015555555555555556,
30
- "loss": 5.214687728881836,
31
- "step": 15
32
- },
33
- {
34
- "epoch": 0.042127435492364404,
35
- "grad_norm": 0.5303641557693481,
36
- "learning_rate": 0.0002111111111111111,
37
- "loss": 5.304478454589844,
38
- "step": 20
39
- },
40
- {
41
- "epoch": 0.0526592943654555,
42
- "grad_norm": 0.6158832907676697,
43
- "learning_rate": 0.0002666666666666667,
44
- "loss": 4.097989273071289,
45
- "step": 25
46
- },
47
- {
48
- "epoch": 0.0631911532385466,
49
- "grad_norm": 0.6168912053108215,
50
- "learning_rate": 0.0003222222222222222,
51
- "loss": 4.195485305786133,
52
- "step": 30
53
- },
54
- {
55
- "epoch": 0.0737230121116377,
56
- "grad_norm": 1.1824705600738525,
57
- "learning_rate": 0.00037777777777777777,
58
- "loss": 3.989824676513672,
59
- "step": 35
60
- },
61
- {
62
- "epoch": 0.08425487098472881,
63
- "grad_norm": 23.726043701171875,
64
- "learning_rate": 0.00043333333333333337,
65
- "loss": 3.813393783569336,
66
- "step": 40
67
- },
68
- {
69
- "epoch": 0.0947867298578199,
70
- "grad_norm": 0.9648836851119995,
71
- "learning_rate": 0.0004888888888888889,
72
- "loss": 3.9115650177001955,
73
- "step": 45
74
- },
75
- {
76
- "epoch": 0.105318588730911,
77
- "grad_norm": 1.5551100969314575,
78
- "learning_rate": 0.0004999906760259783,
79
- "loss": 3.9463314056396483,
80
- "step": 50
81
- },
82
- {
83
- "epoch": 0.11585044760400211,
84
- "grad_norm": 14.366273880004883,
85
- "learning_rate": 0.0004999527985734932,
86
- "loss": 3.3652118682861327,
87
- "step": 55
88
- },
89
- {
90
- "epoch": 0.1263823064770932,
91
- "grad_norm": 0.7795851230621338,
92
- "learning_rate": 0.0004998857893053613,
93
- "loss": 4.018484497070313,
94
- "step": 60
95
- },
96
- {
97
- "epoch": 0.1369141653501843,
98
- "grad_norm": 0.8944413065910339,
99
- "learning_rate": 0.0004997896560314641,
100
- "loss": 3.566949462890625,
101
- "step": 65
102
- },
103
- {
104
- "epoch": 0.1474460242232754,
105
- "grad_norm": 0.4758361876010895,
106
- "learning_rate": 0.0004996644099560641,
107
- "loss": 3.5043781280517576,
108
- "step": 70
109
- },
110
- {
111
- "epoch": 0.1579778830963665,
112
- "grad_norm": 0.5162303447723389,
113
- "learning_rate": 0.0004995100656764997,
114
- "loss": 3.212859344482422,
115
- "step": 75
116
- },
117
- {
118
- "epoch": 0.16850974196945762,
119
- "grad_norm": 0.4172177314758301,
120
- "learning_rate": 0.0004993266411814837,
121
- "loss": 3.3035125732421875,
122
- "step": 80
123
- },
124
- {
125
- "epoch": 0.17904160084254872,
126
- "grad_norm": 4.056116580963135,
127
- "learning_rate": 0.0004991141578490066,
128
- "loss": 3.1954784393310547,
129
- "step": 85
130
- },
131
- {
132
- "epoch": 0.1895734597156398,
133
- "grad_norm": 2.0480830669403076,
134
- "learning_rate": 0.0004988726404438453,
135
- "loss": 3.452958679199219,
136
- "step": 90
137
- },
138
- {
139
- "epoch": 0.2001053185887309,
140
- "grad_norm": 0.3407100439071655,
141
- "learning_rate": 0.0004986021171146765,
142
- "loss": 3.66046028137207,
143
- "step": 95
144
- },
145
- {
146
- "epoch": 0.210637177461822,
147
- "grad_norm": 0.6314069628715515,
148
- "learning_rate": 0.0004983026193907961,
149
- "loss": 3.37341194152832,
150
- "step": 100
151
- },
152
- {
153
- "epoch": 0.2211690363349131,
154
- "grad_norm": 0.29125332832336426,
155
- "learning_rate": 0.0004979741821784446,
156
- "loss": 3.2889537811279297,
157
- "step": 105
158
- },
159
- {
160
- "epoch": 0.23170089520800422,
161
- "grad_norm": 0.3563121259212494,
162
- "learning_rate": 0.0004976168437567384,
163
- "loss": 3.55091552734375,
164
- "step": 110
165
- },
166
- {
167
- "epoch": 0.24223275408109532,
168
- "grad_norm": 0.24429726600646973,
169
- "learning_rate": 0.0004972306457732091,
170
- "loss": 3.087770462036133,
171
- "step": 115
172
- },
173
- {
174
- "epoch": 0.2527646129541864,
175
- "grad_norm": 0.36369070410728455,
176
- "learning_rate": 0.0004968156332389489,
177
- "loss": 3.1231616973876952,
178
- "step": 120
179
- },
180
- {
181
- "epoch": 0.2632964718272775,
182
- "grad_norm": 0.39639607071876526,
183
- "learning_rate": 0.0004963718545233645,
184
- "loss": 3.043613052368164,
185
- "step": 125
186
- },
187
- {
188
- "epoch": 0.2738283307003686,
189
- "grad_norm": 0.2886509299278259,
190
- "learning_rate": 0.0004958993613485406,
191
- "loss": 3.7740196228027343,
192
- "step": 130
193
- },
194
- {
195
- "epoch": 0.2843601895734597,
196
- "grad_norm": 0.31644657254219055,
197
- "learning_rate": 0.0004953982087832103,
198
- "loss": 2.8986371994018554,
199
- "step": 135
200
- },
201
- {
202
- "epoch": 0.2948920484465508,
203
- "grad_norm": 0.3337455689907074,
204
- "learning_rate": 0.0004948684552363386,
205
- "loss": 2.7170455932617186,
206
- "step": 140
207
- },
208
- {
209
- "epoch": 0.3054239073196419,
210
- "grad_norm": 0.2488539218902588,
211
- "learning_rate": 0.0004943101624503133,
212
- "loss": 2.9157670974731444,
213
- "step": 145
214
- },
215
- {
216
- "epoch": 0.315955766192733,
217
- "grad_norm": 0.42236021161079407,
218
- "learning_rate": 0.0004937233954937497,
219
- "loss": 2.7440420150756837,
220
- "step": 150
221
- },
222
- {
223
- "epoch": 0.3264876250658241,
224
- "grad_norm": 0.34990763664245605,
225
- "learning_rate": 0.000493108222753907,
226
- "loss": 3.266927719116211,
227
- "step": 155
228
- },
229
- {
230
- "epoch": 0.33701948393891523,
231
- "grad_norm": 0.33922290802001953,
232
- "learning_rate": 0.0004924647159287175,
233
- "loss": 3.5011825561523438,
234
- "step": 160
235
- },
236
- {
237
- "epoch": 0.34755134281200634,
238
- "grad_norm": 0.45363396406173706,
239
- "learning_rate": 0.0004917929500184307,
240
- "loss": 2.768464469909668,
241
- "step": 165
242
- },
243
- {
244
- "epoch": 0.35808320168509744,
245
- "grad_norm": 0.29426634311676025,
246
- "learning_rate": 0.0004910930033168714,
247
- "loss": 3.0745222091674806,
248
- "step": 170
249
- },
250
- {
251
- "epoch": 0.36861506055818855,
252
- "grad_norm": 0.48457714915275574,
253
- "learning_rate": 0.0004903649574023151,
254
- "loss": 3.1395895004272463,
255
- "step": 175
256
- },
257
- {
258
- "epoch": 0.3791469194312796,
259
- "grad_norm": 0.28997525572776794,
260
- "learning_rate": 0.0004896088971279799,
261
- "loss": 2.9532394409179688,
262
- "step": 180
263
- },
264
- {
265
- "epoch": 0.3896787783043707,
266
- "grad_norm": 0.3158065378665924,
267
- "learning_rate": 0.0004888249106121375,
268
- "loss": 3.242550277709961,
269
- "step": 185
270
- },
271
- {
272
- "epoch": 0.4002106371774618,
273
- "grad_norm": 0.25733378529548645,
274
- "learning_rate": 0.00048801308922784194,
275
- "loss": 2.863876533508301,
276
- "step": 190
277
- },
278
- {
279
- "epoch": 0.4107424960505529,
280
- "grad_norm": 0.39928656816482544,
281
- "learning_rate": 0.00048717352759228115,
282
- "loss": 2.9123611450195312,
283
- "step": 195
284
- },
285
- {
286
- "epoch": 0.421274354923644,
287
- "grad_norm": 0.3962703049182892,
288
- "learning_rate": 0.00048630632355574924,
289
- "loss": 3.159450149536133,
290
- "step": 200
291
- },
292
- {
293
- "epoch": 0.4318062137967351,
294
- "grad_norm": 1.542340874671936,
295
- "learning_rate": 0.0004854115781902414,
296
- "loss": 2.832276725769043,
297
- "step": 205
298
- },
299
- {
300
- "epoch": 0.4423380726698262,
301
- "grad_norm": 0.36583542823791504,
302
- "learning_rate": 0.00048448939577767485,
303
- "loss": 2.690146064758301,
304
- "step": 210
305
- },
306
- {
307
- "epoch": 0.4528699315429173,
308
- "grad_norm": 0.3314652740955353,
309
- "learning_rate": 0.0004835398837977346,
310
- "loss": 2.8558319091796873,
311
- "step": 215
312
- },
313
- {
314
- "epoch": 0.46340179041600843,
315
- "grad_norm": 0.30962228775024414,
316
- "learning_rate": 0.0004825631529153466,
317
- "loss": 2.9323553085327148,
318
- "step": 220
319
- },
320
- {
321
- "epoch": 0.47393364928909953,
322
- "grad_norm": 1.0505726337432861,
323
- "learning_rate": 0.0004815593169677799,
324
- "loss": 2.648083305358887,
325
- "step": 225
326
- },
327
- {
328
- "epoch": 0.48446550816219064,
329
- "grad_norm": 0.4935843050479889,
330
- "learning_rate": 0.00048052849295137924,
331
- "loss": 2.8767162322998048,
332
- "step": 230
333
- },
334
- {
335
- "epoch": 0.49499736703528174,
336
- "grad_norm": 0.3319757580757141,
337
- "learning_rate": 0.00047947080100792884,
338
- "loss": 3.111905097961426,
339
- "step": 235
340
- },
341
- {
342
- "epoch": 0.5055292259083728,
343
- "grad_norm": 1.3790903091430664,
344
- "learning_rate": 0.0004783863644106502,
345
- "loss": 3.082983207702637,
346
- "step": 240
347
- },
348
- {
349
- "epoch": 0.516061084781464,
350
- "grad_norm": 0.2825748026371002,
351
- "learning_rate": 0.00047727530954983475,
352
- "loss": 2.5215627670288088,
353
- "step": 245
354
- },
355
- {
356
- "epoch": 0.526592943654555,
357
- "grad_norm": 0.7788515090942383,
358
- "learning_rate": 0.00047613776591811296,
359
- "loss": 3.078541564941406,
360
- "step": 250
361
- },
362
- {
363
- "epoch": 0.5371248025276462,
364
- "grad_norm": 0.2866535186767578,
365
- "learning_rate": 0.0004749738660953621,
366
- "loss": 2.795052909851074,
367
- "step": 255
368
- },
369
- {
370
- "epoch": 0.5476566614007372,
371
- "grad_norm": 0.35526394844055176,
372
- "learning_rate": 0.00047378374573325415,
373
- "loss": 2.6752908706665037,
374
- "step": 260
375
- },
376
- {
377
- "epoch": 0.5581885202738284,
378
- "grad_norm": 0.38038304448127747,
379
- "learning_rate": 0.00047256754353944605,
380
- "loss": 2.8107267379760743,
381
- "step": 265
382
- },
383
- {
384
- "epoch": 0.5687203791469194,
385
- "grad_norm": 0.3206808269023895,
386
- "learning_rate": 0.00047132540126141275,
387
- "loss": 2.705642509460449,
388
- "step": 270
389
- },
390
- {
391
- "epoch": 0.5792522380200106,
392
- "grad_norm": 0.2499801069498062,
393
- "learning_rate": 0.0004700574636699273,
394
- "loss": 2.475233459472656,
395
- "step": 275
396
- },
397
- {
398
- "epoch": 0.5897840968931016,
399
- "grad_norm": 0.26146742701530457,
400
- "learning_rate": 0.0004687638785421875,
401
- "loss": 2.7663032531738283,
402
- "step": 280
403
- },
404
- {
405
- "epoch": 0.6003159557661928,
406
- "grad_norm": 0.3592541515827179,
407
- "learning_rate": 0.00046744479664459276,
408
- "loss": 2.623735046386719,
409
- "step": 285
410
- },
411
- {
412
- "epoch": 0.6108478146392838,
413
- "grad_norm": 0.31415146589279175,
414
- "learning_rate": 0.00046610037171517237,
415
- "loss": 2.87611083984375,
416
- "step": 290
417
- },
418
- {
419
- "epoch": 0.6213796735123749,
420
- "grad_norm": 0.2771868109703064,
421
- "learning_rate": 0.00046473076044566743,
422
- "loss": 2.7714420318603517,
423
- "step": 295
424
- },
425
- {
426
- "epoch": 0.631911532385466,
427
- "grad_norm": 0.4841095209121704,
428
- "learning_rate": 0.0004633361224632685,
429
- "loss": 2.344076728820801,
430
- "step": 300
431
- },
432
- {
433
- "epoch": 0.6424433912585571,
434
- "grad_norm": 0.3907207250595093,
435
- "learning_rate": 0.00046191662031201116,
436
- "loss": 2.6539451599121096,
437
- "step": 305
438
- },
439
- {
440
- "epoch": 0.6529752501316483,
441
- "grad_norm": 0.25700584053993225,
442
- "learning_rate": 0.00046047241943383176,
443
- "loss": 2.7396242141723635,
444
- "step": 310
445
- },
446
- {
447
- "epoch": 0.6635071090047393,
448
- "grad_norm": 0.30718255043029785,
449
- "learning_rate": 0.00045900368814928504,
450
- "loss": 2.8544797897338867,
451
- "step": 315
452
- },
453
- {
454
- "epoch": 0.6740389678778305,
455
- "grad_norm": 0.30769050121307373,
456
- "learning_rate": 0.00045751059763792694,
457
- "loss": 2.611779975891113,
458
- "step": 320
459
- },
460
- {
461
- "epoch": 0.6845708267509215,
462
- "grad_norm": 0.24997501075267792,
463
- "learning_rate": 0.00045599332191836314,
464
- "loss": 2.708077239990234,
465
- "step": 325
466
- }
467
- ],
468
- "logging_steps": 5,
469
- "max_steps": 1500,
470
- "num_input_tokens_seen": 0,
471
- "num_train_epochs": 4,
472
- "save_steps": 25,
473
- "stateful_callbacks": {
474
- "TrainerControl": {
475
- "args": {
476
- "should_epoch_stop": false,
477
- "should_evaluate": false,
478
- "should_log": false,
479
- "should_save": true,
480
- "should_training_stop": false
481
- },
482
- "attributes": {}
483
- }
484
- },
485
- "total_flos": 6.564817736409073e+17,
486
- "train_batch_size": 2,
487
- "trial_name": null,
488
- "trial_params": null
489
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a644e82ab43b487810df128783a041ad14cadbdb92057386bef746e72976478
3
+ size 12792
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6cb092f02e7015f02eb90df660f71bcf38fa540b6f30d3bb40afc2dacc7c95e
3
+ size 5201