Model save
Browse files- README.md +3 -18
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- all_results.json +5 -20
- runs/Feb08_14-59-32_uclaml04.cs.ucla.edu/events.out.tfevents.1707433228.uclaml04.cs.ucla.edu.2385848.0 +3 -0
- runs/Feb08_15-01-43_uclaml04.cs.ucla.edu/events.out.tfevents.1707433358.uclaml04.cs.ucla.edu.2386554.0 +3 -0
- runs/Feb08_15-09-49_uclaml04.cs.ucla.edu/events.out.tfevents.1707433845.uclaml04.cs.ucla.edu.2387930.0 +3 -0
- runs/Feb08_15-34-19_uclaml04.cs.ucla.edu/events.out.tfevents.1707435315.uclaml04.cs.ucla.edu.2392295.0 +3 -0
- train_results.json +5 -5
- trainer_state.json +15 -1557
- training_args.bin +2 -2
README.md
CHANGED
@@ -14,18 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# zephyr-ds
|
15 |
|
16 |
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
|
17 |
-
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.1909
|
19 |
-
- Rewards/chosen: -3.7579
|
20 |
-
- Rewards/rejected: -6.7356
|
21 |
-
- Rewards/accuracies: 0.6940
|
22 |
-
- Rewards/margins: 2.9777
|
23 |
-
- Logps/rejected: -329.6432
|
24 |
-
- Logps/chosen: -319.5546
|
25 |
-
- Logits/rejected: -2.7931
|
26 |
-
- Logits/chosen: -2.8199
|
27 |
-
- Use Label: 12554.0557
|
28 |
-
- Pred Label: 19507.9434
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -49,10 +37,10 @@ The following hyperparameters were used during training:
|
|
49 |
- eval_batch_size: 4
|
50 |
- seed: 42
|
51 |
- distributed_type: multi-GPU
|
52 |
-
- num_devices:
|
53 |
-
- gradient_accumulation_steps:
|
54 |
- total_train_batch_size: 64
|
55 |
-
- total_eval_batch_size:
|
56 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
- lr_scheduler_type: linear
|
58 |
- lr_scheduler_warmup_ratio: 0.1
|
@@ -60,9 +48,6 @@ The following hyperparameters were used during training:
|
|
60 |
|
61 |
### Training results
|
62 |
|
63 |
-
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Use Label | Pred Label |
|
64 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:----------:|:----------:|
|
65 |
-
| 0.1523 | 1.0 | 955 | 0.1909 | -3.7579 | -6.7356 | 0.6940 | 2.9777 | -329.6432 | -319.5546 | -2.7931 | -2.8199 | 12338.0557 | 18723.9434 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
|
|
14 |
# zephyr-ds
|
15 |
|
16 |
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the None dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
37 |
- eval_batch_size: 4
|
38 |
- seed: 42
|
39 |
- distributed_type: multi-GPU
|
40 |
+
- num_devices: 4
|
41 |
+
- gradient_accumulation_steps: 4
|
42 |
- total_train_batch_size: 64
|
43 |
+
- total_eval_batch_size: 16
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
48 |
|
49 |
### Training results
|
50 |
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -16,10 +16,10 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"o_proj",
|
20 |
"k_proj",
|
21 |
-
"
|
22 |
-
"q_proj"
|
|
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
25 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"k_proj",
|
20 |
+
"o_proj",
|
21 |
+
"q_proj",
|
22 |
+
"v_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
25 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 218138576
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c4851d0fda021876b9eb5ecbd6ec0d108d643bb4b81a517a68af72134d8b407
|
3 |
size 218138576
|
all_results.json
CHANGED
@@ -1,23 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"eval_pred_label": 19507.943359375,
|
9 |
-
"eval_rewards/accuracies": 0.6940000057220459,
|
10 |
-
"eval_rewards/chosen": -3.757920265197754,
|
11 |
-
"eval_rewards/margins": 2.9776601791381836,
|
12 |
-
"eval_rewards/rejected": -6.735579967498779,
|
13 |
-
"eval_runtime": 855.9781,
|
14 |
-
"eval_samples": 2000,
|
15 |
-
"eval_samples_per_second": 2.337,
|
16 |
-
"eval_steps_per_second": 0.292,
|
17 |
-
"eval_use_label": 12554.0556640625,
|
18 |
-
"train_loss": 0.3070014505486214,
|
19 |
-
"train_runtime": 47653.0179,
|
20 |
-
"train_samples": 61135,
|
21 |
-
"train_samples_per_second": 1.283,
|
22 |
-
"train_steps_per_second": 0.02
|
23 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.6931471824645996,
|
4 |
+
"train_runtime": 27.1859,
|
5 |
+
"train_samples": 61,
|
6 |
+
"train_samples_per_second": 2.244,
|
7 |
+
"train_steps_per_second": 0.037
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
}
|
runs/Feb08_14-59-32_uclaml04.cs.ucla.edu/events.out.tfevents.1707433228.uclaml04.cs.ucla.edu.2385848.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa54768cfc2f83049fb86b75de8c756bcb27aab3caaea706223643d1c02f9012
|
3 |
+
size 4347
|
runs/Feb08_15-01-43_uclaml04.cs.ucla.edu/events.out.tfevents.1707433358.uclaml04.cs.ucla.edu.2386554.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad7407776a324966662a5f2d4339fbd7528167f3ec857759d5d6c24ad8b64b80
|
3 |
+
size 5361
|
runs/Feb08_15-09-49_uclaml04.cs.ucla.edu/events.out.tfevents.1707433845.uclaml04.cs.ucla.edu.2387930.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d158d8e5701738b059dcc0c207f95d0252be70aa30bbb4173b970950eebbb59
|
3 |
+
size 5361
|
runs/Feb08_15-34-19_uclaml04.cs.ucla.edu/events.out.tfevents.1707435315.uclaml04.cs.ucla.edu.2392295.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a815b5325316e61e68940e9a8e8bfd421c1ed2a17527dcf13597710f5f5b8e10
|
3 |
+
size 5202
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.6931471824645996,
|
4 |
+
"train_runtime": 27.1859,
|
5 |
+
"train_samples": 61,
|
6 |
+
"train_samples_per_second": 2.244,
|
7 |
+
"train_steps_per_second": 0.037
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,1581 +1,39 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0
|
5 |
-
"eval_steps":
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch":
|
13 |
-
"learning_rate":
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"logps/chosen": -314.8815612792969,
|
17 |
-
"logps/rejected": -239.785888671875,
|
18 |
"loss": 0.6931,
|
19 |
-
"pred_label": 0.0,
|
20 |
"rewards/accuracies": 0.0,
|
21 |
"rewards/chosen": 0.0,
|
22 |
"rewards/margins": 0.0,
|
23 |
"rewards/rejected": 0.0,
|
24 |
-
"step": 1
|
25 |
-
"use_label": 18.0
|
26 |
-
},
|
27 |
-
{
|
28 |
-
"epoch": 0.01,
|
29 |
-
"learning_rate": 1.0416666666666667e-06,
|
30 |
-
"logits/chosen": -2.871338129043579,
|
31 |
-
"logits/rejected": -2.8671977519989014,
|
32 |
-
"logps/chosen": -304.6894226074219,
|
33 |
-
"logps/rejected": -284.7349853515625,
|
34 |
-
"loss": 0.6939,
|
35 |
-
"pred_label": 0.0,
|
36 |
-
"rewards/accuracies": 0.4131944477558136,
|
37 |
-
"rewards/chosen": 0.0006341927801258862,
|
38 |
-
"rewards/margins": -0.0011922286357730627,
|
39 |
-
"rewards/rejected": 0.0018264217069372535,
|
40 |
-
"step": 10,
|
41 |
-
"use_label": 178.0
|
42 |
-
},
|
43 |
-
{
|
44 |
-
"epoch": 0.02,
|
45 |
-
"learning_rate": 2.0833333333333334e-06,
|
46 |
-
"logits/chosen": -2.761018991470337,
|
47 |
-
"logits/rejected": -2.7763421535491943,
|
48 |
-
"logps/chosen": -255.852783203125,
|
49 |
-
"logps/rejected": -260.04364013671875,
|
50 |
-
"loss": 0.6902,
|
51 |
-
"pred_label": 0.0,
|
52 |
-
"rewards/accuracies": 0.5531250238418579,
|
53 |
-
"rewards/chosen": 0.0032608681358397007,
|
54 |
-
"rewards/margins": 0.006093679927289486,
|
55 |
-
"rewards/rejected": -0.002832812489941716,
|
56 |
-
"step": 20,
|
57 |
-
"use_label": 482.0
|
58 |
-
},
|
59 |
-
{
|
60 |
-
"epoch": 0.03,
|
61 |
-
"learning_rate": 3.125e-06,
|
62 |
-
"logits/chosen": -2.85542631149292,
|
63 |
-
"logits/rejected": -2.8387763500213623,
|
64 |
-
"logps/chosen": -274.9126892089844,
|
65 |
-
"logps/rejected": -252.97470092773438,
|
66 |
-
"loss": 0.6909,
|
67 |
-
"pred_label": 0.0,
|
68 |
-
"rewards/accuracies": 0.565625011920929,
|
69 |
-
"rewards/chosen": 0.0062743439339101315,
|
70 |
-
"rewards/margins": 0.007127248682081699,
|
71 |
-
"rewards/rejected": -0.0008529046317562461,
|
72 |
-
"step": 30,
|
73 |
-
"use_label": 802.0
|
74 |
-
},
|
75 |
-
{
|
76 |
-
"epoch": 0.04,
|
77 |
-
"learning_rate": 4.166666666666667e-06,
|
78 |
-
"logits/chosen": -2.829822301864624,
|
79 |
-
"logits/rejected": -2.8364169597625732,
|
80 |
-
"logps/chosen": -279.52288818359375,
|
81 |
-
"logps/rejected": -273.93243408203125,
|
82 |
-
"loss": 0.6846,
|
83 |
-
"pred_label": 0.0,
|
84 |
-
"rewards/accuracies": 0.5687500238418579,
|
85 |
-
"rewards/chosen": 0.0057884035632014275,
|
86 |
-
"rewards/margins": 0.016727477312088013,
|
87 |
-
"rewards/rejected": -0.010939070954918861,
|
88 |
-
"step": 40,
|
89 |
-
"use_label": 1122.0
|
90 |
-
},
|
91 |
-
{
|
92 |
-
"epoch": 0.05,
|
93 |
-
"learning_rate": 5.208333333333334e-06,
|
94 |
-
"logits/chosen": -2.8475687503814697,
|
95 |
-
"logits/rejected": -2.8291072845458984,
|
96 |
-
"logps/chosen": -266.10870361328125,
|
97 |
-
"logps/rejected": -257.93243408203125,
|
98 |
-
"loss": 0.6748,
|
99 |
-
"pred_label": 0.0,
|
100 |
-
"rewards/accuracies": 0.5874999761581421,
|
101 |
-
"rewards/chosen": 0.009051208384335041,
|
102 |
-
"rewards/margins": 0.03577073663473129,
|
103 |
-
"rewards/rejected": -0.026719529181718826,
|
104 |
-
"step": 50,
|
105 |
-
"use_label": 1442.0
|
106 |
-
},
|
107 |
-
{
|
108 |
-
"epoch": 0.06,
|
109 |
-
"learning_rate": 6.25e-06,
|
110 |
-
"logits/chosen": -2.8435542583465576,
|
111 |
-
"logits/rejected": -2.857710838317871,
|
112 |
-
"logps/chosen": -308.6976623535156,
|
113 |
-
"logps/rejected": -283.2618103027344,
|
114 |
-
"loss": 0.6705,
|
115 |
-
"pred_label": 0.0,
|
116 |
-
"rewards/accuracies": 0.609375,
|
117 |
-
"rewards/chosen": 0.015249615535140038,
|
118 |
-
"rewards/margins": 0.05724747106432915,
|
119 |
-
"rewards/rejected": -0.04199784994125366,
|
120 |
-
"step": 60,
|
121 |
-
"use_label": 1762.0
|
122 |
-
},
|
123 |
-
{
|
124 |
-
"epoch": 0.07,
|
125 |
-
"learning_rate": 7.291666666666667e-06,
|
126 |
-
"logits/chosen": -2.8543457984924316,
|
127 |
-
"logits/rejected": -2.8572847843170166,
|
128 |
-
"logps/chosen": -284.14410400390625,
|
129 |
-
"logps/rejected": -268.72344970703125,
|
130 |
-
"loss": 0.648,
|
131 |
-
"pred_label": 0.0,
|
132 |
-
"rewards/accuracies": 0.6875,
|
133 |
-
"rewards/chosen": 0.023584356531500816,
|
134 |
-
"rewards/margins": 0.11067845672369003,
|
135 |
-
"rewards/rejected": -0.08709411323070526,
|
136 |
-
"step": 70,
|
137 |
-
"use_label": 2082.0
|
138 |
-
},
|
139 |
-
{
|
140 |
-
"epoch": 0.08,
|
141 |
-
"learning_rate": 8.333333333333334e-06,
|
142 |
-
"logits/chosen": -2.8060286045074463,
|
143 |
-
"logits/rejected": -2.802976131439209,
|
144 |
-
"logps/chosen": -310.8707580566406,
|
145 |
-
"logps/rejected": -279.11822509765625,
|
146 |
-
"loss": 0.6203,
|
147 |
-
"pred_label": 1.2999999523162842,
|
148 |
-
"rewards/accuracies": 0.703125,
|
149 |
-
"rewards/chosen": 0.010406842455267906,
|
150 |
-
"rewards/margins": 0.17813482880592346,
|
151 |
-
"rewards/rejected": -0.1677280068397522,
|
152 |
-
"step": 80,
|
153 |
-
"use_label": 2400.699951171875
|
154 |
-
},
|
155 |
-
{
|
156 |
-
"epoch": 0.09,
|
157 |
-
"learning_rate": 9.375000000000001e-06,
|
158 |
-
"logits/chosen": -2.7980992794036865,
|
159 |
-
"logits/rejected": -2.7999019622802734,
|
160 |
-
"logps/chosen": -295.4351806640625,
|
161 |
-
"logps/rejected": -256.0653381347656,
|
162 |
-
"loss": 0.6197,
|
163 |
-
"pred_label": 3.612499952316284,
|
164 |
-
"rewards/accuracies": 0.706250011920929,
|
165 |
-
"rewards/chosen": 0.03518597409129143,
|
166 |
-
"rewards/margins": 0.2245054543018341,
|
167 |
-
"rewards/rejected": -0.1893194615840912,
|
168 |
-
"step": 90,
|
169 |
-
"use_label": 2718.387451171875
|
170 |
-
},
|
171 |
-
{
|
172 |
-
"epoch": 0.1,
|
173 |
-
"learning_rate": 9.953434225844005e-06,
|
174 |
-
"logits/chosen": -2.806431770324707,
|
175 |
-
"logits/rejected": -2.791755437850952,
|
176 |
-
"logps/chosen": -275.9968566894531,
|
177 |
-
"logps/rejected": -271.8335876464844,
|
178 |
-
"loss": 0.6156,
|
179 |
-
"pred_label": 14.262499809265137,
|
180 |
-
"rewards/accuracies": 0.6625000238418579,
|
181 |
-
"rewards/chosen": 0.036512341350317,
|
182 |
-
"rewards/margins": 0.2290469855070114,
|
183 |
-
"rewards/rejected": -0.1925346404314041,
|
184 |
-
"step": 100,
|
185 |
-
"use_label": 3027.737548828125
|
186 |
-
},
|
187 |
-
{
|
188 |
-
"epoch": 0.12,
|
189 |
-
"learning_rate": 9.837019790454017e-06,
|
190 |
-
"logits/chosen": -2.8026273250579834,
|
191 |
-
"logits/rejected": -2.7944607734680176,
|
192 |
-
"logps/chosen": -273.5028076171875,
|
193 |
-
"logps/rejected": -257.3667907714844,
|
194 |
-
"loss": 0.5959,
|
195 |
-
"pred_label": 32.9375,
|
196 |
-
"rewards/accuracies": 0.6937500238418579,
|
197 |
-
"rewards/chosen": 0.0005084859440103173,
|
198 |
-
"rewards/margins": 0.29547563195228577,
|
199 |
-
"rewards/rejected": -0.2949671447277069,
|
200 |
-
"step": 110,
|
201 |
-
"use_label": 3329.0625
|
202 |
-
},
|
203 |
-
{
|
204 |
-
"epoch": 0.13,
|
205 |
-
"learning_rate": 9.72060535506403e-06,
|
206 |
-
"logits/chosen": -2.8184993267059326,
|
207 |
-
"logits/rejected": -2.8210482597351074,
|
208 |
-
"logps/chosen": -295.52386474609375,
|
209 |
-
"logps/rejected": -268.7758483886719,
|
210 |
-
"loss": 0.5615,
|
211 |
-
"pred_label": 68.7125015258789,
|
212 |
-
"rewards/accuracies": 0.671875,
|
213 |
-
"rewards/chosen": 0.014611599035561085,
|
214 |
-
"rewards/margins": 0.31382012367248535,
|
215 |
-
"rewards/rejected": -0.29920852184295654,
|
216 |
-
"step": 120,
|
217 |
-
"use_label": 3613.28759765625
|
218 |
-
},
|
219 |
-
{
|
220 |
-
"epoch": 0.14,
|
221 |
-
"learning_rate": 9.60419091967404e-06,
|
222 |
-
"logits/chosen": -2.841566801071167,
|
223 |
-
"logits/rejected": -2.8285374641418457,
|
224 |
-
"logps/chosen": -295.79296875,
|
225 |
-
"logps/rejected": -278.8650817871094,
|
226 |
-
"loss": 0.5672,
|
227 |
-
"pred_label": 103.5999984741211,
|
228 |
-
"rewards/accuracies": 0.6781250238418579,
|
229 |
-
"rewards/chosen": -0.02395879104733467,
|
230 |
-
"rewards/margins": 0.3047763705253601,
|
231 |
-
"rewards/rejected": -0.3287351727485657,
|
232 |
-
"step": 130,
|
233 |
-
"use_label": 3898.39990234375
|
234 |
-
},
|
235 |
-
{
|
236 |
-
"epoch": 0.15,
|
237 |
-
"learning_rate": 9.487776484284052e-06,
|
238 |
-
"logits/chosen": -2.814074993133545,
|
239 |
-
"logits/rejected": -2.8163723945617676,
|
240 |
-
"logps/chosen": -268.4273376464844,
|
241 |
-
"logps/rejected": -256.7865905761719,
|
242 |
-
"loss": 0.5278,
|
243 |
-
"pred_label": 150.2375030517578,
|
244 |
-
"rewards/accuracies": 0.7093750238418579,
|
245 |
-
"rewards/chosen": -0.06842182576656342,
|
246 |
-
"rewards/margins": 0.4312126040458679,
|
247 |
-
"rewards/rejected": -0.49963444471359253,
|
248 |
-
"step": 140,
|
249 |
-
"use_label": 4171.7626953125
|
250 |
-
},
|
251 |
-
{
|
252 |
-
"epoch": 0.16,
|
253 |
-
"learning_rate": 9.371362048894065e-06,
|
254 |
-
"logits/chosen": -2.8159050941467285,
|
255 |
-
"logits/rejected": -2.8136250972747803,
|
256 |
-
"logps/chosen": -302.8164978027344,
|
257 |
-
"logps/rejected": -282.1024475097656,
|
258 |
-
"loss": 0.512,
|
259 |
-
"pred_label": 220.6125030517578,
|
260 |
-
"rewards/accuracies": 0.6499999761581421,
|
261 |
-
"rewards/chosen": -0.09125231206417084,
|
262 |
-
"rewards/margins": 0.46096962690353394,
|
263 |
-
"rewards/rejected": -0.5522218942642212,
|
264 |
-
"step": 150,
|
265 |
-
"use_label": 4421.3876953125
|
266 |
-
},
|
267 |
-
{
|
268 |
-
"epoch": 0.17,
|
269 |
-
"learning_rate": 9.254947613504075e-06,
|
270 |
-
"logits/chosen": -2.824867010116577,
|
271 |
-
"logits/rejected": -2.7856192588806152,
|
272 |
-
"logps/chosen": -289.77410888671875,
|
273 |
-
"logps/rejected": -281.7305603027344,
|
274 |
-
"loss": 0.4774,
|
275 |
-
"pred_label": 313.2124938964844,
|
276 |
-
"rewards/accuracies": 0.7281249761581421,
|
277 |
-
"rewards/chosen": 0.016176635399460793,
|
278 |
-
"rewards/margins": 0.6861985325813293,
|
279 |
-
"rewards/rejected": -0.6700219511985779,
|
280 |
-
"step": 160,
|
281 |
-
"use_label": 4648.78759765625
|
282 |
-
},
|
283 |
-
{
|
284 |
-
"epoch": 0.18,
|
285 |
-
"learning_rate": 9.138533178114087e-06,
|
286 |
-
"logits/chosen": -2.834872007369995,
|
287 |
-
"logits/rejected": -2.8196887969970703,
|
288 |
-
"logps/chosen": -291.0771179199219,
|
289 |
-
"logps/rejected": -259.09747314453125,
|
290 |
-
"loss": 0.4858,
|
291 |
-
"pred_label": 410.9375,
|
292 |
-
"rewards/accuracies": 0.684374988079071,
|
293 |
-
"rewards/chosen": -0.12445585429668427,
|
294 |
-
"rewards/margins": 0.6846336126327515,
|
295 |
-
"rewards/rejected": -0.8090893626213074,
|
296 |
-
"step": 170,
|
297 |
-
"use_label": 4871.0625
|
298 |
-
},
|
299 |
-
{
|
300 |
-
"epoch": 0.19,
|
301 |
-
"learning_rate": 9.022118742724098e-06,
|
302 |
-
"logits/chosen": -2.812523126602173,
|
303 |
-
"logits/rejected": -2.798945188522339,
|
304 |
-
"logps/chosen": -249.18258666992188,
|
305 |
-
"logps/rejected": -272.2208557128906,
|
306 |
-
"loss": 0.4293,
|
307 |
-
"pred_label": 534.9000244140625,
|
308 |
-
"rewards/accuracies": 0.699999988079071,
|
309 |
-
"rewards/chosen": -0.22158575057983398,
|
310 |
-
"rewards/margins": 0.7619065046310425,
|
311 |
-
"rewards/rejected": -0.9834922552108765,
|
312 |
-
"step": 180,
|
313 |
-
"use_label": 5067.10009765625
|
314 |
-
},
|
315 |
-
{
|
316 |
-
"epoch": 0.2,
|
317 |
-
"learning_rate": 8.90570430733411e-06,
|
318 |
-
"logits/chosen": -2.852125883102417,
|
319 |
-
"logits/rejected": -2.8234543800354004,
|
320 |
-
"logps/chosen": -306.91717529296875,
|
321 |
-
"logps/rejected": -280.7167663574219,
|
322 |
-
"loss": 0.4155,
|
323 |
-
"pred_label": 671.125,
|
324 |
-
"rewards/accuracies": 0.737500011920929,
|
325 |
-
"rewards/chosen": -0.15123331546783447,
|
326 |
-
"rewards/margins": 0.8876510858535767,
|
327 |
-
"rewards/rejected": -1.0388844013214111,
|
328 |
-
"step": 190,
|
329 |
-
"use_label": 5250.875
|
330 |
-
},
|
331 |
-
{
|
332 |
-
"epoch": 0.21,
|
333 |
-
"learning_rate": 8.789289871944122e-06,
|
334 |
-
"logits/chosen": -2.8436083793640137,
|
335 |
-
"logits/rejected": -2.84915828704834,
|
336 |
-
"logps/chosen": -272.04266357421875,
|
337 |
-
"logps/rejected": -273.80450439453125,
|
338 |
-
"loss": 0.4063,
|
339 |
-
"pred_label": 820.5999755859375,
|
340 |
-
"rewards/accuracies": 0.721875011920929,
|
341 |
-
"rewards/chosen": -0.2906159460544586,
|
342 |
-
"rewards/margins": 0.9353755712509155,
|
343 |
-
"rewards/rejected": -1.2259914875030518,
|
344 |
-
"step": 200,
|
345 |
-
"use_label": 5421.39990234375
|
346 |
-
},
|
347 |
-
{
|
348 |
-
"epoch": 0.22,
|
349 |
-
"learning_rate": 8.672875436554133e-06,
|
350 |
-
"logits/chosen": -2.7995848655700684,
|
351 |
-
"logits/rejected": -2.805274724960327,
|
352 |
-
"logps/chosen": -287.6289978027344,
|
353 |
-
"logps/rejected": -278.2756652832031,
|
354 |
-
"loss": 0.381,
|
355 |
-
"pred_label": 977.75,
|
356 |
-
"rewards/accuracies": 0.6937500238418579,
|
357 |
-
"rewards/chosen": -0.4142700135707855,
|
358 |
-
"rewards/margins": 0.9491223096847534,
|
359 |
-
"rewards/rejected": -1.3633924722671509,
|
360 |
-
"step": 210,
|
361 |
-
"use_label": 5584.25
|
362 |
-
},
|
363 |
-
{
|
364 |
-
"epoch": 0.23,
|
365 |
-
"learning_rate": 8.556461001164145e-06,
|
366 |
-
"logits/chosen": -2.8255257606506348,
|
367 |
-
"logits/rejected": -2.829308271408081,
|
368 |
-
"logps/chosen": -284.17547607421875,
|
369 |
-
"logps/rejected": -283.9212951660156,
|
370 |
-
"loss": 0.3555,
|
371 |
-
"pred_label": 1152.0999755859375,
|
372 |
-
"rewards/accuracies": 0.699999988079071,
|
373 |
-
"rewards/chosen": -0.5653145909309387,
|
374 |
-
"rewards/margins": 0.9969175457954407,
|
375 |
-
"rewards/rejected": -1.5622321367263794,
|
376 |
-
"step": 220,
|
377 |
-
"use_label": 5729.89990234375
|
378 |
-
},
|
379 |
-
{
|
380 |
-
"epoch": 0.24,
|
381 |
-
"learning_rate": 8.440046565774158e-06,
|
382 |
-
"logits/chosen": -2.8168904781341553,
|
383 |
-
"logits/rejected": -2.8215222358703613,
|
384 |
-
"logps/chosen": -316.2763977050781,
|
385 |
-
"logps/rejected": -286.81451416015625,
|
386 |
-
"loss": 0.3603,
|
387 |
-
"pred_label": 1315.9000244140625,
|
388 |
-
"rewards/accuracies": 0.6781250238418579,
|
389 |
-
"rewards/chosen": -0.6668749451637268,
|
390 |
-
"rewards/margins": 1.111903429031372,
|
391 |
-
"rewards/rejected": -1.778778314590454,
|
392 |
-
"step": 230,
|
393 |
-
"use_label": 5886.10009765625
|
394 |
-
},
|
395 |
-
{
|
396 |
-
"epoch": 0.25,
|
397 |
-
"learning_rate": 8.323632130384168e-06,
|
398 |
-
"logits/chosen": -2.781104803085327,
|
399 |
-
"logits/rejected": -2.7607803344726562,
|
400 |
-
"logps/chosen": -306.5365295410156,
|
401 |
-
"logps/rejected": -278.3562927246094,
|
402 |
-
"loss": 0.3714,
|
403 |
-
"pred_label": 1495.112548828125,
|
404 |
-
"rewards/accuracies": 0.703125,
|
405 |
-
"rewards/chosen": -0.6257501244544983,
|
406 |
-
"rewards/margins": 1.2071430683135986,
|
407 |
-
"rewards/rejected": -1.8328930139541626,
|
408 |
-
"step": 240,
|
409 |
-
"use_label": 6026.8876953125
|
410 |
-
},
|
411 |
-
{
|
412 |
-
"epoch": 0.26,
|
413 |
-
"learning_rate": 8.20721769499418e-06,
|
414 |
-
"logits/chosen": -2.78596830368042,
|
415 |
-
"logits/rejected": -2.7599189281463623,
|
416 |
-
"logps/chosen": -307.82861328125,
|
417 |
-
"logps/rejected": -302.6281433105469,
|
418 |
-
"loss": 0.3539,
|
419 |
-
"pred_label": 1677.699951171875,
|
420 |
-
"rewards/accuracies": 0.715624988079071,
|
421 |
-
"rewards/chosen": -0.6732528805732727,
|
422 |
-
"rewards/margins": 1.3034615516662598,
|
423 |
-
"rewards/rejected": -1.9767143726348877,
|
424 |
-
"step": 250,
|
425 |
-
"use_label": 6164.2998046875
|
426 |
-
},
|
427 |
-
{
|
428 |
-
"epoch": 0.27,
|
429 |
-
"learning_rate": 8.090803259604193e-06,
|
430 |
-
"logits/chosen": -2.815549373626709,
|
431 |
-
"logits/rejected": -2.7940564155578613,
|
432 |
-
"logps/chosen": -286.57562255859375,
|
433 |
-
"logps/rejected": -281.46282958984375,
|
434 |
-
"loss": 0.3442,
|
435 |
-
"pred_label": 1858.2874755859375,
|
436 |
-
"rewards/accuracies": 0.671875,
|
437 |
-
"rewards/chosen": -0.8266381025314331,
|
438 |
-
"rewards/margins": 1.193564772605896,
|
439 |
-
"rewards/rejected": -2.020203113555908,
|
440 |
-
"step": 260,
|
441 |
-
"use_label": 6303.71240234375
|
442 |
-
},
|
443 |
-
{
|
444 |
-
"epoch": 0.28,
|
445 |
-
"learning_rate": 7.974388824214203e-06,
|
446 |
-
"logits/chosen": -2.788181781768799,
|
447 |
-
"logits/rejected": -2.777799129486084,
|
448 |
-
"logps/chosen": -282.0382080078125,
|
449 |
-
"logps/rejected": -283.30877685546875,
|
450 |
-
"loss": 0.3539,
|
451 |
-
"pred_label": 2042.800048828125,
|
452 |
-
"rewards/accuracies": 0.7281249761581421,
|
453 |
-
"rewards/chosen": -0.7480707764625549,
|
454 |
-
"rewards/margins": 1.517256736755371,
|
455 |
-
"rewards/rejected": -2.2653274536132812,
|
456 |
-
"step": 270,
|
457 |
-
"use_label": 6439.2001953125
|
458 |
-
},
|
459 |
-
{
|
460 |
-
"epoch": 0.29,
|
461 |
-
"learning_rate": 7.857974388824214e-06,
|
462 |
-
"logits/chosen": -2.876176357269287,
|
463 |
-
"logits/rejected": -2.8538033962249756,
|
464 |
-
"logps/chosen": -301.6811828613281,
|
465 |
-
"logps/rejected": -271.5317077636719,
|
466 |
-
"loss": 0.3156,
|
467 |
-
"pred_label": 2233.362548828125,
|
468 |
-
"rewards/accuracies": 0.7281249761581421,
|
469 |
-
"rewards/chosen": -0.7781136631965637,
|
470 |
-
"rewards/margins": 1.399305820465088,
|
471 |
-
"rewards/rejected": -2.177419424057007,
|
472 |
-
"step": 280,
|
473 |
-
"use_label": 6568.6376953125
|
474 |
-
},
|
475 |
-
{
|
476 |
-
"epoch": 0.3,
|
477 |
-
"learning_rate": 7.741559953434226e-06,
|
478 |
-
"logits/chosen": -2.8401272296905518,
|
479 |
-
"logits/rejected": -2.8481698036193848,
|
480 |
-
"logps/chosen": -298.8213806152344,
|
481 |
-
"logps/rejected": -259.22357177734375,
|
482 |
-
"loss": 0.3398,
|
483 |
-
"pred_label": 2423.125,
|
484 |
-
"rewards/accuracies": 0.684374988079071,
|
485 |
-
"rewards/chosen": -0.863988995552063,
|
486 |
-
"rewards/margins": 1.1683231592178345,
|
487 |
-
"rewards/rejected": -2.0323121547698975,
|
488 |
-
"step": 290,
|
489 |
-
"use_label": 6698.875
|
490 |
-
},
|
491 |
-
{
|
492 |
-
"epoch": 0.31,
|
493 |
-
"learning_rate": 7.625145518044238e-06,
|
494 |
-
"logits/chosen": -2.8349387645721436,
|
495 |
-
"logits/rejected": -2.8150177001953125,
|
496 |
-
"logps/chosen": -300.6407775878906,
|
497 |
-
"logps/rejected": -268.7109375,
|
498 |
-
"loss": 0.3379,
|
499 |
-
"pred_label": 2605.0625,
|
500 |
-
"rewards/accuracies": 0.675000011920929,
|
501 |
-
"rewards/chosen": -0.9172398447990417,
|
502 |
-
"rewards/margins": 1.3402159214019775,
|
503 |
-
"rewards/rejected": -2.257455348968506,
|
504 |
-
"step": 300,
|
505 |
-
"use_label": 6836.9375
|
506 |
-
},
|
507 |
-
{
|
508 |
-
"epoch": 0.32,
|
509 |
-
"learning_rate": 7.50873108265425e-06,
|
510 |
-
"logits/chosen": -2.8097264766693115,
|
511 |
-
"logits/rejected": -2.7792162895202637,
|
512 |
-
"logps/chosen": -285.2196044921875,
|
513 |
-
"logps/rejected": -293.2747497558594,
|
514 |
-
"loss": 0.31,
|
515 |
-
"pred_label": 2792.4375,
|
516 |
-
"rewards/accuracies": 0.721875011920929,
|
517 |
-
"rewards/chosen": -1.0178813934326172,
|
518 |
-
"rewards/margins": 1.7013041973114014,
|
519 |
-
"rewards/rejected": -2.7191855907440186,
|
520 |
-
"step": 310,
|
521 |
-
"use_label": 6969.5625
|
522 |
-
},
|
523 |
-
{
|
524 |
-
"epoch": 0.33,
|
525 |
-
"learning_rate": 7.392316647264262e-06,
|
526 |
-
"logits/chosen": -2.8490498065948486,
|
527 |
-
"logits/rejected": -2.822798728942871,
|
528 |
-
"logps/chosen": -310.70599365234375,
|
529 |
-
"logps/rejected": -291.4599609375,
|
530 |
-
"loss": 0.2964,
|
531 |
-
"pred_label": 2987.39990234375,
|
532 |
-
"rewards/accuracies": 0.7281249761581421,
|
533 |
-
"rewards/chosen": -0.986463189125061,
|
534 |
-
"rewards/margins": 1.725873589515686,
|
535 |
-
"rewards/rejected": -2.712336540222168,
|
536 |
-
"step": 320,
|
537 |
-
"use_label": 7094.60009765625
|
538 |
-
},
|
539 |
-
{
|
540 |
-
"epoch": 0.35,
|
541 |
-
"learning_rate": 7.275902211874272e-06,
|
542 |
-
"logits/chosen": -2.826206684112549,
|
543 |
-
"logits/rejected": -2.804277181625366,
|
544 |
-
"logps/chosen": -272.4220275878906,
|
545 |
-
"logps/rejected": -269.9629821777344,
|
546 |
-
"loss": 0.3185,
|
547 |
-
"pred_label": 3184.550048828125,
|
548 |
-
"rewards/accuracies": 0.6875,
|
549 |
-
"rewards/chosen": -1.161760687828064,
|
550 |
-
"rewards/margins": 1.4867627620697021,
|
551 |
-
"rewards/rejected": -2.6485238075256348,
|
552 |
-
"step": 330,
|
553 |
-
"use_label": 7217.4501953125
|
554 |
-
},
|
555 |
-
{
|
556 |
-
"epoch": 0.36,
|
557 |
-
"learning_rate": 7.1594877764842855e-06,
|
558 |
-
"logits/chosen": -2.8520660400390625,
|
559 |
-
"logits/rejected": -2.832625150680542,
|
560 |
-
"logps/chosen": -307.9129943847656,
|
561 |
-
"logps/rejected": -286.85198974609375,
|
562 |
-
"loss": 0.315,
|
563 |
-
"pred_label": 3378.5625,
|
564 |
-
"rewards/accuracies": 0.6468750238418579,
|
565 |
-
"rewards/chosen": -1.1871546506881714,
|
566 |
-
"rewards/margins": 1.394044280052185,
|
567 |
-
"rewards/rejected": -2.5811991691589355,
|
568 |
-
"step": 340,
|
569 |
-
"use_label": 7343.4375
|
570 |
-
},
|
571 |
-
{
|
572 |
-
"epoch": 0.37,
|
573 |
-
"learning_rate": 7.043073341094296e-06,
|
574 |
-
"logits/chosen": -2.8574576377868652,
|
575 |
-
"logits/rejected": -2.8412604331970215,
|
576 |
-
"logps/chosen": -302.08367919921875,
|
577 |
-
"logps/rejected": -297.78802490234375,
|
578 |
-
"loss": 0.2612,
|
579 |
-
"pred_label": 3585.8125,
|
580 |
-
"rewards/accuracies": 0.6875,
|
581 |
-
"rewards/chosen": -1.353593349456787,
|
582 |
-
"rewards/margins": 1.50961172580719,
|
583 |
-
"rewards/rejected": -2.8632051944732666,
|
584 |
-
"step": 350,
|
585 |
-
"use_label": 7456.1875
|
586 |
-
},
|
587 |
-
{
|
588 |
-
"epoch": 0.38,
|
589 |
-
"learning_rate": 6.9266589057043075e-06,
|
590 |
-
"logits/chosen": -2.9001529216766357,
|
591 |
-
"logits/rejected": -2.8869528770446777,
|
592 |
-
"logps/chosen": -308.5780944824219,
|
593 |
-
"logps/rejected": -304.3133544921875,
|
594 |
-
"loss": 0.2686,
|
595 |
-
"pred_label": 3807.35009765625,
|
596 |
-
"rewards/accuracies": 0.699999988079071,
|
597 |
-
"rewards/chosen": -1.5075533390045166,
|
598 |
-
"rewards/margins": 1.8883936405181885,
|
599 |
-
"rewards/rejected": -3.395947217941284,
|
600 |
-
"step": 360,
|
601 |
-
"use_label": 7554.64990234375
|
602 |
-
},
|
603 |
-
{
|
604 |
-
"epoch": 0.39,
|
605 |
-
"learning_rate": 6.81024447031432e-06,
|
606 |
-
"logits/chosen": -2.8611207008361816,
|
607 |
-
"logits/rejected": -2.8043880462646484,
|
608 |
-
"logps/chosen": -299.6781921386719,
|
609 |
-
"logps/rejected": -303.0309753417969,
|
610 |
-
"loss": 0.2914,
|
611 |
-
"pred_label": 4018.550048828125,
|
612 |
-
"rewards/accuracies": 0.721875011920929,
|
613 |
-
"rewards/chosen": -1.2945538759231567,
|
614 |
-
"rewards/margins": 1.9656009674072266,
|
615 |
-
"rewards/rejected": -3.2601547241210938,
|
616 |
-
"step": 370,
|
617 |
-
"use_label": 7663.4501953125
|
618 |
-
},
|
619 |
-
{
|
620 |
-
"epoch": 0.4,
|
621 |
-
"learning_rate": 6.693830034924331e-06,
|
622 |
-
"logits/chosen": -2.864997148513794,
|
623 |
-
"logits/rejected": -2.836440324783325,
|
624 |
-
"logps/chosen": -297.97845458984375,
|
625 |
-
"logps/rejected": -299.3329772949219,
|
626 |
-
"loss": 0.2302,
|
627 |
-
"pred_label": 4235.9501953125,
|
628 |
-
"rewards/accuracies": 0.746874988079071,
|
629 |
-
"rewards/chosen": -1.5762511491775513,
|
630 |
-
"rewards/margins": 2.1133368015289307,
|
631 |
-
"rewards/rejected": -3.6895878314971924,
|
632 |
-
"step": 380,
|
633 |
-
"use_label": 7766.0498046875
|
634 |
-
},
|
635 |
-
{
|
636 |
-
"epoch": 0.41,
|
637 |
-
"learning_rate": 6.5774155995343425e-06,
|
638 |
-
"logits/chosen": -2.817526340484619,
|
639 |
-
"logits/rejected": -2.8043646812438965,
|
640 |
-
"logps/chosen": -289.15155029296875,
|
641 |
-
"logps/rejected": -285.8031005859375,
|
642 |
-
"loss": 0.2728,
|
643 |
-
"pred_label": 4468.28759765625,
|
644 |
-
"rewards/accuracies": 0.671875,
|
645 |
-
"rewards/chosen": -1.684571623802185,
|
646 |
-
"rewards/margins": 2.025607109069824,
|
647 |
-
"rewards/rejected": -3.7101783752441406,
|
648 |
-
"step": 390,
|
649 |
-
"use_label": 7853.71240234375
|
650 |
-
},
|
651 |
-
{
|
652 |
-
"epoch": 0.42,
|
653 |
-
"learning_rate": 6.461001164144355e-06,
|
654 |
-
"logits/chosen": -2.853013038635254,
|
655 |
-
"logits/rejected": -2.8416590690612793,
|
656 |
-
"logps/chosen": -306.99212646484375,
|
657 |
-
"logps/rejected": -285.7340393066406,
|
658 |
-
"loss": 0.2494,
|
659 |
-
"pred_label": 4690.5751953125,
|
660 |
-
"rewards/accuracies": 0.7124999761581421,
|
661 |
-
"rewards/chosen": -1.374151587486267,
|
662 |
-
"rewards/margins": 2.0254199504852295,
|
663 |
-
"rewards/rejected": -3.399571657180786,
|
664 |
-
"step": 400,
|
665 |
-
"use_label": 7951.4248046875
|
666 |
-
},
|
667 |
-
{
|
668 |
-
"epoch": 0.43,
|
669 |
-
"learning_rate": 6.344586728754366e-06,
|
670 |
-
"logits/chosen": -2.840266227722168,
|
671 |
-
"logits/rejected": -2.8314151763916016,
|
672 |
-
"logps/chosen": -298.0084533691406,
|
673 |
-
"logps/rejected": -289.5139465332031,
|
674 |
-
"loss": 0.2554,
|
675 |
-
"pred_label": 4908.03759765625,
|
676 |
-
"rewards/accuracies": 0.6812499761581421,
|
677 |
-
"rewards/chosen": -1.3851497173309326,
|
678 |
-
"rewards/margins": 1.9138154983520508,
|
679 |
-
"rewards/rejected": -3.2989654541015625,
|
680 |
-
"step": 410,
|
681 |
-
"use_label": 8053.96240234375
|
682 |
-
},
|
683 |
-
{
|
684 |
-
"epoch": 0.44,
|
685 |
-
"learning_rate": 6.228172293364378e-06,
|
686 |
-
"logits/chosen": -2.8333933353424072,
|
687 |
-
"logits/rejected": -2.8114962577819824,
|
688 |
-
"logps/chosen": -281.6308288574219,
|
689 |
-
"logps/rejected": -283.6402282714844,
|
690 |
-
"loss": 0.2814,
|
691 |
-
"pred_label": 5120.16259765625,
|
692 |
-
"rewards/accuracies": 0.6968749761581421,
|
693 |
-
"rewards/chosen": -1.2441003322601318,
|
694 |
-
"rewards/margins": 1.8000373840332031,
|
695 |
-
"rewards/rejected": -3.044137954711914,
|
696 |
-
"step": 420,
|
697 |
-
"use_label": 8161.83740234375
|
698 |
-
},
|
699 |
-
{
|
700 |
-
"epoch": 0.45,
|
701 |
-
"learning_rate": 6.11175785797439e-06,
|
702 |
-
"logits/chosen": -2.8557116985321045,
|
703 |
-
"logits/rejected": -2.82271146774292,
|
704 |
-
"logps/chosen": -305.80322265625,
|
705 |
-
"logps/rejected": -291.4790954589844,
|
706 |
-
"loss": 0.2721,
|
707 |
-
"pred_label": 5342.97509765625,
|
708 |
-
"rewards/accuracies": 0.6468750238418579,
|
709 |
-
"rewards/chosen": -1.548147439956665,
|
710 |
-
"rewards/margins": 1.3705997467041016,
|
711 |
-
"rewards/rejected": -2.9187471866607666,
|
712 |
-
"step": 430,
|
713 |
-
"use_label": 8259.025390625
|
714 |
-
},
|
715 |
-
{
|
716 |
-
"epoch": 0.46,
|
717 |
-
"learning_rate": 5.995343422584401e-06,
|
718 |
-
"logits/chosen": -2.8646130561828613,
|
719 |
-
"logits/rejected": -2.8445792198181152,
|
720 |
-
"logps/chosen": -299.37811279296875,
|
721 |
-
"logps/rejected": -275.6679382324219,
|
722 |
-
"loss": 0.2555,
|
723 |
-
"pred_label": 5555.8876953125,
|
724 |
-
"rewards/accuracies": 0.668749988079071,
|
725 |
-
"rewards/chosen": -1.6375954151153564,
|
726 |
-
"rewards/margins": 1.7932894229888916,
|
727 |
-
"rewards/rejected": -3.430884838104248,
|
728 |
-
"step": 440,
|
729 |
-
"use_label": 8366.1123046875
|
730 |
-
},
|
731 |
-
{
|
732 |
-
"epoch": 0.47,
|
733 |
-
"learning_rate": 5.878928987194412e-06,
|
734 |
-
"logits/chosen": -2.757448434829712,
|
735 |
-
"logits/rejected": -2.7369332313537598,
|
736 |
-
"logps/chosen": -273.22796630859375,
|
737 |
-
"logps/rejected": -287.7809143066406,
|
738 |
-
"loss": 0.2421,
|
739 |
-
"pred_label": 5778.60009765625,
|
740 |
-
"rewards/accuracies": 0.715624988079071,
|
741 |
-
"rewards/chosen": -1.5854363441467285,
|
742 |
-
"rewards/margins": 1.861823320388794,
|
743 |
-
"rewards/rejected": -3.4472599029541016,
|
744 |
-
"step": 450,
|
745 |
-
"use_label": 8463.400390625
|
746 |
-
},
|
747 |
-
{
|
748 |
-
"epoch": 0.48,
|
749 |
-
"learning_rate": 5.762514551804425e-06,
|
750 |
-
"logits/chosen": -2.8731637001037598,
|
751 |
-
"logits/rejected": -2.8510243892669678,
|
752 |
-
"logps/chosen": -322.58294677734375,
|
753 |
-
"logps/rejected": -296.1365966796875,
|
754 |
-
"loss": 0.2765,
|
755 |
-
"pred_label": 5993.14990234375,
|
756 |
-
"rewards/accuracies": 0.6875,
|
757 |
-
"rewards/chosen": -1.682427167892456,
|
758 |
-
"rewards/margins": 1.4240281581878662,
|
759 |
-
"rewards/rejected": -3.1064553260803223,
|
760 |
-
"step": 460,
|
761 |
-
"use_label": 8568.849609375
|
762 |
-
},
|
763 |
-
{
|
764 |
-
"epoch": 0.49,
|
765 |
-
"learning_rate": 5.6461001164144355e-06,
|
766 |
-
"logits/chosen": -2.85316801071167,
|
767 |
-
"logits/rejected": -2.828878164291382,
|
768 |
-
"logps/chosen": -312.8523254394531,
|
769 |
-
"logps/rejected": -301.6842346191406,
|
770 |
-
"loss": 0.2612,
|
771 |
-
"pred_label": 6206.52490234375,
|
772 |
-
"rewards/accuracies": 0.690625011920929,
|
773 |
-
"rewards/chosen": -1.7460191249847412,
|
774 |
-
"rewards/margins": 1.790623426437378,
|
775 |
-
"rewards/rejected": -3.536642551422119,
|
776 |
-
"step": 470,
|
777 |
-
"use_label": 8675.474609375
|
778 |
-
},
|
779 |
-
{
|
780 |
-
"epoch": 0.5,
|
781 |
-
"learning_rate": 5.529685681024447e-06,
|
782 |
-
"logits/chosen": -2.793785810470581,
|
783 |
-
"logits/rejected": -2.7770721912384033,
|
784 |
-
"logps/chosen": -273.039306640625,
|
785 |
-
"logps/rejected": -294.2169189453125,
|
786 |
-
"loss": 0.2638,
|
787 |
-
"pred_label": 6428.9248046875,
|
788 |
-
"rewards/accuracies": 0.612500011920929,
|
789 |
-
"rewards/chosen": -2.0260262489318848,
|
790 |
-
"rewards/margins": 1.4155540466308594,
|
791 |
-
"rewards/rejected": -3.441580295562744,
|
792 |
-
"step": 480,
|
793 |
-
"use_label": 8773.0751953125
|
794 |
-
},
|
795 |
-
{
|
796 |
-
"epoch": 0.51,
|
797 |
-
"learning_rate": 5.413271245634459e-06,
|
798 |
-
"logits/chosen": -2.8139758110046387,
|
799 |
-
"logits/rejected": -2.8046863079071045,
|
800 |
-
"logps/chosen": -302.76043701171875,
|
801 |
-
"logps/rejected": -283.40069580078125,
|
802 |
-
"loss": 0.2434,
|
803 |
-
"pred_label": 6654.64990234375,
|
804 |
-
"rewards/accuracies": 0.703125,
|
805 |
-
"rewards/chosen": -1.7550468444824219,
|
806 |
-
"rewards/margins": 1.9198501110076904,
|
807 |
-
"rewards/rejected": -3.6748969554901123,
|
808 |
-
"step": 490,
|
809 |
-
"use_label": 8867.349609375
|
810 |
-
},
|
811 |
-
{
|
812 |
-
"epoch": 0.52,
|
813 |
-
"learning_rate": 5.2968568102444705e-06,
|
814 |
-
"logits/chosen": -2.846433162689209,
|
815 |
-
"logits/rejected": -2.8172895908355713,
|
816 |
-
"logps/chosen": -307.9965515136719,
|
817 |
-
"logps/rejected": -305.2622375488281,
|
818 |
-
"loss": 0.2286,
|
819 |
-
"pred_label": 6898.72509765625,
|
820 |
-
"rewards/accuracies": 0.6812499761581421,
|
821 |
-
"rewards/chosen": -1.8360557556152344,
|
822 |
-
"rewards/margins": 2.077921152114868,
|
823 |
-
"rewards/rejected": -3.9139761924743652,
|
824 |
-
"step": 500,
|
825 |
-
"use_label": 8943.275390625
|
826 |
-
},
|
827 |
-
{
|
828 |
-
"epoch": 0.53,
|
829 |
-
"learning_rate": 5.180442374854482e-06,
|
830 |
-
"logits/chosen": -2.8676562309265137,
|
831 |
-
"logits/rejected": -2.8552956581115723,
|
832 |
-
"logps/chosen": -297.22064208984375,
|
833 |
-
"logps/rejected": -299.2649841308594,
|
834 |
-
"loss": 0.2153,
|
835 |
-
"pred_label": 7138.83740234375,
|
836 |
-
"rewards/accuracies": 0.703125,
|
837 |
-
"rewards/chosen": -2.125028610229492,
|
838 |
-
"rewards/margins": 2.392963409423828,
|
839 |
-
"rewards/rejected": -4.51799201965332,
|
840 |
-
"step": 510,
|
841 |
-
"use_label": 9023.162109375
|
842 |
-
},
|
843 |
-
{
|
844 |
-
"epoch": 0.54,
|
845 |
-
"learning_rate": 5.064027939464494e-06,
|
846 |
-
"logits/chosen": -2.861607074737549,
|
847 |
-
"logits/rejected": -2.824428081512451,
|
848 |
-
"logps/chosen": -300.9296569824219,
|
849 |
-
"logps/rejected": -300.1321716308594,
|
850 |
-
"loss": 0.2336,
|
851 |
-
"pred_label": 7372.25,
|
852 |
-
"rewards/accuracies": 0.715624988079071,
|
853 |
-
"rewards/chosen": -1.6840749979019165,
|
854 |
-
"rewards/margins": 2.552696466445923,
|
855 |
-
"rewards/rejected": -4.236771583557129,
|
856 |
-
"step": 520,
|
857 |
-
"use_label": 9109.75
|
858 |
-
},
|
859 |
-
{
|
860 |
-
"epoch": 0.55,
|
861 |
-
"learning_rate": 4.947613504074506e-06,
|
862 |
-
"logits/chosen": -2.8984599113464355,
|
863 |
-
"logits/rejected": -2.8596012592315674,
|
864 |
-
"logps/chosen": -308.25140380859375,
|
865 |
-
"logps/rejected": -307.4395446777344,
|
866 |
-
"loss": 0.2249,
|
867 |
-
"pred_label": 7615.60009765625,
|
868 |
-
"rewards/accuracies": 0.721875011920929,
|
869 |
-
"rewards/chosen": -1.700122594833374,
|
870 |
-
"rewards/margins": 2.4561877250671387,
|
871 |
-
"rewards/rejected": -4.156310558319092,
|
872 |
-
"step": 530,
|
873 |
-
"use_label": 9186.400390625
|
874 |
-
},
|
875 |
-
{
|
876 |
-
"epoch": 0.57,
|
877 |
-
"learning_rate": 4.831199068684517e-06,
|
878 |
-
"logits/chosen": -2.8835153579711914,
|
879 |
-
"logits/rejected": -2.8658623695373535,
|
880 |
-
"logps/chosen": -307.30853271484375,
|
881 |
-
"logps/rejected": -305.19061279296875,
|
882 |
-
"loss": 0.231,
|
883 |
-
"pred_label": 7856.7001953125,
|
884 |
-
"rewards/accuracies": 0.7406250238418579,
|
885 |
-
"rewards/chosen": -1.5762898921966553,
|
886 |
-
"rewards/margins": 2.7267935276031494,
|
887 |
-
"rewards/rejected": -4.303083419799805,
|
888 |
-
"step": 540,
|
889 |
-
"use_label": 9265.2998046875
|
890 |
-
},
|
891 |
-
{
|
892 |
-
"epoch": 0.58,
|
893 |
-
"learning_rate": 4.714784633294529e-06,
|
894 |
-
"logits/chosen": -2.853215456008911,
|
895 |
-
"logits/rejected": -2.827068567276001,
|
896 |
-
"logps/chosen": -299.76446533203125,
|
897 |
-
"logps/rejected": -309.46734619140625,
|
898 |
-
"loss": 0.2155,
|
899 |
-
"pred_label": 8086.875,
|
900 |
-
"rewards/accuracies": 0.684374988079071,
|
901 |
-
"rewards/chosen": -1.7928301095962524,
|
902 |
-
"rewards/margins": 2.323638677597046,
|
903 |
-
"rewards/rejected": -4.116468906402588,
|
904 |
-
"step": 550,
|
905 |
-
"use_label": 9355.125
|
906 |
-
},
|
907 |
-
{
|
908 |
-
"epoch": 0.59,
|
909 |
-
"learning_rate": 4.598370197904541e-06,
|
910 |
-
"logits/chosen": -2.834362506866455,
|
911 |
-
"logits/rejected": -2.810864210128784,
|
912 |
-
"logps/chosen": -316.2347717285156,
|
913 |
-
"logps/rejected": -276.0157775878906,
|
914 |
-
"loss": 0.258,
|
915 |
-
"pred_label": 8320.0126953125,
|
916 |
-
"rewards/accuracies": 0.659375011920929,
|
917 |
-
"rewards/chosen": -1.946148157119751,
|
918 |
-
"rewards/margins": 1.932668685913086,
|
919 |
-
"rewards/rejected": -3.878816604614258,
|
920 |
-
"step": 560,
|
921 |
-
"use_label": 9441.9873046875
|
922 |
-
},
|
923 |
-
{
|
924 |
-
"epoch": 0.6,
|
925 |
-
"learning_rate": 4.481955762514552e-06,
|
926 |
-
"logits/chosen": -2.818577766418457,
|
927 |
-
"logits/rejected": -2.800201416015625,
|
928 |
-
"logps/chosen": -287.69390869140625,
|
929 |
-
"logps/rejected": -290.1914367675781,
|
930 |
-
"loss": 0.211,
|
931 |
-
"pred_label": 8550.4873046875,
|
932 |
-
"rewards/accuracies": 0.7250000238418579,
|
933 |
-
"rewards/chosen": -1.9045298099517822,
|
934 |
-
"rewards/margins": 2.01288104057312,
|
935 |
-
"rewards/rejected": -3.9174110889434814,
|
936 |
-
"step": 570,
|
937 |
-
"use_label": 9531.5126953125
|
938 |
-
},
|
939 |
-
{
|
940 |
-
"epoch": 0.61,
|
941 |
-
"learning_rate": 4.365541327124564e-06,
|
942 |
-
"logits/chosen": -2.833016872406006,
|
943 |
-
"logits/rejected": -2.8276636600494385,
|
944 |
-
"logps/chosen": -294.7558288574219,
|
945 |
-
"logps/rejected": -301.39459228515625,
|
946 |
-
"loss": 0.2456,
|
947 |
-
"pred_label": 8784.2001953125,
|
948 |
-
"rewards/accuracies": 0.6937500238418579,
|
949 |
-
"rewards/chosen": -2.0422422885894775,
|
950 |
-
"rewards/margins": 2.122627019882202,
|
951 |
-
"rewards/rejected": -4.164869785308838,
|
952 |
-
"step": 580,
|
953 |
-
"use_label": 9617.7998046875
|
954 |
-
},
|
955 |
-
{
|
956 |
-
"epoch": 0.62,
|
957 |
-
"learning_rate": 4.249126891734576e-06,
|
958 |
-
"logits/chosen": -2.8091092109680176,
|
959 |
-
"logits/rejected": -2.805959939956665,
|
960 |
-
"logps/chosen": -306.3221740722656,
|
961 |
-
"logps/rejected": -315.2014465332031,
|
962 |
-
"loss": 0.245,
|
963 |
-
"pred_label": 9015.087890625,
|
964 |
-
"rewards/accuracies": 0.6812499761581421,
|
965 |
-
"rewards/chosen": -1.8414281606674194,
|
966 |
-
"rewards/margins": 2.2786455154418945,
|
967 |
-
"rewards/rejected": -4.1200737953186035,
|
968 |
-
"step": 590,
|
969 |
-
"use_label": 9706.912109375
|
970 |
-
},
|
971 |
-
{
|
972 |
-
"epoch": 0.63,
|
973 |
-
"learning_rate": 4.132712456344587e-06,
|
974 |
-
"logits/chosen": -2.8337035179138184,
|
975 |
-
"logits/rejected": -2.829528570175171,
|
976 |
-
"logps/chosen": -313.0551452636719,
|
977 |
-
"logps/rejected": -332.26055908203125,
|
978 |
-
"loss": 0.197,
|
979 |
-
"pred_label": 9257.0126953125,
|
980 |
-
"rewards/accuracies": 0.737500011920929,
|
981 |
-
"rewards/chosen": -1.633183240890503,
|
982 |
-
"rewards/margins": 2.7223196029663086,
|
983 |
-
"rewards/rejected": -4.355503082275391,
|
984 |
-
"step": 600,
|
985 |
-
"use_label": 9784.9873046875
|
986 |
-
},
|
987 |
-
{
|
988 |
-
"epoch": 0.64,
|
989 |
-
"learning_rate": 4.0162980209545985e-06,
|
990 |
-
"logits/chosen": -2.84791898727417,
|
991 |
-
"logits/rejected": -2.8361434936523438,
|
992 |
-
"logps/chosen": -317.21636962890625,
|
993 |
-
"logps/rejected": -296.84759521484375,
|
994 |
-
"loss": 0.2117,
|
995 |
-
"pred_label": 9493.875,
|
996 |
-
"rewards/accuracies": 0.6968749761581421,
|
997 |
-
"rewards/chosen": -1.8508695363998413,
|
998 |
-
"rewards/margins": 2.29063081741333,
|
999 |
-
"rewards/rejected": -4.141500949859619,
|
1000 |
-
"step": 610,
|
1001 |
-
"use_label": 9868.125
|
1002 |
-
},
|
1003 |
-
{
|
1004 |
-
"epoch": 0.65,
|
1005 |
-
"learning_rate": 3.899883585564611e-06,
|
1006 |
-
"logits/chosen": -2.854703426361084,
|
1007 |
-
"logits/rejected": -2.7970035076141357,
|
1008 |
-
"logps/chosen": -306.46490478515625,
|
1009 |
-
"logps/rejected": -295.9690856933594,
|
1010 |
-
"loss": 0.2274,
|
1011 |
-
"pred_label": 9722.4501953125,
|
1012 |
-
"rewards/accuracies": 0.7093750238418579,
|
1013 |
-
"rewards/chosen": -2.2507681846618652,
|
1014 |
-
"rewards/margins": 2.2558112144470215,
|
1015 |
-
"rewards/rejected": -4.506579399108887,
|
1016 |
-
"step": 620,
|
1017 |
-
"use_label": 9959.5498046875
|
1018 |
-
},
|
1019 |
-
{
|
1020 |
-
"epoch": 0.66,
|
1021 |
-
"learning_rate": 3.7834691501746217e-06,
|
1022 |
-
"logits/chosen": -2.8078906536102295,
|
1023 |
-
"logits/rejected": -2.794034957885742,
|
1024 |
-
"logps/chosen": -300.4102478027344,
|
1025 |
-
"logps/rejected": -319.0257263183594,
|
1026 |
-
"loss": 0.2013,
|
1027 |
-
"pred_label": 9961.900390625,
|
1028 |
-
"rewards/accuracies": 0.715624988079071,
|
1029 |
-
"rewards/chosen": -2.219250440597534,
|
1030 |
-
"rewards/margins": 2.7064452171325684,
|
1031 |
-
"rewards/rejected": -4.925694942474365,
|
1032 |
-
"step": 630,
|
1033 |
-
"use_label": 10040.099609375
|
1034 |
-
},
|
1035 |
-
{
|
1036 |
-
"epoch": 0.67,
|
1037 |
-
"learning_rate": 3.6670547147846336e-06,
|
1038 |
-
"logits/chosen": -2.818479061126709,
|
1039 |
-
"logits/rejected": -2.7741947174072266,
|
1040 |
-
"logps/chosen": -286.0899353027344,
|
1041 |
-
"logps/rejected": -285.6925048828125,
|
1042 |
-
"loss": 0.2183,
|
1043 |
-
"pred_label": 10201.8125,
|
1044 |
-
"rewards/accuracies": 0.6499999761581421,
|
1045 |
-
"rewards/chosen": -2.2236666679382324,
|
1046 |
-
"rewards/margins": 2.530942440032959,
|
1047 |
-
"rewards/rejected": -4.75460958480835,
|
1048 |
-
"step": 640,
|
1049 |
-
"use_label": 10120.1875
|
1050 |
-
},
|
1051 |
-
{
|
1052 |
-
"epoch": 0.68,
|
1053 |
-
"learning_rate": 3.5506402793946454e-06,
|
1054 |
-
"logits/chosen": -2.786527156829834,
|
1055 |
-
"logits/rejected": -2.7697250843048096,
|
1056 |
-
"logps/chosen": -311.5790100097656,
|
1057 |
-
"logps/rejected": -327.41448974609375,
|
1058 |
-
"loss": 0.1862,
|
1059 |
-
"pred_label": 10438.400390625,
|
1060 |
-
"rewards/accuracies": 0.7437499761581421,
|
1061 |
-
"rewards/chosen": -2.290921688079834,
|
1062 |
-
"rewards/margins": 3.1013052463531494,
|
1063 |
-
"rewards/rejected": -5.392226696014404,
|
1064 |
-
"step": 650,
|
1065 |
-
"use_label": 10203.599609375
|
1066 |
-
},
|
1067 |
-
{
|
1068 |
-
"epoch": 0.69,
|
1069 |
-
"learning_rate": 3.434225844004657e-06,
|
1070 |
-
"logits/chosen": -2.833200693130493,
|
1071 |
-
"logits/rejected": -2.8118557929992676,
|
1072 |
-
"logps/chosen": -307.580322265625,
|
1073 |
-
"logps/rejected": -289.68023681640625,
|
1074 |
-
"loss": 0.2361,
|
1075 |
-
"pred_label": 10677.7626953125,
|
1076 |
-
"rewards/accuracies": 0.65625,
|
1077 |
-
"rewards/chosen": -2.9750688076019287,
|
1078 |
-
"rewards/margins": 1.9074808359146118,
|
1079 |
-
"rewards/rejected": -4.882550239562988,
|
1080 |
-
"step": 660,
|
1081 |
-
"use_label": 10284.2373046875
|
1082 |
-
},
|
1083 |
-
{
|
1084 |
-
"epoch": 0.7,
|
1085 |
-
"learning_rate": 3.3178114086146686e-06,
|
1086 |
-
"logits/chosen": -2.823399066925049,
|
1087 |
-
"logits/rejected": -2.794682025909424,
|
1088 |
-
"logps/chosen": -306.1806640625,
|
1089 |
-
"logps/rejected": -300.6312255859375,
|
1090 |
-
"loss": 0.1964,
|
1091 |
-
"pred_label": 10918.8251953125,
|
1092 |
-
"rewards/accuracies": 0.7406250238418579,
|
1093 |
-
"rewards/chosen": -2.6798641681671143,
|
1094 |
-
"rewards/margins": 2.8597590923309326,
|
1095 |
-
"rewards/rejected": -5.539623737335205,
|
1096 |
-
"step": 670,
|
1097 |
-
"use_label": 10363.1748046875
|
1098 |
-
},
|
1099 |
-
{
|
1100 |
-
"epoch": 0.71,
|
1101 |
-
"learning_rate": 3.20139697322468e-06,
|
1102 |
-
"logits/chosen": -2.8301963806152344,
|
1103 |
-
"logits/rejected": -2.8216447830200195,
|
1104 |
-
"logps/chosen": -326.2012634277344,
|
1105 |
-
"logps/rejected": -316.03192138671875,
|
1106 |
-
"loss": 0.2123,
|
1107 |
-
"pred_label": 11164.5625,
|
1108 |
-
"rewards/accuracies": 0.6625000238418579,
|
1109 |
-
"rewards/chosen": -2.6657440662384033,
|
1110 |
-
"rewards/margins": 2.024155855178833,
|
1111 |
-
"rewards/rejected": -4.689899444580078,
|
1112 |
-
"step": 680,
|
1113 |
-
"use_label": 10437.4375
|
1114 |
-
},
|
1115 |
-
{
|
1116 |
-
"epoch": 0.72,
|
1117 |
-
"learning_rate": 3.0849825378346914e-06,
|
1118 |
-
"logits/chosen": -2.808143138885498,
|
1119 |
-
"logits/rejected": -2.7844669818878174,
|
1120 |
-
"logps/chosen": -309.50946044921875,
|
1121 |
-
"logps/rejected": -288.86865234375,
|
1122 |
-
"loss": 0.1798,
|
1123 |
-
"pred_label": 11412.3876953125,
|
1124 |
-
"rewards/accuracies": 0.737500011920929,
|
1125 |
-
"rewards/chosen": -2.7414073944091797,
|
1126 |
-
"rewards/margins": 2.5902717113494873,
|
1127 |
-
"rewards/rejected": -5.331678867340088,
|
1128 |
-
"step": 690,
|
1129 |
-
"use_label": 10509.6123046875
|
1130 |
-
},
|
1131 |
-
{
|
1132 |
-
"epoch": 0.73,
|
1133 |
-
"learning_rate": 2.9685681024447033e-06,
|
1134 |
-
"logits/chosen": -2.7990927696228027,
|
1135 |
-
"logits/rejected": -2.770561695098877,
|
1136 |
-
"logps/chosen": -296.21697998046875,
|
1137 |
-
"logps/rejected": -300.41229248046875,
|
1138 |
-
"loss": 0.1884,
|
1139 |
-
"pred_label": 11669.099609375,
|
1140 |
-
"rewards/accuracies": 0.703125,
|
1141 |
-
"rewards/chosen": -2.7120413780212402,
|
1142 |
-
"rewards/margins": 2.8404040336608887,
|
1143 |
-
"rewards/rejected": -5.552445411682129,
|
1144 |
-
"step": 700,
|
1145 |
-
"use_label": 10572.900390625
|
1146 |
-
},
|
1147 |
-
{
|
1148 |
-
"epoch": 0.74,
|
1149 |
-
"learning_rate": 2.852153667054715e-06,
|
1150 |
-
"logits/chosen": -2.8590335845947266,
|
1151 |
-
"logits/rejected": -2.842290163040161,
|
1152 |
-
"logps/chosen": -300.3395080566406,
|
1153 |
-
"logps/rejected": -291.9437561035156,
|
1154 |
-
"loss": 0.1848,
|
1155 |
-
"pred_label": 11914.4501953125,
|
1156 |
-
"rewards/accuracies": 0.7093750238418579,
|
1157 |
-
"rewards/chosen": -2.490241527557373,
|
1158 |
-
"rewards/margins": 2.938403606414795,
|
1159 |
-
"rewards/rejected": -5.428645133972168,
|
1160 |
-
"step": 710,
|
1161 |
-
"use_label": 10647.5498046875
|
1162 |
-
},
|
1163 |
-
{
|
1164 |
-
"epoch": 0.75,
|
1165 |
-
"learning_rate": 2.735739231664727e-06,
|
1166 |
-
"logits/chosen": -2.8020033836364746,
|
1167 |
-
"logits/rejected": -2.8077361583709717,
|
1168 |
-
"logps/chosen": -307.3730773925781,
|
1169 |
-
"logps/rejected": -305.9153137207031,
|
1170 |
-
"loss": 0.1691,
|
1171 |
-
"pred_label": 12175.75,
|
1172 |
-
"rewards/accuracies": 0.706250011920929,
|
1173 |
-
"rewards/chosen": -3.191791534423828,
|
1174 |
-
"rewards/margins": 2.743975877761841,
|
1175 |
-
"rewards/rejected": -5.93576717376709,
|
1176 |
-
"step": 720,
|
1177 |
-
"use_label": 10706.25
|
1178 |
-
},
|
1179 |
-
{
|
1180 |
-
"epoch": 0.76,
|
1181 |
-
"learning_rate": 2.6193247962747383e-06,
|
1182 |
-
"logits/chosen": -2.84368896484375,
|
1183 |
-
"logits/rejected": -2.8325092792510986,
|
1184 |
-
"logps/chosen": -319.6998596191406,
|
1185 |
-
"logps/rejected": -299.0663146972656,
|
1186 |
-
"loss": 0.1831,
|
1187 |
-
"pred_label": 12431.7001953125,
|
1188 |
-
"rewards/accuracies": 0.706250011920929,
|
1189 |
-
"rewards/chosen": -2.6903202533721924,
|
1190 |
-
"rewards/margins": 2.7115437984466553,
|
1191 |
-
"rewards/rejected": -5.401864051818848,
|
1192 |
-
"step": 730,
|
1193 |
-
"use_label": 10770.2998046875
|
1194 |
-
},
|
1195 |
-
{
|
1196 |
-
"epoch": 0.77,
|
1197 |
-
"learning_rate": 2.5029103608847497e-06,
|
1198 |
-
"logits/chosen": -2.8156962394714355,
|
1199 |
-
"logits/rejected": -2.816779613494873,
|
1200 |
-
"logps/chosen": -331.8976135253906,
|
1201 |
-
"logps/rejected": -335.2292175292969,
|
1202 |
-
"loss": 0.184,
|
1203 |
-
"pred_label": 12686.3251953125,
|
1204 |
-
"rewards/accuracies": 0.715624988079071,
|
1205 |
-
"rewards/chosen": -3.126286745071411,
|
1206 |
-
"rewards/margins": 3.2427031993865967,
|
1207 |
-
"rewards/rejected": -6.36898946762085,
|
1208 |
-
"step": 740,
|
1209 |
-
"use_label": 10835.6748046875
|
1210 |
-
},
|
1211 |
-
{
|
1212 |
-
"epoch": 0.79,
|
1213 |
-
"learning_rate": 2.3864959254947616e-06,
|
1214 |
-
"logits/chosen": -2.8092589378356934,
|
1215 |
-
"logits/rejected": -2.7743942737579346,
|
1216 |
-
"logps/chosen": -294.40643310546875,
|
1217 |
-
"logps/rejected": -323.6761169433594,
|
1218 |
-
"loss": 0.1726,
|
1219 |
-
"pred_label": 12944.5498046875,
|
1220 |
-
"rewards/accuracies": 0.737500011920929,
|
1221 |
-
"rewards/chosen": -3.147745132446289,
|
1222 |
-
"rewards/margins": 3.201345443725586,
|
1223 |
-
"rewards/rejected": -6.349090576171875,
|
1224 |
-
"step": 750,
|
1225 |
-
"use_label": 10897.4501953125
|
1226 |
-
},
|
1227 |
-
{
|
1228 |
-
"epoch": 0.8,
|
1229 |
-
"learning_rate": 2.2700814901047734e-06,
|
1230 |
-
"logits/chosen": -2.81386399269104,
|
1231 |
-
"logits/rejected": -2.815582752227783,
|
1232 |
-
"logps/chosen": -326.869873046875,
|
1233 |
-
"logps/rejected": -325.6067199707031,
|
1234 |
-
"loss": 0.1704,
|
1235 |
-
"pred_label": 13210.6748046875,
|
1236 |
-
"rewards/accuracies": 0.734375,
|
1237 |
-
"rewards/chosen": -3.039788246154785,
|
1238 |
-
"rewards/margins": 3.261427402496338,
|
1239 |
-
"rewards/rejected": -6.301215171813965,
|
1240 |
-
"step": 760,
|
1241 |
-
"use_label": 10951.3251953125
|
1242 |
-
},
|
1243 |
-
{
|
1244 |
-
"epoch": 0.81,
|
1245 |
-
"learning_rate": 2.153667054714785e-06,
|
1246 |
-
"logits/chosen": -2.886383533477783,
|
1247 |
-
"logits/rejected": -2.861985445022583,
|
1248 |
-
"logps/chosen": -347.4055480957031,
|
1249 |
-
"logps/rejected": -348.0740661621094,
|
1250 |
-
"loss": 0.171,
|
1251 |
-
"pred_label": 13468.4375,
|
1252 |
-
"rewards/accuracies": 0.715624988079071,
|
1253 |
-
"rewards/chosen": -3.009340763092041,
|
1254 |
-
"rewards/margins": 3.336160182952881,
|
1255 |
-
"rewards/rejected": -6.3454999923706055,
|
1256 |
-
"step": 770,
|
1257 |
-
"use_label": 11013.5625
|
1258 |
-
},
|
1259 |
-
{
|
1260 |
-
"epoch": 0.82,
|
1261 |
-
"learning_rate": 2.0372526193247966e-06,
|
1262 |
-
"logits/chosen": -2.831890344619751,
|
1263 |
-
"logits/rejected": -2.814185619354248,
|
1264 |
-
"logps/chosen": -318.90240478515625,
|
1265 |
-
"logps/rejected": -319.7893981933594,
|
1266 |
-
"loss": 0.1618,
|
1267 |
-
"pred_label": 13735.0751953125,
|
1268 |
-
"rewards/accuracies": 0.706250011920929,
|
1269 |
-
"rewards/chosen": -3.30363392829895,
|
1270 |
-
"rewards/margins": 2.769784688949585,
|
1271 |
-
"rewards/rejected": -6.073418140411377,
|
1272 |
-
"step": 780,
|
1273 |
-
"use_label": 11066.9248046875
|
1274 |
-
},
|
1275 |
-
{
|
1276 |
-
"epoch": 0.83,
|
1277 |
-
"learning_rate": 1.920838183934808e-06,
|
1278 |
-
"logits/chosen": -2.845829486846924,
|
1279 |
-
"logits/rejected": -2.8150553703308105,
|
1280 |
-
"logps/chosen": -299.32720947265625,
|
1281 |
-
"logps/rejected": -322.7772521972656,
|
1282 |
-
"loss": 0.1829,
|
1283 |
-
"pred_label": 13994.1875,
|
1284 |
-
"rewards/accuracies": 0.675000011920929,
|
1285 |
-
"rewards/chosen": -3.5865261554718018,
|
1286 |
-
"rewards/margins": 2.9081783294677734,
|
1287 |
-
"rewards/rejected": -6.494704246520996,
|
1288 |
-
"step": 790,
|
1289 |
-
"use_label": 11127.8125
|
1290 |
-
},
|
1291 |
-
{
|
1292 |
-
"epoch": 0.84,
|
1293 |
-
"learning_rate": 1.8044237485448196e-06,
|
1294 |
-
"logits/chosen": -2.7826781272888184,
|
1295 |
-
"logits/rejected": -2.74163818359375,
|
1296 |
-
"logps/chosen": -319.0447082519531,
|
1297 |
-
"logps/rejected": -339.4092712402344,
|
1298 |
-
"loss": 0.1622,
|
1299 |
-
"pred_label": 14244.275390625,
|
1300 |
-
"rewards/accuracies": 0.7093750238418579,
|
1301 |
-
"rewards/chosen": -3.1698780059814453,
|
1302 |
-
"rewards/margins": 3.544410228729248,
|
1303 |
-
"rewards/rejected": -6.714288234710693,
|
1304 |
-
"step": 800,
|
1305 |
-
"use_label": 11197.724609375
|
1306 |
-
},
|
1307 |
-
{
|
1308 |
-
"epoch": 0.85,
|
1309 |
-
"learning_rate": 1.6880093131548315e-06,
|
1310 |
-
"logits/chosen": -2.7925405502319336,
|
1311 |
-
"logits/rejected": -2.7898240089416504,
|
1312 |
-
"logps/chosen": -316.834716796875,
|
1313 |
-
"logps/rejected": -300.3663330078125,
|
1314 |
-
"loss": 0.1831,
|
1315 |
-
"pred_label": 14493.287109375,
|
1316 |
-
"rewards/accuracies": 0.6937500238418579,
|
1317 |
-
"rewards/chosen": -3.4652843475341797,
|
1318 |
-
"rewards/margins": 2.749237060546875,
|
1319 |
-
"rewards/rejected": -6.214521408081055,
|
1320 |
-
"step": 810,
|
1321 |
-
"use_label": 11268.712890625
|
1322 |
-
},
|
1323 |
-
{
|
1324 |
-
"epoch": 0.86,
|
1325 |
-
"learning_rate": 1.5715948777648429e-06,
|
1326 |
-
"logits/chosen": -2.7998623847961426,
|
1327 |
-
"logits/rejected": -2.7955284118652344,
|
1328 |
-
"logps/chosen": -329.0666198730469,
|
1329 |
-
"logps/rejected": -320.14495849609375,
|
1330 |
-
"loss": 0.203,
|
1331 |
-
"pred_label": 14746.7998046875,
|
1332 |
-
"rewards/accuracies": 0.6937500238418579,
|
1333 |
-
"rewards/chosen": -3.2825725078582764,
|
1334 |
-
"rewards/margins": 3.25768780708313,
|
1335 |
-
"rewards/rejected": -6.540260314941406,
|
1336 |
-
"step": 820,
|
1337 |
-
"use_label": 11335.2001953125
|
1338 |
-
},
|
1339 |
-
{
|
1340 |
-
"epoch": 0.87,
|
1341 |
-
"learning_rate": 1.4551804423748547e-06,
|
1342 |
-
"logits/chosen": -2.800252914428711,
|
1343 |
-
"logits/rejected": -2.7940683364868164,
|
1344 |
-
"logps/chosen": -293.72113037109375,
|
1345 |
-
"logps/rejected": -365.59320068359375,
|
1346 |
-
"loss": 0.1561,
|
1347 |
-
"pred_label": 15014.0126953125,
|
1348 |
-
"rewards/accuracies": 0.734375,
|
1349 |
-
"rewards/chosen": -3.40069842338562,
|
1350 |
-
"rewards/margins": 3.9982776641845703,
|
1351 |
-
"rewards/rejected": -7.3989763259887695,
|
1352 |
-
"step": 830,
|
1353 |
-
"use_label": 11387.9873046875
|
1354 |
-
},
|
1355 |
-
{
|
1356 |
-
"epoch": 0.88,
|
1357 |
-
"learning_rate": 1.3387660069848663e-06,
|
1358 |
-
"logits/chosen": -2.803891181945801,
|
1359 |
-
"logits/rejected": -2.8099112510681152,
|
1360 |
-
"logps/chosen": -318.6631164550781,
|
1361 |
-
"logps/rejected": -330.1468811035156,
|
1362 |
-
"loss": 0.1712,
|
1363 |
-
"pred_label": 15274.9873046875,
|
1364 |
-
"rewards/accuracies": 0.6781250238418579,
|
1365 |
-
"rewards/chosen": -3.874751567840576,
|
1366 |
-
"rewards/margins": 2.169405698776245,
|
1367 |
-
"rewards/rejected": -6.044157981872559,
|
1368 |
-
"step": 840,
|
1369 |
-
"use_label": 11447.0126953125
|
1370 |
-
},
|
1371 |
-
{
|
1372 |
-
"epoch": 0.89,
|
1373 |
-
"learning_rate": 1.222351571594878e-06,
|
1374 |
-
"logits/chosen": -2.803412914276123,
|
1375 |
-
"logits/rejected": -2.825878620147705,
|
1376 |
-
"logps/chosen": -309.2081604003906,
|
1377 |
-
"logps/rejected": -315.7529602050781,
|
1378 |
-
"loss": 0.1758,
|
1379 |
-
"pred_label": 15528.2001953125,
|
1380 |
-
"rewards/accuracies": 0.7124999761581421,
|
1381 |
-
"rewards/chosen": -3.5470733642578125,
|
1382 |
-
"rewards/margins": 3.1740689277648926,
|
1383 |
-
"rewards/rejected": -6.721141815185547,
|
1384 |
-
"step": 850,
|
1385 |
-
"use_label": 11513.7998046875
|
1386 |
-
},
|
1387 |
-
{
|
1388 |
-
"epoch": 0.9,
|
1389 |
-
"learning_rate": 1.1059371362048893e-06,
|
1390 |
-
"logits/chosen": -2.7905640602111816,
|
1391 |
-
"logits/rejected": -2.7931439876556396,
|
1392 |
-
"logps/chosen": -333.94171142578125,
|
1393 |
-
"logps/rejected": -340.4829406738281,
|
1394 |
-
"loss": 0.194,
|
1395 |
-
"pred_label": 15781.775390625,
|
1396 |
-
"rewards/accuracies": 0.640625,
|
1397 |
-
"rewards/chosen": -4.047911643981934,
|
1398 |
-
"rewards/margins": 2.3354756832122803,
|
1399 |
-
"rewards/rejected": -6.383387565612793,
|
1400 |
-
"step": 860,
|
1401 |
-
"use_label": 11580.224609375
|
1402 |
-
},
|
1403 |
-
{
|
1404 |
-
"epoch": 0.91,
|
1405 |
-
"learning_rate": 9.895227008149012e-07,
|
1406 |
-
"logits/chosen": -2.773538112640381,
|
1407 |
-
"logits/rejected": -2.7751145362854004,
|
1408 |
-
"logps/chosen": -297.7669982910156,
|
1409 |
-
"logps/rejected": -327.5148010253906,
|
1410 |
-
"loss": 0.1636,
|
1411 |
-
"pred_label": 16038.3251953125,
|
1412 |
-
"rewards/accuracies": 0.7093750238418579,
|
1413 |
-
"rewards/chosen": -3.391941547393799,
|
1414 |
-
"rewards/margins": 3.371931552886963,
|
1415 |
-
"rewards/rejected": -6.7638726234436035,
|
1416 |
-
"step": 870,
|
1417 |
-
"use_label": 11643.6748046875
|
1418 |
-
},
|
1419 |
-
{
|
1420 |
-
"epoch": 0.92,
|
1421 |
-
"learning_rate": 8.731082654249128e-07,
|
1422 |
-
"logits/chosen": -2.8104777336120605,
|
1423 |
-
"logits/rejected": -2.7986841201782227,
|
1424 |
-
"logps/chosen": -308.0206298828125,
|
1425 |
-
"logps/rejected": -325.0122985839844,
|
1426 |
-
"loss": 0.1666,
|
1427 |
-
"pred_label": 16292.400390625,
|
1428 |
-
"rewards/accuracies": 0.6875,
|
1429 |
-
"rewards/chosen": -3.5868797302246094,
|
1430 |
-
"rewards/margins": 2.8977627754211426,
|
1431 |
-
"rewards/rejected": -6.484642028808594,
|
1432 |
-
"step": 880,
|
1433 |
-
"use_label": 11709.599609375
|
1434 |
-
},
|
1435 |
-
{
|
1436 |
-
"epoch": 0.93,
|
1437 |
-
"learning_rate": 7.566938300349244e-07,
|
1438 |
-
"logits/chosen": -2.830348491668701,
|
1439 |
-
"logits/rejected": -2.8405864238739014,
|
1440 |
-
"logps/chosen": -300.59930419921875,
|
1441 |
-
"logps/rejected": -333.3864440917969,
|
1442 |
-
"loss": 0.1743,
|
1443 |
-
"pred_label": 16542.474609375,
|
1444 |
-
"rewards/accuracies": 0.703125,
|
1445 |
-
"rewards/chosen": -3.5683798789978027,
|
1446 |
-
"rewards/margins": 2.9162092208862305,
|
1447 |
-
"rewards/rejected": -6.48459005355835,
|
1448 |
-
"step": 890,
|
1449 |
-
"use_label": 11779.525390625
|
1450 |
-
},
|
1451 |
-
{
|
1452 |
-
"epoch": 0.94,
|
1453 |
-
"learning_rate": 6.402793946449361e-07,
|
1454 |
-
"logits/chosen": -2.7899200916290283,
|
1455 |
-
"logits/rejected": -2.780874252319336,
|
1456 |
-
"logps/chosen": -311.51422119140625,
|
1457 |
-
"logps/rejected": -318.4853210449219,
|
1458 |
-
"loss": 0.1903,
|
1459 |
-
"pred_label": 16801.587890625,
|
1460 |
-
"rewards/accuracies": 0.7093750238418579,
|
1461 |
-
"rewards/chosen": -3.593315601348877,
|
1462 |
-
"rewards/margins": 2.630795955657959,
|
1463 |
-
"rewards/rejected": -6.224111080169678,
|
1464 |
-
"step": 900,
|
1465 |
-
"use_label": 11840.412109375
|
1466 |
-
},
|
1467 |
-
{
|
1468 |
-
"epoch": 0.95,
|
1469 |
-
"learning_rate": 5.238649592549476e-07,
|
1470 |
-
"logits/chosen": -2.805046558380127,
|
1471 |
-
"logits/rejected": -2.774458408355713,
|
1472 |
-
"logps/chosen": -337.86859130859375,
|
1473 |
-
"logps/rejected": -338.61444091796875,
|
1474 |
-
"loss": 0.1984,
|
1475 |
-
"pred_label": 17054.8125,
|
1476 |
-
"rewards/accuracies": 0.6937500238418579,
|
1477 |
-
"rewards/chosen": -3.481353282928467,
|
1478 |
-
"rewards/margins": 3.0629849433898926,
|
1479 |
-
"rewards/rejected": -6.544338226318359,
|
1480 |
-
"step": 910,
|
1481 |
-
"use_label": 11907.1875
|
1482 |
-
},
|
1483 |
-
{
|
1484 |
-
"epoch": 0.96,
|
1485 |
-
"learning_rate": 4.0745052386495924e-07,
|
1486 |
-
"logits/chosen": -2.776197671890259,
|
1487 |
-
"logits/rejected": -2.7662010192871094,
|
1488 |
-
"logps/chosen": -325.04901123046875,
|
1489 |
-
"logps/rejected": -332.0552978515625,
|
1490 |
-
"loss": 0.1684,
|
1491 |
-
"pred_label": 17301.6875,
|
1492 |
-
"rewards/accuracies": 0.6968749761581421,
|
1493 |
-
"rewards/chosen": -3.9256300926208496,
|
1494 |
-
"rewards/margins": 2.9148411750793457,
|
1495 |
-
"rewards/rejected": -6.8404717445373535,
|
1496 |
-
"step": 920,
|
1497 |
-
"use_label": 11980.3125
|
1498 |
-
},
|
1499 |
-
{
|
1500 |
-
"epoch": 0.97,
|
1501 |
-
"learning_rate": 2.910360884749709e-07,
|
1502 |
-
"logits/chosen": -2.7972004413604736,
|
1503 |
-
"logits/rejected": -2.7847728729248047,
|
1504 |
-
"logps/chosen": -313.59600830078125,
|
1505 |
-
"logps/rejected": -332.9956359863281,
|
1506 |
-
"loss": 0.1698,
|
1507 |
-
"pred_label": 17560.25,
|
1508 |
-
"rewards/accuracies": 0.7593749761581421,
|
1509 |
-
"rewards/chosen": -3.093097686767578,
|
1510 |
-
"rewards/margins": 4.027865886688232,
|
1511 |
-
"rewards/rejected": -7.120964050292969,
|
1512 |
-
"step": 930,
|
1513 |
-
"use_label": 12041.75
|
1514 |
-
},
|
1515 |
-
{
|
1516 |
-
"epoch": 0.98,
|
1517 |
-
"learning_rate": 1.7462165308498255e-07,
|
1518 |
-
"logits/chosen": -2.8208765983581543,
|
1519 |
-
"logits/rejected": -2.8135807514190674,
|
1520 |
-
"logps/chosen": -323.46075439453125,
|
1521 |
-
"logps/rejected": -343.5670471191406,
|
1522 |
-
"loss": 0.1804,
|
1523 |
-
"pred_label": 17812.375,
|
1524 |
-
"rewards/accuracies": 0.7281249761581421,
|
1525 |
-
"rewards/chosen": -3.7054646015167236,
|
1526 |
-
"rewards/margins": 3.41404390335083,
|
1527 |
-
"rewards/rejected": -7.119508266448975,
|
1528 |
-
"step": 940,
|
1529 |
-
"use_label": 12109.625
|
1530 |
-
},
|
1531 |
-
{
|
1532 |
-
"epoch": 0.99,
|
1533 |
-
"learning_rate": 5.8207217694994185e-08,
|
1534 |
-
"logits/chosen": -2.8133676052093506,
|
1535 |
-
"logits/rejected": -2.7860281467437744,
|
1536 |
-
"logps/chosen": -309.82440185546875,
|
1537 |
-
"logps/rejected": -331.61480712890625,
|
1538 |
-
"loss": 0.1523,
|
1539 |
-
"pred_label": 18072.86328125,
|
1540 |
-
"rewards/accuracies": 0.7250000238418579,
|
1541 |
-
"rewards/chosen": -3.8211193084716797,
|
1542 |
-
"rewards/margins": 3.1999752521514893,
|
1543 |
-
"rewards/rejected": -7.021093845367432,
|
1544 |
-
"step": 950,
|
1545 |
-
"use_label": 12169.1376953125
|
1546 |
-
},
|
1547 |
-
{
|
1548 |
-
"epoch": 1.0,
|
1549 |
-
"eval_logits/chosen": -2.819918155670166,
|
1550 |
-
"eval_logits/rejected": -2.7931315898895264,
|
1551 |
-
"eval_logps/chosen": -319.5545654296875,
|
1552 |
-
"eval_logps/rejected": -329.6432189941406,
|
1553 |
-
"eval_loss": 0.19092892110347748,
|
1554 |
-
"eval_pred_label": 18723.943359375,
|
1555 |
-
"eval_rewards/accuracies": 0.6940000057220459,
|
1556 |
-
"eval_rewards/chosen": -3.757920265197754,
|
1557 |
-
"eval_rewards/margins": 2.9776601791381836,
|
1558 |
-
"eval_rewards/rejected": -6.735579967498779,
|
1559 |
-
"eval_runtime": 857.7691,
|
1560 |
-
"eval_samples_per_second": 2.332,
|
1561 |
-
"eval_steps_per_second": 0.291,
|
1562 |
-
"eval_use_label": 12338.0556640625,
|
1563 |
-
"step": 955
|
1564 |
},
|
1565 |
{
|
1566 |
"epoch": 1.0,
|
1567 |
-
"step":
|
1568 |
"total_flos": 0.0,
|
1569 |
-
"train_loss": 0.
|
1570 |
-
"train_runtime":
|
1571 |
-
"train_samples_per_second":
|
1572 |
-
"train_steps_per_second": 0.
|
1573 |
}
|
1574 |
],
|
1575 |
"logging_steps": 10,
|
1576 |
-
"max_steps":
|
1577 |
"num_train_epochs": 1,
|
1578 |
-
"save_steps":
|
1579 |
"total_flos": 0.0,
|
1580 |
"trial_name": null,
|
1581 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"learning_rate": 0.0,
|
14 |
+
"logps/chosen": -242.30880737304688,
|
15 |
+
"logps/rejected": -225.008056640625,
|
|
|
|
|
16 |
"loss": 0.6931,
|
|
|
17 |
"rewards/accuracies": 0.0,
|
18 |
"rewards/chosen": 0.0,
|
19 |
"rewards/margins": 0.0,
|
20 |
"rewards/rejected": 0.0,
|
21 |
+
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
},
|
23 |
{
|
24 |
"epoch": 1.0,
|
25 |
+
"step": 1,
|
26 |
"total_flos": 0.0,
|
27 |
+
"train_loss": 0.6931471824645996,
|
28 |
+
"train_runtime": 27.1859,
|
29 |
+
"train_samples_per_second": 2.244,
|
30 |
+
"train_steps_per_second": 0.037
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 10,
|
34 |
+
"max_steps": 1,
|
35 |
"num_train_epochs": 1,
|
36 |
+
"save_steps": 100,
|
37 |
"total_flos": 0.0,
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -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:d299158ded921c7c4a382f6de9a9047ea7879151db50274c82a74d2f19ddaeb9
|
3 |
+
size 4664
|