NicholasCorrado
commited on
Commit
•
ccdfcea
1
Parent(s):
d16c0da
Model save
Browse files- README.md +1 -28
- all_results.json +6 -19
- train_results.json +6 -6
- trainer_state.json +18 -1603
README.md
CHANGED
@@ -3,15 +3,9 @@ library_name: transformers
|
|
3 |
license: apache-2.0
|
4 |
base_model: alignment-handbook/zephyr-7b-sft-full
|
5 |
tags:
|
6 |
-
- alignment-handbook
|
7 |
- trl
|
8 |
- dpo
|
9 |
- generated_from_trainer
|
10 |
-
- trl
|
11 |
-
- dpo
|
12 |
-
- generated_from_trainer
|
13 |
-
datasets:
|
14 |
-
- data/rlced_conifer
|
15 |
model-index:
|
16 |
- name: rlced-conifer-zephyr-7b-dpo-2e
|
17 |
results: []
|
@@ -22,17 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
22 |
|
23 |
# rlced-conifer-zephyr-7b-dpo-2e
|
24 |
|
25 |
-
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on
|
26 |
-
It achieves the following results on the evaluation set:
|
27 |
-
- Loss: 0.1593
|
28 |
-
- Rewards/chosen: -9.2247
|
29 |
-
- Rewards/rejected: -22.0325
|
30 |
-
- Rewards/accuracies: 0.9326
|
31 |
-
- Rewards/margins: 12.8079
|
32 |
-
- Logps/rejected: -2649.1938
|
33 |
-
- Logps/chosen: -1345.8763
|
34 |
-
- Logits/rejected: 3.3806
|
35 |
-
- Logits/chosen: 0.2633
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -67,17 +51,6 @@ The following hyperparameters were used during training:
|
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
-
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
71 |
-
|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
72 |
-
| 0.2571 | 0.2076 | 100 | 0.2502 | -2.3096 | -5.4299 | 0.8897 | 3.1203 | -988.9271 | -654.3687 | -2.5612 | -2.5702 |
|
73 |
-
| 0.1684 | 0.4152 | 200 | 0.1771 | -3.3724 | -8.6989 | 0.9142 | 5.3265 | -1315.8264 | -760.6486 | 0.9749 | -0.3442 |
|
74 |
-
| 0.1506 | 0.6227 | 300 | 0.1640 | -3.1556 | -9.7233 | 0.9216 | 6.5677 | -1418.2717 | -738.9712 | 1.6434 | -0.4687 |
|
75 |
-
| 0.1426 | 0.8303 | 400 | 0.1523 | -5.6795 | -14.2428 | 0.9301 | 8.5633 | -1870.2236 | -991.3617 | 3.6793 | 0.9505 |
|
76 |
-
| 0.0881 | 1.0379 | 500 | 0.1592 | -8.3376 | -21.0153 | 0.9314 | 12.6778 | -2547.4749 | -1257.1659 | 4.5267 | 1.2345 |
|
77 |
-
| 0.0774 | 1.2455 | 600 | 0.1560 | -8.5445 | -20.6787 | 0.9326 | 12.1342 | -2513.8113 | -1277.8566 | 4.0373 | 1.1427 |
|
78 |
-
| 0.0747 | 1.4530 | 700 | 0.1579 | -8.8472 | -21.2653 | 0.9277 | 12.4181 | -2572.4675 | -1308.1294 | 3.5812 | 0.4989 |
|
79 |
-
| 0.0811 | 1.6606 | 800 | 0.1545 | -8.3810 | -19.9040 | 0.9289 | 11.5230 | -2436.3406 | -1261.5127 | 3.2546 | 0.2172 |
|
80 |
-
| 0.069 | 1.8682 | 900 | 0.1592 | -9.2177 | -21.9885 | 0.9326 | 12.7708 | -2644.7937 | -1345.1790 | 3.3692 | 0.2563 |
|
81 |
|
82 |
|
83 |
### Framework versions
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: alignment-handbook/zephyr-7b-sft-full
|
5 |
tags:
|
|
|
6 |
- trl
|
7 |
- dpo
|
8 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
9 |
model-index:
|
10 |
- name: rlced-conifer-zephyr-7b-dpo-2e
|
11 |
results: []
|
|
|
16 |
|
17 |
# rlced-conifer-zephyr-7b-dpo-2e
|
18 |
|
19 |
+
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
51 |
|
52 |
### Training results
|
53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,22 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_logits/chosen": 0.2633172273635864,
|
4 |
-
"eval_logits/rejected": 3.3806047439575195,
|
5 |
-
"eval_logps/chosen": -1345.8763427734375,
|
6 |
-
"eval_logps/rejected": -2649.19384765625,
|
7 |
-
"eval_loss": 0.15931174159049988,
|
8 |
-
"eval_rewards/accuracies": 0.9325980544090271,
|
9 |
-
"eval_rewards/chosen": -9.224682807922363,
|
10 |
-
"eval_rewards/margins": 12.807853698730469,
|
11 |
-
"eval_rewards/rejected": -22.03253746032715,
|
12 |
-
"eval_runtime": 298.1405,
|
13 |
-
"eval_samples": 6491,
|
14 |
-
"eval_samples_per_second": 21.772,
|
15 |
-
"eval_steps_per_second": 0.342,
|
16 |
"total_flos": 0.0,
|
17 |
-
"train_loss": 0.
|
18 |
-
"train_runtime":
|
19 |
-
"train_samples":
|
20 |
-
"train_samples_per_second":
|
21 |
-
"train_steps_per_second": 0.
|
22 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.1732867956161499,
|
5 |
+
"train_runtime": 97.0028,
|
6 |
+
"train_samples": 50,
|
7 |
+
"train_samples_per_second": 1.031,
|
8 |
+
"train_steps_per_second": 0.021
|
9 |
}
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"total_flos": 0.0,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples":
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.0,
|
3 |
"total_flos": 0.0,
|
4 |
+
"train_loss": 0.1732867956161499,
|
5 |
+
"train_runtime": 97.0028,
|
6 |
+
"train_samples": 50,
|
7 |
+
"train_samples_per_second": 1.031,
|
8 |
+
"train_steps_per_second": 0.021
|
9 |
}
|
trainer_state.json
CHANGED
@@ -1,22 +1,21 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
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": 0
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"logits/
|
16 |
-
"
|
17 |
-
"logps/
|
18 |
-
"
|
19 |
-
"loss": 0.6931,
|
20 |
"rewards/accuracies": 0.0,
|
21 |
"rewards/chosen": 0.0,
|
22 |
"rewards/margins": 0.0,
|
@@ -24,1604 +23,20 @@
|
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
-
"epoch": 0
|
28 |
-
"
|
29 |
-
"learning_rate": 5.154639175257731e-08,
|
30 |
-
"logits/chosen": -2.732799768447876,
|
31 |
-
"logits/rejected": -2.7348814010620117,
|
32 |
-
"logps/chosen": -366.5058288574219,
|
33 |
-
"logps/rejected": -412.2818908691406,
|
34 |
-
"loss": 0.6931,
|
35 |
-
"rewards/accuracies": 0.4652777910232544,
|
36 |
-
"rewards/chosen": -0.00011030762834707275,
|
37 |
-
"rewards/margins": 0.00028051523258909583,
|
38 |
-
"rewards/rejected": -0.0003908228827640414,
|
39 |
-
"step": 10
|
40 |
-
},
|
41 |
-
{
|
42 |
-
"epoch": 0.04151530877010898,
|
43 |
-
"grad_norm": 7.570830729268252,
|
44 |
-
"learning_rate": 1.0309278350515462e-07,
|
45 |
-
"logits/chosen": -2.7170357704162598,
|
46 |
-
"logits/rejected": -2.6939330101013184,
|
47 |
-
"logps/chosen": -378.942138671875,
|
48 |
-
"logps/rejected": -404.09735107421875,
|
49 |
-
"loss": 0.6921,
|
50 |
-
"rewards/accuracies": 0.640625,
|
51 |
-
"rewards/chosen": 0.00050427729729563,
|
52 |
-
"rewards/margins": 0.0023104187566787004,
|
53 |
-
"rewards/rejected": -0.001806141110137105,
|
54 |
-
"step": 20
|
55 |
-
},
|
56 |
-
{
|
57 |
-
"epoch": 0.062272963155163466,
|
58 |
-
"grad_norm": 7.630669954109631,
|
59 |
-
"learning_rate": 1.5463917525773197e-07,
|
60 |
-
"logits/chosen": -2.7188973426818848,
|
61 |
-
"logits/rejected": -2.7039918899536133,
|
62 |
-
"logps/chosen": -365.66571044921875,
|
63 |
-
"logps/rejected": -388.82623291015625,
|
64 |
-
"loss": 0.6864,
|
65 |
-
"rewards/accuracies": 0.815625011920929,
|
66 |
-
"rewards/chosen": 0.0047697038389742374,
|
67 |
-
"rewards/margins": 0.01397106982767582,
|
68 |
-
"rewards/rejected": -0.00920136459171772,
|
69 |
-
"step": 30
|
70 |
-
},
|
71 |
-
{
|
72 |
-
"epoch": 0.08303061754021795,
|
73 |
-
"grad_norm": 7.812718404148332,
|
74 |
-
"learning_rate": 2.0618556701030925e-07,
|
75 |
-
"logits/chosen": -2.7190403938293457,
|
76 |
-
"logits/rejected": -2.684091091156006,
|
77 |
-
"logps/chosen": -350.58087158203125,
|
78 |
-
"logps/rejected": -365.0170593261719,
|
79 |
-
"loss": 0.6693,
|
80 |
-
"rewards/accuracies": 0.8656250238418579,
|
81 |
-
"rewards/chosen": 0.027430161833763123,
|
82 |
-
"rewards/margins": 0.04917122796177864,
|
83 |
-
"rewards/rejected": -0.021741071715950966,
|
84 |
-
"step": 40
|
85 |
-
},
|
86 |
-
{
|
87 |
-
"epoch": 0.10378827192527244,
|
88 |
-
"grad_norm": 8.920978446164991,
|
89 |
-
"learning_rate": 2.5773195876288655e-07,
|
90 |
-
"logits/chosen": -2.729093074798584,
|
91 |
-
"logits/rejected": -2.7239317893981934,
|
92 |
-
"logps/chosen": -358.971435546875,
|
93 |
-
"logps/rejected": -397.4567565917969,
|
94 |
-
"loss": 0.6298,
|
95 |
-
"rewards/accuracies": 0.859375,
|
96 |
-
"rewards/chosen": 0.07278638333082199,
|
97 |
-
"rewards/margins": 0.1439397633075714,
|
98 |
-
"rewards/rejected": -0.07115338742733002,
|
99 |
-
"step": 50
|
100 |
-
},
|
101 |
-
{
|
102 |
-
"epoch": 0.12454592631032693,
|
103 |
-
"grad_norm": 9.920116758805731,
|
104 |
-
"learning_rate": 3.0927835051546394e-07,
|
105 |
-
"logits/chosen": -2.6944854259490967,
|
106 |
-
"logits/rejected": -2.677772045135498,
|
107 |
-
"logps/chosen": -348.3173522949219,
|
108 |
-
"logps/rejected": -426.961669921875,
|
109 |
-
"loss": 0.548,
|
110 |
-
"rewards/accuracies": 0.875,
|
111 |
-
"rewards/chosen": -0.01142303366214037,
|
112 |
-
"rewards/margins": 0.3693596422672272,
|
113 |
-
"rewards/rejected": -0.3807826638221741,
|
114 |
-
"step": 60
|
115 |
-
},
|
116 |
-
{
|
117 |
-
"epoch": 0.14530358069538143,
|
118 |
-
"grad_norm": 14.365707646692588,
|
119 |
-
"learning_rate": 3.608247422680412e-07,
|
120 |
-
"logits/chosen": -2.7343642711639404,
|
121 |
-
"logits/rejected": -2.691175937652588,
|
122 |
-
"logps/chosen": -450.86602783203125,
|
123 |
-
"logps/rejected": -535.1449584960938,
|
124 |
-
"loss": 0.4278,
|
125 |
-
"rewards/accuracies": 0.856249988079071,
|
126 |
-
"rewards/chosen": -0.5426548719406128,
|
127 |
-
"rewards/margins": 0.7670809626579285,
|
128 |
-
"rewards/rejected": -1.3097360134124756,
|
129 |
-
"step": 70
|
130 |
-
},
|
131 |
-
{
|
132 |
-
"epoch": 0.1660612350804359,
|
133 |
-
"grad_norm": 17.310434488935346,
|
134 |
-
"learning_rate": 4.123711340206185e-07,
|
135 |
-
"logits/chosen": -2.697681188583374,
|
136 |
-
"logits/rejected": -2.6777291297912598,
|
137 |
-
"logps/chosen": -547.9215087890625,
|
138 |
-
"logps/rejected": -699.3780517578125,
|
139 |
-
"loss": 0.3591,
|
140 |
-
"rewards/accuracies": 0.8656250238418579,
|
141 |
-
"rewards/chosen": -1.5689979791641235,
|
142 |
-
"rewards/margins": 1.4014527797698975,
|
143 |
-
"rewards/rejected": -2.9704508781433105,
|
144 |
-
"step": 80
|
145 |
-
},
|
146 |
-
{
|
147 |
-
"epoch": 0.1868188894654904,
|
148 |
-
"grad_norm": 18.777123719069813,
|
149 |
-
"learning_rate": 4.639175257731959e-07,
|
150 |
-
"logits/chosen": -2.646989107131958,
|
151 |
-
"logits/rejected": -2.6466164588928223,
|
152 |
-
"logps/chosen": -557.4159545898438,
|
153 |
-
"logps/rejected": -791.6094970703125,
|
154 |
-
"loss": 0.3056,
|
155 |
-
"rewards/accuracies": 0.871874988079071,
|
156 |
-
"rewards/chosen": -1.921556830406189,
|
157 |
-
"rewards/margins": 2.1401381492614746,
|
158 |
-
"rewards/rejected": -4.061694622039795,
|
159 |
-
"step": 90
|
160 |
-
},
|
161 |
-
{
|
162 |
-
"epoch": 0.2075765438505449,
|
163 |
-
"grad_norm": 14.527848025037288,
|
164 |
-
"learning_rate": 4.999851606199919e-07,
|
165 |
-
"logits/chosen": -2.598267078399658,
|
166 |
-
"logits/rejected": -2.5736942291259766,
|
167 |
-
"logps/chosen": -581.7288818359375,
|
168 |
-
"logps/rejected": -923.7081909179688,
|
169 |
-
"loss": 0.2571,
|
170 |
-
"rewards/accuracies": 0.9156249761581421,
|
171 |
-
"rewards/chosen": -2.0622379779815674,
|
172 |
-
"rewards/margins": 3.1660473346710205,
|
173 |
-
"rewards/rejected": -5.228285789489746,
|
174 |
-
"step": 100
|
175 |
-
},
|
176 |
-
{
|
177 |
-
"epoch": 0.2075765438505449,
|
178 |
-
"eval_logits/chosen": -2.570211172103882,
|
179 |
-
"eval_logits/rejected": -2.5612430572509766,
|
180 |
-
"eval_logps/chosen": -654.36865234375,
|
181 |
-
"eval_logps/rejected": -988.9270629882812,
|
182 |
-
"eval_loss": 0.250244677066803,
|
183 |
-
"eval_rewards/accuracies": 0.8897058963775635,
|
184 |
-
"eval_rewards/chosen": -2.3096041679382324,
|
185 |
-
"eval_rewards/margins": 3.120264768600464,
|
186 |
-
"eval_rewards/rejected": -5.429868698120117,
|
187 |
-
"eval_runtime": 298.2798,
|
188 |
-
"eval_samples_per_second": 21.761,
|
189 |
-
"eval_steps_per_second": 0.342,
|
190 |
-
"step": 100
|
191 |
-
},
|
192 |
-
{
|
193 |
-
"epoch": 0.2283341982355994,
|
194 |
-
"grad_norm": 20.425432278137276,
|
195 |
-
"learning_rate": 4.997213984244138e-07,
|
196 |
-
"logits/chosen": -2.288006067276001,
|
197 |
-
"logits/rejected": -2.136007070541382,
|
198 |
-
"logps/chosen": -608.41552734375,
|
199 |
-
"logps/rejected": -1056.211669921875,
|
200 |
-
"loss": 0.2306,
|
201 |
-
"rewards/accuracies": 0.9281250238418579,
|
202 |
-
"rewards/chosen": -2.3692779541015625,
|
203 |
-
"rewards/margins": 4.241728782653809,
|
204 |
-
"rewards/rejected": -6.611006259918213,
|
205 |
-
"step": 110
|
206 |
-
},
|
207 |
-
{
|
208 |
-
"epoch": 0.24909185262065386,
|
209 |
-
"grad_norm": 13.460106318977088,
|
210 |
-
"learning_rate": 4.991282726678214e-07,
|
211 |
-
"logits/chosen": -1.7061725854873657,
|
212 |
-
"logits/rejected": -1.2435765266418457,
|
213 |
-
"logps/chosen": -665.3823852539062,
|
214 |
-
"logps/rejected": -1083.344482421875,
|
215 |
-
"loss": 0.2092,
|
216 |
-
"rewards/accuracies": 0.9125000238418579,
|
217 |
-
"rewards/chosen": -2.7041690349578857,
|
218 |
-
"rewards/margins": 3.9961719512939453,
|
219 |
-
"rewards/rejected": -6.700340270996094,
|
220 |
-
"step": 120
|
221 |
-
},
|
222 |
-
{
|
223 |
-
"epoch": 0.26984950700570837,
|
224 |
-
"grad_norm": 19.086564033070054,
|
225 |
-
"learning_rate": 4.982065656380468e-07,
|
226 |
-
"logits/chosen": -1.483633041381836,
|
227 |
-
"logits/rejected": -0.8341295123100281,
|
228 |
-
"logps/chosen": -623.9300537109375,
|
229 |
-
"logps/rejected": -1075.849853515625,
|
230 |
-
"loss": 0.194,
|
231 |
-
"rewards/accuracies": 0.903124988079071,
|
232 |
-
"rewards/chosen": -2.44337797164917,
|
233 |
-
"rewards/margins": 4.244832515716553,
|
234 |
-
"rewards/rejected": -6.688210487365723,
|
235 |
-
"step": 130
|
236 |
-
},
|
237 |
-
{
|
238 |
-
"epoch": 0.29060716139076287,
|
239 |
-
"grad_norm": 15.042161368077187,
|
240 |
-
"learning_rate": 4.969574929966689e-07,
|
241 |
-
"logits/chosen": -1.0453473329544067,
|
242 |
-
"logits/rejected": -0.016147825866937637,
|
243 |
-
"logps/chosen": -633.580078125,
|
244 |
-
"logps/rejected": -1098.5224609375,
|
245 |
-
"loss": 0.2082,
|
246 |
-
"rewards/accuracies": 0.890625,
|
247 |
-
"rewards/chosen": -2.631155490875244,
|
248 |
-
"rewards/margins": 4.421234130859375,
|
249 |
-
"rewards/rejected": -7.052389621734619,
|
250 |
-
"step": 140
|
251 |
-
},
|
252 |
-
{
|
253 |
-
"epoch": 0.3113648157758173,
|
254 |
-
"grad_norm": 15.666211126762926,
|
255 |
-
"learning_rate": 4.953827021756488e-07,
|
256 |
-
"logits/chosen": -1.3857558965682983,
|
257 |
-
"logits/rejected": -0.03474185988306999,
|
258 |
-
"logps/chosen": -641.5021362304688,
|
259 |
-
"logps/rejected": -1154.77587890625,
|
260 |
-
"loss": 0.1733,
|
261 |
-
"rewards/accuracies": 0.9281250238418579,
|
262 |
-
"rewards/chosen": -2.8129067420959473,
|
263 |
-
"rewards/margins": 4.9361677169799805,
|
264 |
-
"rewards/rejected": -7.749074459075928,
|
265 |
-
"step": 150
|
266 |
-
},
|
267 |
-
{
|
268 |
-
"epoch": 0.3321224701608718,
|
269 |
-
"grad_norm": 27.48848947004099,
|
270 |
-
"learning_rate": 4.93484270204492e-07,
|
271 |
-
"logits/chosen": -1.0413181781768799,
|
272 |
-
"logits/rejected": 0.31071561574935913,
|
273 |
-
"logps/chosen": -641.2700805664062,
|
274 |
-
"logps/rejected": -1222.7462158203125,
|
275 |
-
"loss": 0.1801,
|
276 |
-
"rewards/accuracies": 0.9312499761581421,
|
277 |
-
"rewards/chosen": -2.573660373687744,
|
278 |
-
"rewards/margins": 5.559605121612549,
|
279 |
-
"rewards/rejected": -8.133265495300293,
|
280 |
-
"step": 160
|
281 |
-
},
|
282 |
-
{
|
283 |
-
"epoch": 0.3528801245459263,
|
284 |
-
"grad_norm": 20.795363548975157,
|
285 |
-
"learning_rate": 4.91264700970804e-07,
|
286 |
-
"logits/chosen": -0.4338255822658539,
|
287 |
-
"logits/rejected": 0.8560503125190735,
|
288 |
-
"logps/chosen": -664.4598388671875,
|
289 |
-
"logps/rejected": -1253.003662109375,
|
290 |
-
"loss": 0.1834,
|
291 |
-
"rewards/accuracies": 0.903124988079071,
|
292 |
-
"rewards/chosen": -3.056209087371826,
|
293 |
-
"rewards/margins": 5.69351863861084,
|
294 |
-
"rewards/rejected": -8.749728202819824,
|
295 |
-
"step": 170
|
296 |
-
},
|
297 |
-
{
|
298 |
-
"epoch": 0.3736377789309808,
|
299 |
-
"grad_norm": 17.31415644551086,
|
300 |
-
"learning_rate": 4.88726921917853e-07,
|
301 |
-
"logits/chosen": -1.2734315395355225,
|
302 |
-
"logits/rejected": 0.053898729383945465,
|
303 |
-
"logps/chosen": -594.52685546875,
|
304 |
-
"logps/rejected": -1158.65380859375,
|
305 |
-
"loss": 0.1862,
|
306 |
-
"rewards/accuracies": 0.925000011920929,
|
307 |
-
"rewards/chosen": -2.2788708209991455,
|
308 |
-
"rewards/margins": 5.445026397705078,
|
309 |
-
"rewards/rejected": -7.723898410797119,
|
310 |
-
"step": 180
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"epoch": 0.39439543331603527,
|
314 |
-
"grad_norm": 14.853072406578221,
|
315 |
-
"learning_rate": 4.858742801834942e-07,
|
316 |
-
"logits/chosen": -0.5313376784324646,
|
317 |
-
"logits/rejected": 0.8287642598152161,
|
318 |
-
"logps/chosen": -676.4669189453125,
|
319 |
-
"logps/rejected": -1298.01318359375,
|
320 |
-
"loss": 0.173,
|
321 |
-
"rewards/accuracies": 0.9312499761581421,
|
322 |
-
"rewards/chosen": -2.9378976821899414,
|
323 |
-
"rewards/margins": 5.850995063781738,
|
324 |
-
"rewards/rejected": -8.788891792297363,
|
325 |
-
"step": 190
|
326 |
-
},
|
327 |
-
{
|
328 |
-
"epoch": 0.4151530877010898,
|
329 |
-
"grad_norm": 14.26284853662138,
|
330 |
-
"learning_rate": 4.827105381855496e-07,
|
331 |
-
"logits/chosen": -0.06869231164455414,
|
332 |
-
"logits/rejected": 1.29701828956604,
|
333 |
-
"logps/chosen": -653.2413330078125,
|
334 |
-
"logps/rejected": -1239.662353515625,
|
335 |
-
"loss": 0.1684,
|
336 |
-
"rewards/accuracies": 0.925000011920929,
|
337 |
-
"rewards/chosen": -2.8566927909851074,
|
338 |
-
"rewards/margins": 5.576047897338867,
|
339 |
-
"rewards/rejected": -8.432741165161133,
|
340 |
-
"step": 200
|
341 |
-
},
|
342 |
-
{
|
343 |
-
"epoch": 0.4151530877010898,
|
344 |
-
"eval_logits/chosen": -0.344154953956604,
|
345 |
-
"eval_logits/rejected": 0.9748669266700745,
|
346 |
-
"eval_logps/chosen": -760.6486206054688,
|
347 |
-
"eval_logps/rejected": -1315.826416015625,
|
348 |
-
"eval_loss": 0.1770959049463272,
|
349 |
-
"eval_rewards/accuracies": 0.9142156839370728,
|
350 |
-
"eval_rewards/chosen": -3.372403383255005,
|
351 |
-
"eval_rewards/margins": 5.326459884643555,
|
352 |
-
"eval_rewards/rejected": -8.69886302947998,
|
353 |
-
"eval_runtime": 296.8516,
|
354 |
-
"eval_samples_per_second": 21.866,
|
355 |
-
"eval_steps_per_second": 0.344,
|
356 |
-
"step": 200
|
357 |
-
},
|
358 |
-
{
|
359 |
-
"epoch": 0.4359107420861443,
|
360 |
-
"grad_norm": 13.687894338265775,
|
361 |
-
"learning_rate": 4.79239868659464e-07,
|
362 |
-
"logits/chosen": -0.5194350481033325,
|
363 |
-
"logits/rejected": 1.2649457454681396,
|
364 |
-
"logps/chosen": -699.4662475585938,
|
365 |
-
"logps/rejected": -1312.603515625,
|
366 |
-
"loss": 0.1582,
|
367 |
-
"rewards/accuracies": 0.934374988079071,
|
368 |
-
"rewards/chosen": -3.3037147521972656,
|
369 |
-
"rewards/margins": 5.938404083251953,
|
370 |
-
"rewards/rejected": -9.242118835449219,
|
371 |
-
"step": 210
|
372 |
-
},
|
373 |
-
{
|
374 |
-
"epoch": 0.4566683964711988,
|
375 |
-
"grad_norm": 21.754337046254733,
|
376 |
-
"learning_rate": 4.7546684915478443e-07,
|
377 |
-
"logits/chosen": -0.8742658495903015,
|
378 |
-
"logits/rejected": 1.3033313751220703,
|
379 |
-
"logps/chosen": -670.0702514648438,
|
380 |
-
"logps/rejected": -1371.7958984375,
|
381 |
-
"loss": 0.1675,
|
382 |
-
"rewards/accuracies": 0.9156249761581421,
|
383 |
-
"rewards/chosen": -3.048536777496338,
|
384 |
-
"rewards/margins": 6.837308406829834,
|
385 |
-
"rewards/rejected": -9.885846138000488,
|
386 |
-
"step": 220
|
387 |
-
},
|
388 |
-
{
|
389 |
-
"epoch": 0.4774260508562532,
|
390 |
-
"grad_norm": 27.016825262219978,
|
391 |
-
"learning_rate": 4.7139645599771953e-07,
|
392 |
-
"logits/chosen": -1.2103874683380127,
|
393 |
-
"logits/rejected": 1.2142726182937622,
|
394 |
-
"logps/chosen": -635.36376953125,
|
395 |
-
"logps/rejected": -1365.181640625,
|
396 |
-
"loss": 0.1733,
|
397 |
-
"rewards/accuracies": 0.921875,
|
398 |
-
"rewards/chosen": -2.743067502975464,
|
399 |
-
"rewards/margins": 7.142025947570801,
|
400 |
-
"rewards/rejected": -9.885092735290527,
|
401 |
-
"step": 230
|
402 |
-
},
|
403 |
-
{
|
404 |
-
"epoch": 0.49818370524130773,
|
405 |
-
"grad_norm": 14.606776233016102,
|
406 |
-
"learning_rate": 4.6703405772774325e-07,
|
407 |
-
"logits/chosen": -0.6876879930496216,
|
408 |
-
"logits/rejected": 1.9533984661102295,
|
409 |
-
"logps/chosen": -648.3201904296875,
|
410 |
-
"logps/rejected": -1378.4886474609375,
|
411 |
-
"loss": 0.1624,
|
412 |
-
"rewards/accuracies": 0.9312499761581421,
|
413 |
-
"rewards/chosen": -2.901624917984009,
|
414 |
-
"rewards/margins": 7.063530921936035,
|
415 |
-
"rewards/rejected": -9.965155601501465,
|
416 |
-
"step": 240
|
417 |
-
},
|
418 |
-
{
|
419 |
-
"epoch": 0.5189413596263622,
|
420 |
-
"grad_norm": 14.879180241164281,
|
421 |
-
"learning_rate": 4.6238540801689896e-07,
|
422 |
-
"logits/chosen": -1.068670630455017,
|
423 |
-
"logits/rejected": 1.5525070428848267,
|
424 |
-
"logps/chosen": -595.411376953125,
|
425 |
-
"logps/rejected": -1218.922119140625,
|
426 |
-
"loss": 0.1618,
|
427 |
-
"rewards/accuracies": 0.9281250238418579,
|
428 |
-
"rewards/chosen": -2.1561543941497803,
|
429 |
-
"rewards/margins": 6.024182319641113,
|
430 |
-
"rewards/rejected": -8.180335998535156,
|
431 |
-
"step": 250
|
432 |
-
},
|
433 |
-
{
|
434 |
-
"epoch": 0.5396990140114167,
|
435 |
-
"grad_norm": 21.085080794483027,
|
436 |
-
"learning_rate": 4.5745663808114316e-07,
|
437 |
-
"logits/chosen": -1.2082252502441406,
|
438 |
-
"logits/rejected": 1.332776427268982,
|
439 |
-
"logps/chosen": -641.9990844726562,
|
440 |
-
"logps/rejected": -1324.9752197265625,
|
441 |
-
"loss": 0.164,
|
442 |
-
"rewards/accuracies": 0.925000011920929,
|
443 |
-
"rewards/chosen": -2.6882810592651367,
|
444 |
-
"rewards/margins": 6.606905460357666,
|
445 |
-
"rewards/rejected": -9.295186042785645,
|
446 |
-
"step": 260
|
447 |
-
},
|
448 |
-
{
|
449 |
-
"epoch": 0.5604566683964712,
|
450 |
-
"grad_norm": 14.503555786921384,
|
451 |
-
"learning_rate": 4.5225424859373684e-07,
|
452 |
-
"logits/chosen": -0.5242375731468201,
|
453 |
-
"logits/rejected": 2.3043034076690674,
|
454 |
-
"logps/chosen": -642.212890625,
|
455 |
-
"logps/rejected": -1466.6038818359375,
|
456 |
-
"loss": 0.1535,
|
457 |
-
"rewards/accuracies": 0.949999988079071,
|
458 |
-
"rewards/chosen": -2.8858113288879395,
|
459 |
-
"rewards/margins": 7.929835319519043,
|
460 |
-
"rewards/rejected": -10.81564712524414,
|
461 |
-
"step": 270
|
462 |
-
},
|
463 |
-
{
|
464 |
-
"epoch": 0.5812143227815257,
|
465 |
-
"grad_norm": 14.500876590205559,
|
466 |
-
"learning_rate": 4.467851011113515e-07,
|
467 |
-
"logits/chosen": -0.34295958280563354,
|
468 |
-
"logits/rejected": 2.470365047454834,
|
469 |
-
"logps/chosen": -626.3866577148438,
|
470 |
-
"logps/rejected": -1347.487060546875,
|
471 |
-
"loss": 0.1557,
|
472 |
-
"rewards/accuracies": 0.921875,
|
473 |
-
"rewards/chosen": -2.5040247440338135,
|
474 |
-
"rewards/margins": 6.9828643798828125,
|
475 |
-
"rewards/rejected": -9.486889839172363,
|
476 |
-
"step": 280
|
477 |
-
},
|
478 |
-
{
|
479 |
-
"epoch": 0.6019719771665801,
|
480 |
-
"grad_norm": 21.11138081532862,
|
481 |
-
"learning_rate": 4.410564090241966e-07,
|
482 |
-
"logits/chosen": -0.4226152002811432,
|
483 |
-
"logits/rejected": 2.2370669841766357,
|
484 |
-
"logps/chosen": -715.9142456054688,
|
485 |
-
"logps/rejected": -1435.792724609375,
|
486 |
-
"loss": 0.166,
|
487 |
-
"rewards/accuracies": 0.9125000238418579,
|
488 |
-
"rewards/chosen": -3.411532163619995,
|
489 |
-
"rewards/margins": 7.1244330406188965,
|
490 |
-
"rewards/rejected": -10.535964012145996,
|
491 |
-
"step": 290
|
492 |
-
},
|
493 |
-
{
|
494 |
-
"epoch": 0.6227296315516346,
|
495 |
-
"grad_norm": 12.837411656046333,
|
496 |
-
"learning_rate": 4.35075728042106e-07,
|
497 |
-
"logits/chosen": -0.646745502948761,
|
498 |
-
"logits/rejected": 1.6430190801620483,
|
499 |
-
"logps/chosen": -651.37060546875,
|
500 |
-
"logps/rejected": -1312.945068359375,
|
501 |
-
"loss": 0.1506,
|
502 |
-
"rewards/accuracies": 0.9468749761581421,
|
503 |
-
"rewards/chosen": -2.753232717514038,
|
504 |
-
"rewards/margins": 6.365309715270996,
|
505 |
-
"rewards/rejected": -9.118542671203613,
|
506 |
-
"step": 300
|
507 |
-
},
|
508 |
-
{
|
509 |
-
"epoch": 0.6227296315516346,
|
510 |
-
"eval_logits/chosen": -0.4686531722545624,
|
511 |
-
"eval_logits/rejected": 1.6434051990509033,
|
512 |
-
"eval_logps/chosen": -738.97119140625,
|
513 |
-
"eval_logps/rejected": -1418.271728515625,
|
514 |
-
"eval_loss": 0.16402015089988708,
|
515 |
-
"eval_rewards/accuracies": 0.9215686321258545,
|
516 |
-
"eval_rewards/chosen": -3.1556289196014404,
|
517 |
-
"eval_rewards/margins": 6.567685127258301,
|
518 |
-
"eval_rewards/rejected": -9.72331428527832,
|
519 |
-
"eval_runtime": 296.3154,
|
520 |
-
"eval_samples_per_second": 21.906,
|
521 |
-
"eval_steps_per_second": 0.344,
|
522 |
-
"step": 300
|
523 |
-
},
|
524 |
-
{
|
525 |
-
"epoch": 0.6434872859366891,
|
526 |
-
"grad_norm": 12.299461167843033,
|
527 |
-
"learning_rate": 4.2885094622913016e-07,
|
528 |
-
"logits/chosen": -0.22457298636436462,
|
529 |
-
"logits/rejected": 2.304126024246216,
|
530 |
-
"logps/chosen": -696.1895141601562,
|
531 |
-
"logps/rejected": -1399.352783203125,
|
532 |
-
"loss": 0.1538,
|
533 |
-
"rewards/accuracies": 0.903124988079071,
|
534 |
-
"rewards/chosen": -3.2637131214141846,
|
535 |
-
"rewards/margins": 6.956628322601318,
|
536 |
-
"rewards/rejected": -10.220341682434082,
|
537 |
-
"step": 310
|
538 |
-
},
|
539 |
-
{
|
540 |
-
"epoch": 0.6642449403217436,
|
541 |
-
"grad_norm": 13.016357165526102,
|
542 |
-
"learning_rate": 4.223902735997788e-07,
|
543 |
-
"logits/chosen": -0.8427863121032715,
|
544 |
-
"logits/rejected": 1.8859798908233643,
|
545 |
-
"logps/chosen": -618.1915283203125,
|
546 |
-
"logps/rejected": -1367.597412109375,
|
547 |
-
"loss": 0.1525,
|
548 |
-
"rewards/accuracies": 0.9281250238418579,
|
549 |
-
"rewards/chosen": -2.5306873321533203,
|
550 |
-
"rewards/margins": 7.276186466217041,
|
551 |
-
"rewards/rejected": -9.80687427520752,
|
552 |
-
"step": 320
|
553 |
-
},
|
554 |
-
{
|
555 |
-
"epoch": 0.6850025947067981,
|
556 |
-
"grad_norm": 11.40441988789802,
|
557 |
-
"learning_rate": 4.157022312906352e-07,
|
558 |
-
"logits/chosen": -0.8463101387023926,
|
559 |
-
"logits/rejected": 2.104464292526245,
|
560 |
-
"logps/chosen": -682.7887573242188,
|
561 |
-
"logps/rejected": -1518.4447021484375,
|
562 |
-
"loss": 0.1436,
|
563 |
-
"rewards/accuracies": 0.9156249761581421,
|
564 |
-
"rewards/chosen": -3.10284423828125,
|
565 |
-
"rewards/margins": 8.061182022094727,
|
566 |
-
"rewards/rejected": -11.164026260375977,
|
567 |
-
"step": 330
|
568 |
-
},
|
569 |
-
{
|
570 |
-
"epoch": 0.7057602490918526,
|
571 |
-
"grad_norm": 12.82722167792133,
|
572 |
-
"learning_rate": 4.0879564032162425e-07,
|
573 |
-
"logits/chosen": -0.18682530522346497,
|
574 |
-
"logits/rejected": 3.2691047191619873,
|
575 |
-
"logps/chosen": -832.2535400390625,
|
576 |
-
"logps/rejected": -1820.017333984375,
|
577 |
-
"loss": 0.1461,
|
578 |
-
"rewards/accuracies": 0.921875,
|
579 |
-
"rewards/chosen": -4.5879225730896,
|
580 |
-
"rewards/margins": 9.579926490783691,
|
581 |
-
"rewards/rejected": -14.16784954071045,
|
582 |
-
"step": 340
|
583 |
-
},
|
584 |
-
{
|
585 |
-
"epoch": 0.7265179034769071,
|
586 |
-
"grad_norm": 16.44365591813322,
|
587 |
-
"learning_rate": 4.016796099617569e-07,
|
588 |
-
"logits/chosen": -0.138845294713974,
|
589 |
-
"logits/rejected": 3.01670503616333,
|
590 |
-
"logps/chosen": -769.3917236328125,
|
591 |
-
"logps/rejected": -1580.634765625,
|
592 |
-
"loss": 0.1552,
|
593 |
-
"rewards/accuracies": 0.8843749761581421,
|
594 |
-
"rewards/chosen": -4.0832200050354,
|
595 |
-
"rewards/margins": 7.8098883628845215,
|
596 |
-
"rewards/rejected": -11.893107414245605,
|
597 |
-
"step": 350
|
598 |
-
},
|
599 |
-
{
|
600 |
-
"epoch": 0.7472755578619616,
|
601 |
-
"grad_norm": 19.24789069287223,
|
602 |
-
"learning_rate": 3.9436352571469577e-07,
|
603 |
-
"logits/chosen": 1.5992153882980347,
|
604 |
-
"logits/rejected": 5.1132683753967285,
|
605 |
-
"logps/chosen": -974.8264770507812,
|
606 |
-
"logps/rejected": -1869.984375,
|
607 |
-
"loss": 0.1447,
|
608 |
-
"rewards/accuracies": 0.9281250238418579,
|
609 |
-
"rewards/chosen": -6.103518962860107,
|
610 |
-
"rewards/margins": 8.862874031066895,
|
611 |
-
"rewards/rejected": -14.966394424438477,
|
612 |
-
"step": 360
|
613 |
-
},
|
614 |
-
{
|
615 |
-
"epoch": 0.768033212247016,
|
616 |
-
"grad_norm": 14.764411673021232,
|
617 |
-
"learning_rate": 3.868570369399893e-07,
|
618 |
-
"logits/chosen": 0.504949152469635,
|
619 |
-
"logits/rejected": 4.207425117492676,
|
620 |
-
"logps/chosen": -842.4241943359375,
|
621 |
-
"logps/rejected": -1723.845703125,
|
622 |
-
"loss": 0.1461,
|
623 |
-
"rewards/accuracies": 0.9125000238418579,
|
624 |
-
"rewards/chosen": -4.756136894226074,
|
625 |
-
"rewards/margins": 8.685012817382812,
|
626 |
-
"rewards/rejected": -13.441149711608887,
|
627 |
-
"step": 370
|
628 |
-
},
|
629 |
-
{
|
630 |
-
"epoch": 0.7887908666320705,
|
631 |
-
"grad_norm": 11.306971906638802,
|
632 |
-
"learning_rate": 3.791700441262987e-07,
|
633 |
-
"logits/chosen": 1.6941606998443604,
|
634 |
-
"logits/rejected": 4.910915374755859,
|
635 |
-
"logps/chosen": -991.244140625,
|
636 |
-
"logps/rejected": -1979.561279296875,
|
637 |
-
"loss": 0.1394,
|
638 |
-
"rewards/accuracies": 0.925000011920929,
|
639 |
-
"rewards/chosen": -6.388211727142334,
|
640 |
-
"rewards/margins": 9.29551887512207,
|
641 |
-
"rewards/rejected": -15.683731079101562,
|
642 |
-
"step": 380
|
643 |
-
},
|
644 |
-
{
|
645 |
-
"epoch": 0.809548521017125,
|
646 |
-
"grad_norm": 13.65730703963766,
|
647 |
-
"learning_rate": 3.7131268583340515e-07,
|
648 |
-
"logits/chosen": 1.5387306213378906,
|
649 |
-
"logits/rejected": 4.950864315032959,
|
650 |
-
"logps/chosen": -1013.9693603515625,
|
651 |
-
"logps/rejected": -1817.079345703125,
|
652 |
-
"loss": 0.1518,
|
653 |
-
"rewards/accuracies": 0.9468749761581421,
|
654 |
-
"rewards/chosen": -6.383057117462158,
|
655 |
-
"rewards/margins": 7.826146125793457,
|
656 |
-
"rewards/rejected": -14.209203720092773,
|
657 |
-
"step": 390
|
658 |
-
},
|
659 |
-
{
|
660 |
-
"epoch": 0.8303061754021795,
|
661 |
-
"grad_norm": 14.179745096678028,
|
662 |
-
"learning_rate": 3.632953253202198e-07,
|
663 |
-
"logits/chosen": 1.0768206119537354,
|
664 |
-
"logits/rejected": 4.270804405212402,
|
665 |
-
"logps/chosen": -915.9781494140625,
|
666 |
-
"logps/rejected": -1812.755859375,
|
667 |
-
"loss": 0.1426,
|
668 |
-
"rewards/accuracies": 0.9281250238418579,
|
669 |
-
"rewards/chosen": -5.507952690124512,
|
670 |
-
"rewards/margins": 8.6758394241333,
|
671 |
-
"rewards/rejected": -14.183792114257812,
|
672 |
-
"step": 400
|
673 |
-
},
|
674 |
-
{
|
675 |
-
"epoch": 0.8303061754021795,
|
676 |
-
"eval_logits/chosen": 0.9505479335784912,
|
677 |
-
"eval_logits/rejected": 3.6792540550231934,
|
678 |
-
"eval_logps/chosen": -991.3616943359375,
|
679 |
-
"eval_logps/rejected": -1870.2236328125,
|
680 |
-
"eval_loss": 0.15229202806949615,
|
681 |
-
"eval_rewards/accuracies": 0.9301470518112183,
|
682 |
-
"eval_rewards/chosen": -5.6795334815979,
|
683 |
-
"eval_rewards/margins": 8.563300132751465,
|
684 |
-
"eval_rewards/rejected": -14.242834091186523,
|
685 |
-
"eval_runtime": 298.0288,
|
686 |
-
"eval_samples_per_second": 21.78,
|
687 |
-
"eval_steps_per_second": 0.342,
|
688 |
-
"step": 400
|
689 |
-
},
|
690 |
-
{
|
691 |
-
"epoch": 0.851063829787234,
|
692 |
-
"grad_norm": 14.225050299873093,
|
693 |
-
"learning_rate": 3.551285368764321e-07,
|
694 |
-
"logits/chosen": 1.3883212804794312,
|
695 |
-
"logits/rejected": 4.056710243225098,
|
696 |
-
"logps/chosen": -921.244140625,
|
697 |
-
"logps/rejected": -1725.069091796875,
|
698 |
-
"loss": 0.1414,
|
699 |
-
"rewards/accuracies": 0.921875,
|
700 |
-
"rewards/chosen": -5.557861328125,
|
701 |
-
"rewards/margins": 7.890999794006348,
|
702 |
-
"rewards/rejected": -13.448862075805664,
|
703 |
-
"step": 410
|
704 |
-
},
|
705 |
-
{
|
706 |
-
"epoch": 0.8718214841722886,
|
707 |
-
"grad_norm": 21.908810437787125,
|
708 |
-
"learning_rate": 3.468230918758242e-07,
|
709 |
-
"logits/chosen": 1.0017262697219849,
|
710 |
-
"logits/rejected": 4.086182594299316,
|
711 |
-
"logps/chosen": -934.9280395507812,
|
712 |
-
"logps/rejected": -1826.6614990234375,
|
713 |
-
"loss": 0.1487,
|
714 |
-
"rewards/accuracies": 0.9281250238418579,
|
715 |
-
"rewards/chosen": -5.608671188354492,
|
716 |
-
"rewards/margins": 8.596394538879395,
|
717 |
-
"rewards/rejected": -14.205065727233887,
|
718 |
-
"step": 420
|
719 |
-
},
|
720 |
-
{
|
721 |
-
"epoch": 0.892579138557343,
|
722 |
-
"grad_norm": 14.422793954218163,
|
723 |
-
"learning_rate": 3.383899445696477e-07,
|
724 |
-
"logits/chosen": 0.6862390637397766,
|
725 |
-
"logits/rejected": 3.530297040939331,
|
726 |
-
"logps/chosen": -932.3873291015625,
|
727 |
-
"logps/rejected": -1817.0745849609375,
|
728 |
-
"loss": 0.129,
|
729 |
-
"rewards/accuracies": 0.921875,
|
730 |
-
"rewards/chosen": -5.5939507484436035,
|
731 |
-
"rewards/margins": 8.62092399597168,
|
732 |
-
"rewards/rejected": -14.214874267578125,
|
733 |
-
"step": 430
|
734 |
-
},
|
735 |
-
{
|
736 |
-
"epoch": 0.9133367929423976,
|
737 |
-
"grad_norm": 17.011117159702987,
|
738 |
-
"learning_rate": 3.2984021763879756e-07,
|
739 |
-
"logits/chosen": 1.3755428791046143,
|
740 |
-
"logits/rejected": 4.330183029174805,
|
741 |
-
"logps/chosen": -1071.127197265625,
|
742 |
-
"logps/rejected": -2124.4716796875,
|
743 |
-
"loss": 0.1488,
|
744 |
-
"rewards/accuracies": 0.9281250238418579,
|
745 |
-
"rewards/chosen": -6.959136009216309,
|
746 |
-
"rewards/margins": 10.387044906616211,
|
747 |
-
"rewards/rejected": -17.346179962158203,
|
748 |
-
"step": 440
|
749 |
-
},
|
750 |
-
{
|
751 |
-
"epoch": 0.934094447327452,
|
752 |
-
"grad_norm": 14.158345398063162,
|
753 |
-
"learning_rate": 3.211851875238408e-07,
|
754 |
-
"logits/chosen": 1.2293100357055664,
|
755 |
-
"logits/rejected": 4.549264430999756,
|
756 |
-
"logps/chosen": -1061.044189453125,
|
757 |
-
"logps/rejected": -2061.3359375,
|
758 |
-
"loss": 0.1387,
|
759 |
-
"rewards/accuracies": 0.940625011920929,
|
760 |
-
"rewards/chosen": -6.939100742340088,
|
761 |
-
"rewards/margins": 9.909866333007812,
|
762 |
-
"rewards/rejected": -16.848966598510742,
|
763 |
-
"step": 450
|
764 |
-
},
|
765 |
-
{
|
766 |
-
"epoch": 0.9548521017125065,
|
767 |
-
"grad_norm": 15.78022665142005,
|
768 |
-
"learning_rate": 3.124362695522476e-07,
|
769 |
-
"logits/chosen": 2.06438946723938,
|
770 |
-
"logits/rejected": 4.793455123901367,
|
771 |
-
"logps/chosen": -1161.7301025390625,
|
772 |
-
"logps/rejected": -2112.584228515625,
|
773 |
-
"loss": 0.1387,
|
774 |
-
"rewards/accuracies": 0.949999988079071,
|
775 |
-
"rewards/chosen": -7.919003963470459,
|
776 |
-
"rewards/margins": 9.370214462280273,
|
777 |
-
"rewards/rejected": -17.289216995239258,
|
778 |
-
"step": 460
|
779 |
-
},
|
780 |
-
{
|
781 |
-
"epoch": 0.975609756097561,
|
782 |
-
"grad_norm": 14.672366285416803,
|
783 |
-
"learning_rate": 3.036050028824415e-07,
|
784 |
-
"logits/chosen": 1.6745359897613525,
|
785 |
-
"logits/rejected": 4.174818515777588,
|
786 |
-
"logps/chosen": -1067.4365234375,
|
787 |
-
"logps/rejected": -1914.353515625,
|
788 |
-
"loss": 0.1267,
|
789 |
-
"rewards/accuracies": 0.9312499761581421,
|
790 |
-
"rewards/chosen": -6.962777137756348,
|
791 |
-
"rewards/margins": 8.22961711883545,
|
792 |
-
"rewards/rejected": -15.192395210266113,
|
793 |
-
"step": 470
|
794 |
-
},
|
795 |
-
{
|
796 |
-
"epoch": 0.9963674104826155,
|
797 |
-
"grad_norm": 10.30547100028778,
|
798 |
-
"learning_rate": 2.9470303528452547e-07,
|
799 |
-
"logits/chosen": 2.291341543197632,
|
800 |
-
"logits/rejected": 4.340534687042236,
|
801 |
-
"logps/chosen": -1134.796630859375,
|
802 |
-
"logps/rejected": -2049.962890625,
|
803 |
-
"loss": 0.1409,
|
804 |
-
"rewards/accuracies": 0.925000011920929,
|
805 |
-
"rewards/chosen": -7.828709602355957,
|
806 |
-
"rewards/margins": 8.853391647338867,
|
807 |
-
"rewards/rejected": -16.68210220336914,
|
808 |
-
"step": 480
|
809 |
-
},
|
810 |
-
{
|
811 |
-
"epoch": 1.01712506486767,
|
812 |
-
"grad_norm": 15.21191565767335,
|
813 |
-
"learning_rate": 2.8574210777775755e-07,
|
814 |
-
"logits/chosen": 2.009263277053833,
|
815 |
-
"logits/rejected": 4.9940924644470215,
|
816 |
-
"logps/chosen": -1182.762939453125,
|
817 |
-
"logps/rejected": -2222.476318359375,
|
818 |
-
"loss": 0.0933,
|
819 |
-
"rewards/accuracies": 0.949999988079071,
|
820 |
-
"rewards/chosen": -8.175220489501953,
|
821 |
-
"rewards/margins": 10.224291801452637,
|
822 |
-
"rewards/rejected": -18.399513244628906,
|
823 |
-
"step": 490
|
824 |
-
},
|
825 |
-
{
|
826 |
-
"epoch": 1.0378827192527245,
|
827 |
-
"grad_norm": 15.585906686341703,
|
828 |
-
"learning_rate": 2.767340391450384e-07,
|
829 |
-
"logits/chosen": 1.0047972202301025,
|
830 |
-
"logits/rejected": 4.8316521644592285,
|
831 |
-
"logps/chosen": -1162.712646484375,
|
832 |
-
"logps/rejected": -2610.682373046875,
|
833 |
-
"loss": 0.0881,
|
834 |
-
"rewards/accuracies": 0.949999988079071,
|
835 |
-
"rewards/chosen": -7.991292476654053,
|
836 |
-
"rewards/margins": 14.244958877563477,
|
837 |
-
"rewards/rejected": -22.236251831054688,
|
838 |
-
"step": 500
|
839 |
-
},
|
840 |
-
{
|
841 |
-
"epoch": 1.0378827192527245,
|
842 |
-
"eval_logits/chosen": 1.2345364093780518,
|
843 |
-
"eval_logits/rejected": 4.526747703552246,
|
844 |
-
"eval_logps/chosen": -1257.1658935546875,
|
845 |
-
"eval_logps/rejected": -2547.474853515625,
|
846 |
-
"eval_loss": 0.15922115743160248,
|
847 |
-
"eval_rewards/accuracies": 0.9313725233078003,
|
848 |
-
"eval_rewards/chosen": -8.337576866149902,
|
849 |
-
"eval_rewards/margins": 12.677770614624023,
|
850 |
-
"eval_rewards/rejected": -21.01534652709961,
|
851 |
-
"eval_runtime": 297.9014,
|
852 |
-
"eval_samples_per_second": 21.789,
|
853 |
-
"eval_steps_per_second": 0.342,
|
854 |
-
"step": 500
|
855 |
-
},
|
856 |
-
{
|
857 |
-
"epoch": 1.058640373637779,
|
858 |
-
"grad_norm": 14.041828775113027,
|
859 |
-
"learning_rate": 2.6769071034483407e-07,
|
860 |
-
"logits/chosen": 1.5315182209014893,
|
861 |
-
"logits/rejected": 5.140109062194824,
|
862 |
-
"logps/chosen": -1049.8817138671875,
|
863 |
-
"logps/rejected": -2273.5029296875,
|
864 |
-
"loss": 0.0856,
|
865 |
-
"rewards/accuracies": 0.9750000238418579,
|
866 |
-
"rewards/chosen": -6.837597846984863,
|
867 |
-
"rewards/margins": 11.946271896362305,
|
868 |
-
"rewards/rejected": -18.783870697021484,
|
869 |
-
"step": 510
|
870 |
-
},
|
871 |
-
{
|
872 |
-
"epoch": 1.0793980280228335,
|
873 |
-
"grad_norm": 18.45189270725633,
|
874 |
-
"learning_rate": 2.5862404884109365e-07,
|
875 |
-
"logits/chosen": 1.529955267906189,
|
876 |
-
"logits/rejected": 4.867814064025879,
|
877 |
-
"logps/chosen": -1038.77001953125,
|
878 |
-
"logps/rejected": -2317.119384765625,
|
879 |
-
"loss": 0.0826,
|
880 |
-
"rewards/accuracies": 0.949999988079071,
|
881 |
-
"rewards/chosen": -6.80930233001709,
|
882 |
-
"rewards/margins": 12.373517990112305,
|
883 |
-
"rewards/rejected": -19.18282127380371,
|
884 |
-
"step": 520
|
885 |
-
},
|
886 |
-
{
|
887 |
-
"epoch": 1.100155682407888,
|
888 |
-
"grad_norm": 13.857547492254254,
|
889 |
-
"learning_rate": 2.495460128718305e-07,
|
890 |
-
"logits/chosen": 0.9307753443717957,
|
891 |
-
"logits/rejected": 4.540700435638428,
|
892 |
-
"logps/chosen": -1109.2952880859375,
|
893 |
-
"logps/rejected": -2351.9580078125,
|
894 |
-
"loss": 0.0791,
|
895 |
-
"rewards/accuracies": 0.9593750238418579,
|
896 |
-
"rewards/chosen": -7.225480556488037,
|
897 |
-
"rewards/margins": 12.243474006652832,
|
898 |
-
"rewards/rejected": -19.468952178955078,
|
899 |
-
"step": 530
|
900 |
-
},
|
901 |
-
{
|
902 |
-
"epoch": 1.1209133367929425,
|
903 |
-
"grad_norm": 17.715699549300524,
|
904 |
-
"learning_rate": 2.404685756771143e-07,
|
905 |
-
"logits/chosen": 0.9044798612594604,
|
906 |
-
"logits/rejected": 4.5168304443359375,
|
907 |
-
"logps/chosen": -1108.01416015625,
|
908 |
-
"logps/rejected": -2464.59375,
|
909 |
-
"loss": 0.0872,
|
910 |
-
"rewards/accuracies": 0.9750000238418579,
|
911 |
-
"rewards/chosen": -7.498801231384277,
|
912 |
-
"rewards/margins": 13.343009948730469,
|
913 |
-
"rewards/rejected": -20.841812133789062,
|
914 |
-
"step": 540
|
915 |
-
},
|
916 |
-
{
|
917 |
-
"epoch": 1.141670991177997,
|
918 |
-
"grad_norm": 11.817665551721014,
|
919 |
-
"learning_rate": 2.314037097072764e-07,
|
920 |
-
"logits/chosen": 1.3692632913589478,
|
921 |
-
"logits/rejected": 4.569345474243164,
|
922 |
-
"logps/chosen": -1150.0703125,
|
923 |
-
"logps/rejected": -2468.03271484375,
|
924 |
-
"loss": 0.0754,
|
925 |
-
"rewards/accuracies": 0.9750000238418579,
|
926 |
-
"rewards/chosen": -7.868742942810059,
|
927 |
-
"rewards/margins": 13.00172233581543,
|
928 |
-
"rewards/rejected": -20.870466232299805,
|
929 |
-
"step": 550
|
930 |
-
},
|
931 |
-
{
|
932 |
-
"epoch": 1.1624286455630513,
|
933 |
-
"grad_norm": 13.98618450585046,
|
934 |
-
"learning_rate": 2.2236337083215723e-07,
|
935 |
-
"logits/chosen": 1.508049488067627,
|
936 |
-
"logits/rejected": 5.1392316818237305,
|
937 |
-
"logps/chosen": -1217.515625,
|
938 |
-
"logps/rejected": -2590.57421875,
|
939 |
-
"loss": 0.0853,
|
940 |
-
"rewards/accuracies": 0.9624999761581421,
|
941 |
-
"rewards/chosen": -8.472477912902832,
|
942 |
-
"rewards/margins": 13.660308837890625,
|
943 |
-
"rewards/rejected": -22.13278579711914,
|
944 |
-
"step": 560
|
945 |
-
},
|
946 |
-
{
|
947 |
-
"epoch": 1.183186299948106,
|
948 |
-
"grad_norm": 9.239685997581025,
|
949 |
-
"learning_rate": 2.13359482572222e-07,
|
950 |
-
"logits/chosen": 0.9549428820610046,
|
951 |
-
"logits/rejected": 4.445387363433838,
|
952 |
-
"logps/chosen": -1040.99267578125,
|
953 |
-
"logps/rejected": -2247.80615234375,
|
954 |
-
"loss": 0.0847,
|
955 |
-
"rewards/accuracies": 0.9468749761581421,
|
956 |
-
"rewards/chosen": -6.785864353179932,
|
957 |
-
"rewards/margins": 11.840021133422852,
|
958 |
-
"rewards/rejected": -18.62588882446289,
|
959 |
-
"step": 570
|
960 |
-
},
|
961 |
-
{
|
962 |
-
"epoch": 1.2039439543331603,
|
963 |
-
"grad_norm": 11.315109261026508,
|
964 |
-
"learning_rate": 2.044039203723423e-07,
|
965 |
-
"logits/chosen": 0.5468926429748535,
|
966 |
-
"logits/rejected": 3.945660352706909,
|
967 |
-
"logps/chosen": -1037.985595703125,
|
968 |
-
"logps/rejected": -2178.81103515625,
|
969 |
-
"loss": 0.0889,
|
970 |
-
"rewards/accuracies": 0.953125,
|
971 |
-
"rewards/chosen": -6.750271797180176,
|
972 |
-
"rewards/margins": 11.077262878417969,
|
973 |
-
"rewards/rejected": -17.827533721923828,
|
974 |
-
"step": 580
|
975 |
-
},
|
976 |
-
{
|
977 |
-
"epoch": 1.2247016087182148,
|
978 |
-
"grad_norm": 20.88556623186479,
|
979 |
-
"learning_rate": 1.955084959389864e-07,
|
980 |
-
"logits/chosen": 1.7732290029525757,
|
981 |
-
"logits/rejected": 4.805976867675781,
|
982 |
-
"logps/chosen": -1254.5054931640625,
|
983 |
-
"logps/rejected": -2677.98974609375,
|
984 |
-
"loss": 0.0704,
|
985 |
-
"rewards/accuracies": 0.981249988079071,
|
986 |
-
"rewards/chosen": -9.03892993927002,
|
987 |
-
"rewards/margins": 13.861906051635742,
|
988 |
-
"rewards/rejected": -22.900836944580078,
|
989 |
-
"step": 590
|
990 |
-
},
|
991 |
-
{
|
992 |
-
"epoch": 1.2454592631032693,
|
993 |
-
"grad_norm": 19.615657624738002,
|
994 |
-
"learning_rate": 1.866849416614753e-07,
|
995 |
-
"logits/chosen": 1.4045512676239014,
|
996 |
-
"logits/rejected": 4.72921895980835,
|
997 |
-
"logps/chosen": -1266.108154296875,
|
998 |
-
"logps/rejected": -2709.53857421875,
|
999 |
-
"loss": 0.0774,
|
1000 |
-
"rewards/accuracies": 0.9781249761581421,
|
1001 |
-
"rewards/chosen": -8.943242073059082,
|
1002 |
-
"rewards/margins": 14.16535758972168,
|
1003 |
-
"rewards/rejected": -23.108600616455078,
|
1004 |
-
"step": 600
|
1005 |
-
},
|
1006 |
-
{
|
1007 |
-
"epoch": 1.2454592631032693,
|
1008 |
-
"eval_logits/chosen": 1.1427009105682373,
|
1009 |
-
"eval_logits/rejected": 4.037267208099365,
|
1010 |
-
"eval_logps/chosen": -1277.8565673828125,
|
1011 |
-
"eval_logps/rejected": -2513.811279296875,
|
1012 |
-
"eval_loss": 0.15603666007518768,
|
1013 |
-
"eval_rewards/accuracies": 0.9325980544090271,
|
1014 |
-
"eval_rewards/chosen": -8.544482231140137,
|
1015 |
-
"eval_rewards/margins": 12.134225845336914,
|
1016 |
-
"eval_rewards/rejected": -20.6787109375,
|
1017 |
-
"eval_runtime": 298.0443,
|
1018 |
-
"eval_samples_per_second": 21.779,
|
1019 |
-
"eval_steps_per_second": 0.342,
|
1020 |
-
"step": 600
|
1021 |
-
},
|
1022 |
-
{
|
1023 |
-
"epoch": 1.2662169174883238,
|
1024 |
-
"grad_norm": 20.13025478182326,
|
1025 |
-
"learning_rate": 1.7794489513785227e-07,
|
1026 |
-
"logits/chosen": 1.091370940208435,
|
1027 |
-
"logits/rejected": 4.404737949371338,
|
1028 |
-
"logps/chosen": -1142.038330078125,
|
1029 |
-
"logps/rejected": -2377.242919921875,
|
1030 |
-
"loss": 0.0835,
|
1031 |
-
"rewards/accuracies": 0.971875011920929,
|
1032 |
-
"rewards/chosen": -7.555553436279297,
|
1033 |
-
"rewards/margins": 12.173652648925781,
|
1034 |
-
"rewards/rejected": -19.729206085205078,
|
1035 |
-
"step": 610
|
1036 |
-
},
|
1037 |
-
{
|
1038 |
-
"epoch": 1.2869745718733783,
|
1039 |
-
"grad_norm": 10.83536532630756,
|
1040 |
-
"learning_rate": 1.692998838257744e-07,
|
1041 |
-
"logits/chosen": 1.4595911502838135,
|
1042 |
-
"logits/rejected": 4.403286457061768,
|
1043 |
-
"logps/chosen": -1153.688720703125,
|
1044 |
-
"logps/rejected": -2336.400634765625,
|
1045 |
-
"loss": 0.0792,
|
1046 |
-
"rewards/accuracies": 0.9781249761581421,
|
1047 |
-
"rewards/chosen": -7.824929714202881,
|
1048 |
-
"rewards/margins": 11.501016616821289,
|
1049 |
-
"rewards/rejected": -19.32594871520996,
|
1050 |
-
"step": 620
|
1051 |
-
},
|
1052 |
-
{
|
1053 |
-
"epoch": 1.3077322262584328,
|
1054 |
-
"grad_norm": 20.828438171756602,
|
1055 |
-
"learning_rate": 1.6076130983867191e-07,
|
1056 |
-
"logits/chosen": 1.5300322771072388,
|
1057 |
-
"logits/rejected": 4.811184883117676,
|
1058 |
-
"logps/chosen": -1134.029296875,
|
1059 |
-
"logps/rejected": -2562.76025390625,
|
1060 |
-
"loss": 0.076,
|
1061 |
-
"rewards/accuracies": 0.9750000238418579,
|
1062 |
-
"rewards/chosen": -7.6294426918029785,
|
1063 |
-
"rewards/margins": 13.96863079071045,
|
1064 |
-
"rewards/rejected": -21.59807014465332,
|
1065 |
-
"step": 630
|
1066 |
-
},
|
1067 |
-
{
|
1068 |
-
"epoch": 1.3284898806434873,
|
1069 |
-
"grad_norm": 18.16265960764559,
|
1070 |
-
"learning_rate": 1.5234043490722587e-07,
|
1071 |
-
"logits/chosen": 0.9964359402656555,
|
1072 |
-
"logits/rejected": 4.313546657562256,
|
1073 |
-
"logps/chosen": -1163.1513671875,
|
1074 |
-
"logps/rejected": -2395.21923828125,
|
1075 |
-
"loss": 0.0823,
|
1076 |
-
"rewards/accuracies": 0.956250011920929,
|
1077 |
-
"rewards/chosen": -8.007986068725586,
|
1078 |
-
"rewards/margins": 12.177099227905273,
|
1079 |
-
"rewards/rejected": -20.185087203979492,
|
1080 |
-
"step": 640
|
1081 |
-
},
|
1082 |
-
{
|
1083 |
-
"epoch": 1.3492475350285418,
|
1084 |
-
"grad_norm": 20.314345446941065,
|
1085 |
-
"learning_rate": 1.44048365526001e-07,
|
1086 |
-
"logits/chosen": 1.159566879272461,
|
1087 |
-
"logits/rejected": 4.513047695159912,
|
1088 |
-
"logps/chosen": -1154.093017578125,
|
1089 |
-
"logps/rejected": -2576.34326171875,
|
1090 |
-
"loss": 0.0833,
|
1091 |
-
"rewards/accuracies": 0.971875011920929,
|
1092 |
-
"rewards/chosen": -7.905519962310791,
|
1093 |
-
"rewards/margins": 13.832204818725586,
|
1094 |
-
"rewards/rejected": -21.73772430419922,
|
1095 |
-
"step": 650
|
1096 |
-
},
|
1097 |
-
{
|
1098 |
-
"epoch": 1.3700051894135963,
|
1099 |
-
"grad_norm": 16.284929311743372,
|
1100 |
-
"learning_rate": 1.3589603830482243e-07,
|
1101 |
-
"logits/chosen": 0.8507378697395325,
|
1102 |
-
"logits/rejected": 4.674212455749512,
|
1103 |
-
"logps/chosen": -1195.9324951171875,
|
1104 |
-
"logps/rejected": -2728.91748046875,
|
1105 |
-
"loss": 0.0711,
|
1106 |
-
"rewards/accuracies": 0.96875,
|
1107 |
-
"rewards/chosen": -8.17365550994873,
|
1108 |
-
"rewards/margins": 15.162320137023926,
|
1109 |
-
"rewards/rejected": -23.335979461669922,
|
1110 |
-
"step": 660
|
1111 |
-
},
|
1112 |
-
{
|
1113 |
-
"epoch": 1.3907628437986508,
|
1114 |
-
"grad_norm": 23.91471168720134,
|
1115 |
-
"learning_rate": 1.2789420554421821e-07,
|
1116 |
-
"logits/chosen": 0.8655555844306946,
|
1117 |
-
"logits/rejected": 4.348161220550537,
|
1118 |
-
"logps/chosen": -1252.838623046875,
|
1119 |
-
"logps/rejected": -2602.3056640625,
|
1120 |
-
"loss": 0.0839,
|
1121 |
-
"rewards/accuracies": 0.9624999761581421,
|
1122 |
-
"rewards/chosen": -8.924249649047852,
|
1123 |
-
"rewards/margins": 13.221219062805176,
|
1124 |
-
"rewards/rejected": -22.14546775817871,
|
1125 |
-
"step": 670
|
1126 |
-
},
|
1127 |
-
{
|
1128 |
-
"epoch": 1.4115204981837053,
|
1129 |
-
"grad_norm": 15.367814675454188,
|
1130 |
-
"learning_rate": 1.200534210539509e-07,
|
1131 |
-
"logits/chosen": 0.17712223529815674,
|
1132 |
-
"logits/rejected": 3.673604965209961,
|
1133 |
-
"logps/chosen": -1158.31640625,
|
1134 |
-
"logps/rejected": -2521.94482421875,
|
1135 |
-
"loss": 0.0877,
|
1136 |
-
"rewards/accuracies": 0.965624988079071,
|
1137 |
-
"rewards/chosen": -7.891541481018066,
|
1138 |
-
"rewards/margins": 13.315177917480469,
|
1139 |
-
"rewards/rejected": -21.20671844482422,
|
1140 |
-
"step": 680
|
1141 |
-
},
|
1142 |
-
{
|
1143 |
-
"epoch": 1.4322781525687598,
|
1144 |
-
"grad_norm": 22.079625577964986,
|
1145 |
-
"learning_rate": 1.1238402623334492e-07,
|
1146 |
-
"logits/chosen": 0.07270300388336182,
|
1147 |
-
"logits/rejected": 3.5430798530578613,
|
1148 |
-
"logps/chosen": -1109.5074462890625,
|
1149 |
-
"logps/rejected": -2462.455078125,
|
1150 |
-
"loss": 0.0899,
|
1151 |
-
"rewards/accuracies": 0.953125,
|
1152 |
-
"rewards/chosen": -7.3517746925354,
|
1153 |
-
"rewards/margins": 13.166239738464355,
|
1154 |
-
"rewards/rejected": -20.51801109313965,
|
1155 |
-
"step": 690
|
1156 |
-
},
|
1157 |
-
{
|
1158 |
-
"epoch": 1.4530358069538143,
|
1159 |
-
"grad_norm": 11.289239524989192,
|
1160 |
-
"learning_rate": 1.0489613643176479e-07,
|
1161 |
-
"logits/chosen": 0.2879738509654999,
|
1162 |
-
"logits/rejected": 3.8537840843200684,
|
1163 |
-
"logps/chosen": -1176.748779296875,
|
1164 |
-
"logps/rejected": -2515.61083984375,
|
1165 |
-
"loss": 0.0747,
|
1166 |
-
"rewards/accuracies": 0.9624999761581421,
|
1167 |
-
"rewards/chosen": -7.953884124755859,
|
1168 |
-
"rewards/margins": 13.24780559539795,
|
1169 |
-
"rewards/rejected": -21.20168685913086,
|
1170 |
-
"step": 700
|
1171 |
-
},
|
1172 |
-
{
|
1173 |
-
"epoch": 1.4530358069538143,
|
1174 |
-
"eval_logits/chosen": 0.4988805651664734,
|
1175 |
-
"eval_logits/rejected": 3.581174612045288,
|
1176 |
-
"eval_logps/chosen": -1308.12939453125,
|
1177 |
-
"eval_logps/rejected": -2572.467529296875,
|
1178 |
-
"eval_loss": 0.15788544714450836,
|
1179 |
-
"eval_rewards/accuracies": 0.9276960492134094,
|
1180 |
-
"eval_rewards/chosen": -8.847211837768555,
|
1181 |
-
"eval_rewards/margins": 12.418061256408691,
|
1182 |
-
"eval_rewards/rejected": -21.265270233154297,
|
1183 |
-
"eval_runtime": 296.7811,
|
1184 |
-
"eval_samples_per_second": 21.871,
|
1185 |
-
"eval_steps_per_second": 0.344,
|
1186 |
-
"step": 700
|
1187 |
-
},
|
1188 |
-
{
|
1189 |
-
"epoch": 1.4737934613388686,
|
1190 |
-
"grad_norm": 16.700822811969054,
|
1191 |
-
"learning_rate": 9.759962760723855e-08,
|
1192 |
-
"logits/chosen": 0.7035635113716125,
|
1193 |
-
"logits/rejected": 4.354310035705566,
|
1194 |
-
"logps/chosen": -1203.5103759765625,
|
1195 |
-
"logps/rejected": -2514.58154296875,
|
1196 |
-
"loss": 0.0671,
|
1197 |
-
"rewards/accuracies": 0.96875,
|
1198 |
-
"rewards/chosen": -8.514452934265137,
|
1199 |
-
"rewards/margins": 12.95274543762207,
|
1200 |
-
"rewards/rejected": -21.46719741821289,
|
1201 |
-
"step": 710
|
1202 |
-
},
|
1203 |
-
{
|
1204 |
-
"epoch": 1.4945511157239233,
|
1205 |
-
"grad_norm": 20.004128089517163,
|
1206 |
-
"learning_rate": 9.050412330081883e-08,
|
1207 |
-
"logits/chosen": 0.296795517206192,
|
1208 |
-
"logits/rejected": 4.032415390014648,
|
1209 |
-
"logps/chosen": -1271.940185546875,
|
1210 |
-
"logps/rejected": -2761.74365234375,
|
1211 |
-
"loss": 0.0861,
|
1212 |
-
"rewards/accuracies": 0.9624999761581421,
|
1213 |
-
"rewards/chosen": -8.98901653289795,
|
1214 |
-
"rewards/margins": 14.629063606262207,
|
1215 |
-
"rewards/rejected": -23.61808204650879,
|
1216 |
-
"step": 720
|
1217 |
-
},
|
1218 |
-
{
|
1219 |
-
"epoch": 1.5153087701089776,
|
1220 |
-
"grad_norm": 18.269599252001203,
|
1221 |
-
"learning_rate": 8.36189819438625e-08,
|
1222 |
-
"logits/chosen": 0.12335433810949326,
|
1223 |
-
"logits/rejected": 3.770864963531494,
|
1224 |
-
"logps/chosen": -1231.0367431640625,
|
1225 |
-
"logps/rejected": -2575.371826171875,
|
1226 |
-
"loss": 0.0842,
|
1227 |
-
"rewards/accuracies": 0.9593750238418579,
|
1228 |
-
"rewards/chosen": -8.523446083068848,
|
1229 |
-
"rewards/margins": 13.358665466308594,
|
1230 |
-
"rewards/rejected": -21.882112503051758,
|
1231 |
-
"step": 730
|
1232 |
-
},
|
1233 |
-
{
|
1234 |
-
"epoch": 1.5360664244940323,
|
1235 |
-
"grad_norm": 21.887817722932024,
|
1236 |
-
"learning_rate": 7.69532845149711e-08,
|
1237 |
-
"logits/chosen": -0.06583809852600098,
|
1238 |
-
"logits/rejected": 3.8187732696533203,
|
1239 |
-
"logps/chosen": -1204.005615234375,
|
1240 |
-
"logps/rejected": -2569.55615234375,
|
1241 |
-
"loss": 0.0791,
|
1242 |
-
"rewards/accuracies": 0.953125,
|
1243 |
-
"rewards/chosen": -8.176721572875977,
|
1244 |
-
"rewards/margins": 13.470640182495117,
|
1245 |
-
"rewards/rejected": -21.647363662719727,
|
1246 |
-
"step": 740
|
1247 |
-
},
|
1248 |
-
{
|
1249 |
-
"epoch": 1.5568240788790866,
|
1250 |
-
"grad_norm": 20.92101563028829,
|
1251 |
-
"learning_rate": 7.051582256286929e-08,
|
1252 |
-
"logits/chosen": 0.0026878931093961,
|
1253 |
-
"logits/rejected": 3.554405927658081,
|
1254 |
-
"logps/chosen": -1194.286376953125,
|
1255 |
-
"logps/rejected": -2548.453125,
|
1256 |
-
"loss": 0.0711,
|
1257 |
-
"rewards/accuracies": 0.9624999761581421,
|
1258 |
-
"rewards/chosen": -8.033935546875,
|
1259 |
-
"rewards/margins": 13.331436157226562,
|
1260 |
-
"rewards/rejected": -21.365371704101562,
|
1261 |
-
"step": 750
|
1262 |
-
},
|
1263 |
-
{
|
1264 |
-
"epoch": 1.5775817332641413,
|
1265 |
-
"grad_norm": 18.796351433954527,
|
1266 |
-
"learning_rate": 6.431508661101954e-08,
|
1267 |
-
"logits/chosen": 0.2032267153263092,
|
1268 |
-
"logits/rejected": 3.864830493927002,
|
1269 |
-
"logps/chosen": -1201.6220703125,
|
1270 |
-
"logps/rejected": -2415.40673828125,
|
1271 |
-
"loss": 0.0881,
|
1272 |
-
"rewards/accuracies": 0.956250011920929,
|
1273 |
-
"rewards/chosen": -8.291030883789062,
|
1274 |
-
"rewards/margins": 12.069987297058105,
|
1275 |
-
"rewards/rejected": -20.36101722717285,
|
1276 |
-
"step": 760
|
1277 |
-
},
|
1278 |
-
{
|
1279 |
-
"epoch": 1.5983393876491956,
|
1280 |
-
"grad_norm": 18.9865340327329,
|
1281 |
-
"learning_rate": 5.8359254959266826e-08,
|
1282 |
-
"logits/chosen": 0.17426332831382751,
|
1283 |
-
"logits/rejected": 3.7378311157226562,
|
1284 |
-
"logps/chosen": -1135.3184814453125,
|
1285 |
-
"logps/rejected": -2408.099365234375,
|
1286 |
-
"loss": 0.0744,
|
1287 |
-
"rewards/accuracies": 0.965624988079071,
|
1288 |
-
"rewards/chosen": -7.850682258605957,
|
1289 |
-
"rewards/margins": 12.461448669433594,
|
1290 |
-
"rewards/rejected": -20.312129974365234,
|
1291 |
-
"step": 770
|
1292 |
-
},
|
1293 |
-
{
|
1294 |
-
"epoch": 1.61909704203425,
|
1295 |
-
"grad_norm": 14.350034716496568,
|
1296 |
-
"learning_rate": 5.265618289728199e-08,
|
1297 |
-
"logits/chosen": 0.2724596858024597,
|
1298 |
-
"logits/rejected": 3.901758909225464,
|
1299 |
-
"logps/chosen": -1125.8365478515625,
|
1300 |
-
"logps/rejected": -2402.55029296875,
|
1301 |
-
"loss": 0.0758,
|
1302 |
-
"rewards/accuracies": 0.9624999761581421,
|
1303 |
-
"rewards/chosen": -7.693342685699463,
|
1304 |
-
"rewards/margins": 12.453673362731934,
|
1305 |
-
"rewards/rejected": -20.147018432617188,
|
1306 |
-
"step": 780
|
1307 |
-
},
|
1308 |
-
{
|
1309 |
-
"epoch": 1.6398546964193046,
|
1310 |
-
"grad_norm": 16.05161662904945,
|
1311 |
-
"learning_rate": 4.721339234403121e-08,
|
1312 |
-
"logits/chosen": 0.07050670683383942,
|
1313 |
-
"logits/rejected": 3.7205798625946045,
|
1314 |
-
"logps/chosen": -1121.5814208984375,
|
1315 |
-
"logps/rejected": -2443.16015625,
|
1316 |
-
"loss": 0.0857,
|
1317 |
-
"rewards/accuracies": 0.971875011920929,
|
1318 |
-
"rewards/chosen": -7.602121829986572,
|
1319 |
-
"rewards/margins": 12.968803405761719,
|
1320 |
-
"rewards/rejected": -20.5709228515625,
|
1321 |
-
"step": 790
|
1322 |
-
},
|
1323 |
-
{
|
1324 |
-
"epoch": 1.660612350804359,
|
1325 |
-
"grad_norm": 8.47571609534727,
|
1326 |
-
"learning_rate": 4.203806192693587e-08,
|
1327 |
-
"logits/chosen": 0.38345223665237427,
|
1328 |
-
"logits/rejected": 3.6582157611846924,
|
1329 |
-
"logps/chosen": -1135.015380859375,
|
1330 |
-
"logps/rejected": -2251.6806640625,
|
1331 |
-
"loss": 0.0811,
|
1332 |
-
"rewards/accuracies": 0.965624988079071,
|
1333 |
-
"rewards/chosen": -7.660782814025879,
|
1334 |
-
"rewards/margins": 10.944924354553223,
|
1335 |
-
"rewards/rejected": -18.6057071685791,
|
1336 |
-
"step": 800
|
1337 |
-
},
|
1338 |
-
{
|
1339 |
-
"epoch": 1.660612350804359,
|
1340 |
-
"eval_logits/chosen": 0.2172178030014038,
|
1341 |
-
"eval_logits/rejected": 3.254581928253174,
|
1342 |
-
"eval_logps/chosen": -1261.5126953125,
|
1343 |
-
"eval_logps/rejected": -2436.340576171875,
|
1344 |
-
"eval_loss": 0.15446949005126953,
|
1345 |
-
"eval_rewards/accuracies": 0.9289215803146362,
|
1346 |
-
"eval_rewards/chosen": -8.381046295166016,
|
1347 |
-
"eval_rewards/margins": 11.522958755493164,
|
1348 |
-
"eval_rewards/rejected": -19.90400505065918,
|
1349 |
-
"eval_runtime": 297.9226,
|
1350 |
-
"eval_samples_per_second": 21.788,
|
1351 |
-
"eval_steps_per_second": 0.342,
|
1352 |
-
"step": 800
|
1353 |
-
},
|
1354 |
-
{
|
1355 |
-
"epoch": 1.6813700051894136,
|
1356 |
-
"grad_norm": 11.983781457709991,
|
1357 |
-
"learning_rate": 3.7137017513808544e-08,
|
1358 |
-
"logits/chosen": 0.1190919280052185,
|
1359 |
-
"logits/rejected": 3.681546449661255,
|
1360 |
-
"logps/chosen": -1151.4061279296875,
|
1361 |
-
"logps/rejected": -2382.40966796875,
|
1362 |
-
"loss": 0.0787,
|
1363 |
-
"rewards/accuracies": 0.9593750238418579,
|
1364 |
-
"rewards/chosen": -7.798292636871338,
|
1365 |
-
"rewards/margins": 12.149864196777344,
|
1366 |
-
"rewards/rejected": -19.94815444946289,
|
1367 |
-
"step": 810
|
1368 |
-
},
|
1369 |
-
{
|
1370 |
-
"epoch": 1.702127659574468,
|
1371 |
-
"grad_norm": 15.404111765676271,
|
1372 |
-
"learning_rate": 3.251672321005147e-08,
|
1373 |
-
"logits/chosen": 0.0303075909614563,
|
1374 |
-
"logits/rejected": 3.4457364082336426,
|
1375 |
-
"logps/chosen": -1154.9154052734375,
|
1376 |
-
"logps/rejected": -2477.01220703125,
|
1377 |
-
"loss": 0.0781,
|
1378 |
-
"rewards/accuracies": 0.9750000238418579,
|
1379 |
-
"rewards/chosen": -7.82059383392334,
|
1380 |
-
"rewards/margins": 12.896100044250488,
|
1381 |
-
"rewards/rejected": -20.716693878173828,
|
1382 |
-
"step": 820
|
1383 |
-
},
|
1384 |
-
{
|
1385 |
-
"epoch": 1.7228853139595226,
|
1386 |
-
"grad_norm": 18.5892582498577,
|
1387 |
-
"learning_rate": 2.8183272832992267e-08,
|
1388 |
-
"logits/chosen": 0.05088377743959427,
|
1389 |
-
"logits/rejected": 3.3782405853271484,
|
1390 |
-
"logps/chosen": -1138.544921875,
|
1391 |
-
"logps/rejected": -2476.583984375,
|
1392 |
-
"loss": 0.0781,
|
1393 |
-
"rewards/accuracies": 0.953125,
|
1394 |
-
"rewards/chosen": -7.821805000305176,
|
1395 |
-
"rewards/margins": 13.025341987609863,
|
1396 |
-
"rewards/rejected": -20.847145080566406,
|
1397 |
-
"step": 830
|
1398 |
-
},
|
1399 |
-
{
|
1400 |
-
"epoch": 1.743642968344577,
|
1401 |
-
"grad_norm": 15.008344755715465,
|
1402 |
-
"learning_rate": 2.414238187460191e-08,
|
1403 |
-
"logits/chosen": 0.09483002126216888,
|
1404 |
-
"logits/rejected": 3.978058338165283,
|
1405 |
-
"logps/chosen": -1192.2017822265625,
|
1406 |
-
"logps/rejected": -2495.4228515625,
|
1407 |
-
"loss": 0.0809,
|
1408 |
-
"rewards/accuracies": 0.965624988079071,
|
1409 |
-
"rewards/chosen": -8.194788932800293,
|
1410 |
-
"rewards/margins": 12.927266120910645,
|
1411 |
-
"rewards/rejected": -21.122053146362305,
|
1412 |
-
"step": 840
|
1413 |
-
},
|
1414 |
-
{
|
1415 |
-
"epoch": 1.7644006227296316,
|
1416 |
-
"grad_norm": 18.202201847253505,
|
1417 |
-
"learning_rate": 2.0399379963194713e-08,
|
1418 |
-
"logits/chosen": 0.28226789832115173,
|
1419 |
-
"logits/rejected": 4.104235649108887,
|
1420 |
-
"logps/chosen": -1198.5599365234375,
|
1421 |
-
"logps/rejected": -2697.082275390625,
|
1422 |
-
"loss": 0.0726,
|
1423 |
-
"rewards/accuracies": 0.96875,
|
1424 |
-
"rewards/chosen": -8.269991874694824,
|
1425 |
-
"rewards/margins": 14.753326416015625,
|
1426 |
-
"rewards/rejected": -23.0233154296875,
|
1427 |
-
"step": 850
|
1428 |
-
},
|
1429 |
-
{
|
1430 |
-
"epoch": 1.7851582771146859,
|
1431 |
-
"grad_norm": 12.20972861300344,
|
1432 |
-
"learning_rate": 1.695920383405322e-08,
|
1433 |
-
"logits/chosen": 0.1344248354434967,
|
1434 |
-
"logits/rejected": 3.7496190071105957,
|
1435 |
-
"logps/chosen": -1236.697509765625,
|
1436 |
-
"logps/rejected": -2696.864990234375,
|
1437 |
-
"loss": 0.0834,
|
1438 |
-
"rewards/accuracies": 0.971875011920929,
|
1439 |
-
"rewards/chosen": -8.43194580078125,
|
1440 |
-
"rewards/margins": 14.396467208862305,
|
1441 |
-
"rewards/rejected": -22.828411102294922,
|
1442 |
-
"step": 860
|
1443 |
-
},
|
1444 |
-
{
|
1445 |
-
"epoch": 1.8059159314997406,
|
1446 |
-
"grad_norm": 23.070004800505263,
|
1447 |
-
"learning_rate": 1.3826390818249434e-08,
|
1448 |
-
"logits/chosen": 0.2998521625995636,
|
1449 |
-
"logits/rejected": 3.7659850120544434,
|
1450 |
-
"logps/chosen": -1205.6510009765625,
|
1451 |
-
"logps/rejected": -2611.88525390625,
|
1452 |
-
"loss": 0.0866,
|
1453 |
-
"rewards/accuracies": 0.965624988079071,
|
1454 |
-
"rewards/chosen": -8.398554801940918,
|
1455 |
-
"rewards/margins": 13.68336296081543,
|
1456 |
-
"rewards/rejected": -22.081918716430664,
|
1457 |
-
"step": 870
|
1458 |
-
},
|
1459 |
-
{
|
1460 |
-
"epoch": 1.826673585884795,
|
1461 |
-
"grad_norm": 12.610473638421219,
|
1462 |
-
"learning_rate": 1.1005072858249614e-08,
|
1463 |
-
"logits/chosen": 0.12997238337993622,
|
1464 |
-
"logits/rejected": 3.8439629077911377,
|
1465 |
-
"logps/chosen": -1214.625,
|
1466 |
-
"logps/rejected": -2609.048583984375,
|
1467 |
-
"loss": 0.0713,
|
1468 |
-
"rewards/accuracies": 0.9750000238418579,
|
1469 |
-
"rewards/chosen": -8.35765266418457,
|
1470 |
-
"rewards/margins": 13.758280754089355,
|
1471 |
-
"rewards/rejected": -22.11593246459961,
|
1472 |
-
"step": 880
|
1473 |
-
},
|
1474 |
-
{
|
1475 |
-
"epoch": 1.8474312402698496,
|
1476 |
-
"grad_norm": 17.876398721018592,
|
1477 |
-
"learning_rate": 8.498971058195886e-09,
|
1478 |
-
"logits/chosen": 0.18721507489681244,
|
1479 |
-
"logits/rejected": 3.927520275115967,
|
1480 |
-
"logps/chosen": -1229.69482421875,
|
1481 |
-
"logps/rejected": -2654.132568359375,
|
1482 |
-
"loss": 0.0685,
|
1483 |
-
"rewards/accuracies": 0.9750000238418579,
|
1484 |
-
"rewards/chosen": -8.53508472442627,
|
1485 |
-
"rewards/margins": 14.071182250976562,
|
1486 |
-
"rewards/rejected": -22.606266021728516,
|
1487 |
-
"step": 890
|
1488 |
-
},
|
1489 |
-
{
|
1490 |
-
"epoch": 1.868188894654904,
|
1491 |
-
"grad_norm": 16.34958614861239,
|
1492 |
-
"learning_rate": 6.311390776052527e-09,
|
1493 |
-
"logits/chosen": 0.20388635993003845,
|
1494 |
-
"logits/rejected": 3.8464550971984863,
|
1495 |
-
"logps/chosen": -1190.66064453125,
|
1496 |
-
"logps/rejected": -2582.68212890625,
|
1497 |
-
"loss": 0.069,
|
1498 |
-
"rewards/accuracies": 0.953125,
|
1499 |
-
"rewards/chosen": -8.267062187194824,
|
1500 |
-
"rewards/margins": 13.608221054077148,
|
1501 |
-
"rewards/rejected": -21.87528419494629,
|
1502 |
-
"step": 900
|
1503 |
-
},
|
1504 |
-
{
|
1505 |
-
"epoch": 1.868188894654904,
|
1506 |
-
"eval_logits/chosen": 0.2562587261199951,
|
1507 |
-
"eval_logits/rejected": 3.369171380996704,
|
1508 |
-
"eval_logps/chosen": -1345.178955078125,
|
1509 |
-
"eval_logps/rejected": -2644.793701171875,
|
1510 |
-
"eval_loss": 0.1591682732105255,
|
1511 |
-
"eval_rewards/accuracies": 0.9325980544090271,
|
1512 |
-
"eval_rewards/chosen": -9.217706680297852,
|
1513 |
-
"eval_rewards/margins": 12.770830154418945,
|
1514 |
-
"eval_rewards/rejected": -21.988536834716797,
|
1515 |
-
"eval_runtime": 297.6019,
|
1516 |
-
"eval_samples_per_second": 21.811,
|
1517 |
-
"eval_steps_per_second": 0.343,
|
1518 |
-
"step": 900
|
1519 |
-
},
|
1520 |
-
{
|
1521 |
-
"epoch": 1.8889465490399586,
|
1522 |
-
"grad_norm": 17.144158000944817,
|
1523 |
-
"learning_rate": 4.445217264089751e-09,
|
1524 |
-
"logits/chosen": 0.10267569869756699,
|
1525 |
-
"logits/rejected": 4.0425705909729,
|
1526 |
-
"logps/chosen": -1188.369873046875,
|
1527 |
-
"logps/rejected": -2630.327392578125,
|
1528 |
-
"loss": 0.0659,
|
1529 |
-
"rewards/accuracies": 0.971875011920929,
|
1530 |
-
"rewards/chosen": -8.262983322143555,
|
1531 |
-
"rewards/margins": 14.21807861328125,
|
1532 |
-
"rewards/rejected": -22.481060028076172,
|
1533 |
-
"step": 910
|
1534 |
-
},
|
1535 |
-
{
|
1536 |
-
"epoch": 1.909704203425013,
|
1537 |
-
"grad_norm": 16.781554983940616,
|
1538 |
-
"learning_rate": 2.902911863455121e-09,
|
1539 |
-
"logits/chosen": 0.2743522524833679,
|
1540 |
-
"logits/rejected": 4.136692047119141,
|
1541 |
-
"logps/chosen": -1213.719970703125,
|
1542 |
-
"logps/rejected": -2728.411376953125,
|
1543 |
-
"loss": 0.0767,
|
1544 |
-
"rewards/accuracies": 0.9750000238418579,
|
1545 |
-
"rewards/chosen": -8.522599220275879,
|
1546 |
-
"rewards/margins": 14.904146194458008,
|
1547 |
-
"rewards/rejected": -23.42674446105957,
|
1548 |
-
"step": 920
|
1549 |
-
},
|
1550 |
-
{
|
1551 |
-
"epoch": 1.9304618578100676,
|
1552 |
-
"grad_norm": 23.227111674511338,
|
1553 |
-
"learning_rate": 1.686508757851507e-09,
|
1554 |
-
"logits/chosen": 0.2027033567428589,
|
1555 |
-
"logits/rejected": 3.8271079063415527,
|
1556 |
-
"logps/chosen": -1229.591796875,
|
1557 |
-
"logps/rejected": -2668.19970703125,
|
1558 |
-
"loss": 0.0872,
|
1559 |
-
"rewards/accuracies": 0.965624988079071,
|
1560 |
-
"rewards/chosen": -8.599322319030762,
|
1561 |
-
"rewards/margins": 14.134483337402344,
|
1562 |
-
"rewards/rejected": -22.733806610107422,
|
1563 |
-
"step": 930
|
1564 |
-
},
|
1565 |
-
{
|
1566 |
-
"epoch": 1.951219512195122,
|
1567 |
-
"grad_norm": 22.90252956159655,
|
1568 |
-
"learning_rate": 7.976122906031557e-10,
|
1569 |
-
"logits/chosen": 0.30234938859939575,
|
1570 |
-
"logits/rejected": 3.9263412952423096,
|
1571 |
-
"logps/chosen": -1212.529541015625,
|
1572 |
-
"logps/rejected": -2572.277587890625,
|
1573 |
-
"loss": 0.087,
|
1574 |
-
"rewards/accuracies": 0.9593750238418579,
|
1575 |
-
"rewards/chosen": -8.438420295715332,
|
1576 |
-
"rewards/margins": 13.364117622375488,
|
1577 |
-
"rewards/rejected": -21.802536010742188,
|
1578 |
-
"step": 940
|
1579 |
-
},
|
1580 |
-
{
|
1581 |
-
"epoch": 1.9719771665801764,
|
1582 |
-
"grad_norm": 17.95357887786745,
|
1583 |
-
"learning_rate": 2.37394848648792e-10,
|
1584 |
-
"logits/chosen": 0.09388472139835358,
|
1585 |
-
"logits/rejected": 3.5805296897888184,
|
1586 |
-
"logps/chosen": -1182.0406494140625,
|
1587 |
-
"logps/rejected": -2537.778564453125,
|
1588 |
-
"loss": 0.0821,
|
1589 |
-
"rewards/accuracies": 0.956250011920929,
|
1590 |
-
"rewards/chosen": -8.203265190124512,
|
1591 |
-
"rewards/margins": 13.360048294067383,
|
1592 |
-
"rewards/rejected": -21.56331443786621,
|
1593 |
-
"step": 950
|
1594 |
-
},
|
1595 |
-
{
|
1596 |
-
"epoch": 1.992734820965231,
|
1597 |
-
"grad_norm": 18.37972352009023,
|
1598 |
-
"learning_rate": 6.5953162521614755e-12,
|
1599 |
-
"logits/chosen": 0.16293412446975708,
|
1600 |
-
"logits/rejected": 3.703944444656372,
|
1601 |
-
"logps/chosen": -1242.895751953125,
|
1602 |
-
"logps/rejected": -2706.61279296875,
|
1603 |
-
"loss": 0.0738,
|
1604 |
-
"rewards/accuracies": 0.981249988079071,
|
1605 |
-
"rewards/chosen": -8.82257080078125,
|
1606 |
-
"rewards/margins": 14.438652038574219,
|
1607 |
-
"rewards/rejected": -23.261220932006836,
|
1608 |
-
"step": 960
|
1609 |
-
},
|
1610 |
-
{
|
1611 |
-
"epoch": 1.996886351842242,
|
1612 |
-
"step": 962,
|
1613 |
"total_flos": 0.0,
|
1614 |
-
"train_loss": 0.
|
1615 |
-
"train_runtime":
|
1616 |
-
"train_samples_per_second":
|
1617 |
-
"train_steps_per_second": 0.
|
1618 |
}
|
1619 |
],
|
1620 |
"logging_steps": 10,
|
1621 |
-
"max_steps":
|
1622 |
"num_input_tokens_seen": 0,
|
1623 |
"num_train_epochs": 2,
|
1624 |
-
"save_steps":
|
1625 |
"stateful_callbacks": {
|
1626 |
"TrainerControl": {
|
1627 |
"args": {
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 240,
|
6 |
+
"global_step": 2,
|
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": 5e-07,
|
14 |
+
"logits/chosen": -2.766833543777466,
|
15 |
+
"logits/rejected": -2.7548677921295166,
|
16 |
+
"logps/chosen": -492.5103759765625,
|
17 |
+
"logps/rejected": -501.75994873046875,
|
18 |
+
"loss": 0.1733,
|
|
|
19 |
"rewards/accuracies": 0.0,
|
20 |
"rewards/chosen": 0.0,
|
21 |
"rewards/margins": 0.0,
|
|
|
23 |
"step": 1
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"step": 2,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
"total_flos": 0.0,
|
29 |
+
"train_loss": 0.1732867956161499,
|
30 |
+
"train_runtime": 97.0028,
|
31 |
+
"train_samples_per_second": 1.031,
|
32 |
+
"train_steps_per_second": 0.021
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 10,
|
36 |
+
"max_steps": 2,
|
37 |
"num_input_tokens_seen": 0,
|
38 |
"num_train_epochs": 2,
|
39 |
+
"save_steps": 240,
|
40 |
"stateful_callbacks": {
|
41 |
"TrainerControl": {
|
42 |
"args": {
|