sedrickkeh
commited on
Commit
•
9f3bb40
1
Parent(s):
27a3ee9
End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +983 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
4 |
base_model: Qwen/Qwen2.5-7B
|
5 |
tags:
|
6 |
- llama-factory
|
|
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: hp_ablations_qwen_adambeta1_0.95
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# hp_ablations_qwen_adambeta1_0.95
|
17 |
|
18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.6188
|
21 |
|
|
|
4 |
base_model: Qwen/Qwen2.5-7B
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
+
- full
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: hp_ablations_qwen_adambeta1_0.95
|
|
|
16 |
|
17 |
# hp_ablations_qwen_adambeta1_0.95
|
18 |
|
19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.6188
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.996011396011396,
|
3 |
+
"eval_loss": 0.6188442707061768,
|
4 |
+
"eval_runtime": 448.4128,
|
5 |
+
"eval_samples_per_second": 26.366,
|
6 |
+
"eval_steps_per_second": 0.413,
|
7 |
+
"total_flos": 2755219238682624.0,
|
8 |
+
"train_loss": 0.6039808779909549,
|
9 |
+
"train_runtime": 71394.4326,
|
10 |
+
"train_samples_per_second": 9.439,
|
11 |
+
"train_steps_per_second": 0.018
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.996011396011396,
|
3 |
+
"eval_loss": 0.6188442707061768,
|
4 |
+
"eval_runtime": 448.4128,
|
5 |
+
"eval_samples_per_second": 26.366,
|
6 |
+
"eval_steps_per_second": 0.413
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.996011396011396,
|
3 |
+
"total_flos": 2755219238682624.0,
|
4 |
+
"train_loss": 0.6039808779909549,
|
5 |
+
"train_runtime": 71394.4326,
|
6 |
+
"train_samples_per_second": 9.439,
|
7 |
+
"train_steps_per_second": 0.018
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,983 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.996011396011396,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1314,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.022792022792022793,
|
13 |
+
"grad_norm": 1.4386693012758085,
|
14 |
+
"learning_rate": 5e-06,
|
15 |
+
"loss": 0.7579,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.045584045584045586,
|
20 |
+
"grad_norm": 0.8867158367707256,
|
21 |
+
"learning_rate": 5e-06,
|
22 |
+
"loss": 0.7029,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06837606837606838,
|
27 |
+
"grad_norm": 0.9488403053522199,
|
28 |
+
"learning_rate": 5e-06,
|
29 |
+
"loss": 0.6832,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.09116809116809117,
|
34 |
+
"grad_norm": 0.884176264535841,
|
35 |
+
"learning_rate": 5e-06,
|
36 |
+
"loss": 0.6835,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.11396011396011396,
|
41 |
+
"grad_norm": 0.8397561690644878,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 0.6797,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.13675213675213677,
|
48 |
+
"grad_norm": 0.7606997383385686,
|
49 |
+
"learning_rate": 5e-06,
|
50 |
+
"loss": 0.6592,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.15954415954415954,
|
55 |
+
"grad_norm": 0.5641772966117866,
|
56 |
+
"learning_rate": 5e-06,
|
57 |
+
"loss": 0.6555,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.18233618233618235,
|
62 |
+
"grad_norm": 0.4455570943818377,
|
63 |
+
"learning_rate": 5e-06,
|
64 |
+
"loss": 0.6573,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.20512820512820512,
|
69 |
+
"grad_norm": 0.35344748753637006,
|
70 |
+
"learning_rate": 5e-06,
|
71 |
+
"loss": 0.641,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.22792022792022792,
|
76 |
+
"grad_norm": 0.3194926627231166,
|
77 |
+
"learning_rate": 5e-06,
|
78 |
+
"loss": 0.6419,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.25071225071225073,
|
83 |
+
"grad_norm": 0.327073140109101,
|
84 |
+
"learning_rate": 5e-06,
|
85 |
+
"loss": 0.6329,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.27350427350427353,
|
90 |
+
"grad_norm": 0.2902488319100315,
|
91 |
+
"learning_rate": 5e-06,
|
92 |
+
"loss": 0.641,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.2962962962962963,
|
97 |
+
"grad_norm": 0.3250030845224132,
|
98 |
+
"learning_rate": 5e-06,
|
99 |
+
"loss": 0.642,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.3190883190883191,
|
104 |
+
"grad_norm": 0.301467717572835,
|
105 |
+
"learning_rate": 5e-06,
|
106 |
+
"loss": 0.644,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.3418803418803419,
|
111 |
+
"grad_norm": 0.3335273058944758,
|
112 |
+
"learning_rate": 5e-06,
|
113 |
+
"loss": 0.6365,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.3646723646723647,
|
118 |
+
"grad_norm": 0.3296991550356145,
|
119 |
+
"learning_rate": 5e-06,
|
120 |
+
"loss": 0.6417,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.38746438746438744,
|
125 |
+
"grad_norm": 0.3103731635734424,
|
126 |
+
"learning_rate": 5e-06,
|
127 |
+
"loss": 0.6334,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.41025641025641024,
|
132 |
+
"grad_norm": 0.29665465750244296,
|
133 |
+
"learning_rate": 5e-06,
|
134 |
+
"loss": 0.639,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.43304843304843305,
|
139 |
+
"grad_norm": 0.3060805101577135,
|
140 |
+
"learning_rate": 5e-06,
|
141 |
+
"loss": 0.6316,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.45584045584045585,
|
146 |
+
"grad_norm": 0.2969598209435155,
|
147 |
+
"learning_rate": 5e-06,
|
148 |
+
"loss": 0.6396,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.47863247863247865,
|
153 |
+
"grad_norm": 0.30839851830912446,
|
154 |
+
"learning_rate": 5e-06,
|
155 |
+
"loss": 0.6359,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5014245014245015,
|
160 |
+
"grad_norm": 0.3053987642580341,
|
161 |
+
"learning_rate": 5e-06,
|
162 |
+
"loss": 0.6396,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5242165242165242,
|
167 |
+
"grad_norm": 0.3348094885478149,
|
168 |
+
"learning_rate": 5e-06,
|
169 |
+
"loss": 0.6352,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.5470085470085471,
|
174 |
+
"grad_norm": 0.2950949465171189,
|
175 |
+
"learning_rate": 5e-06,
|
176 |
+
"loss": 0.631,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.5698005698005698,
|
181 |
+
"grad_norm": 0.3225072083038658,
|
182 |
+
"learning_rate": 5e-06,
|
183 |
+
"loss": 0.636,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.5925925925925926,
|
188 |
+
"grad_norm": 0.33126618150169374,
|
189 |
+
"learning_rate": 5e-06,
|
190 |
+
"loss": 0.6342,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.6153846153846154,
|
195 |
+
"grad_norm": 0.3123676307295024,
|
196 |
+
"learning_rate": 5e-06,
|
197 |
+
"loss": 0.6314,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.6381766381766382,
|
202 |
+
"grad_norm": 0.31608075186025725,
|
203 |
+
"learning_rate": 5e-06,
|
204 |
+
"loss": 0.6422,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.6609686609686609,
|
209 |
+
"grad_norm": 0.295304591634291,
|
210 |
+
"learning_rate": 5e-06,
|
211 |
+
"loss": 0.6308,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.6837606837606838,
|
216 |
+
"grad_norm": 0.2889796046509888,
|
217 |
+
"learning_rate": 5e-06,
|
218 |
+
"loss": 0.6289,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7065527065527065,
|
223 |
+
"grad_norm": 0.2828279092197474,
|
224 |
+
"learning_rate": 5e-06,
|
225 |
+
"loss": 0.6287,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.7293447293447294,
|
230 |
+
"grad_norm": 0.3123856218189676,
|
231 |
+
"learning_rate": 5e-06,
|
232 |
+
"loss": 0.6293,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.7521367521367521,
|
237 |
+
"grad_norm": 0.3053322180872748,
|
238 |
+
"learning_rate": 5e-06,
|
239 |
+
"loss": 0.6259,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.7749287749287749,
|
244 |
+
"grad_norm": 0.2926207509847771,
|
245 |
+
"learning_rate": 5e-06,
|
246 |
+
"loss": 0.6317,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.7977207977207977,
|
251 |
+
"grad_norm": 0.29988955618078283,
|
252 |
+
"learning_rate": 5e-06,
|
253 |
+
"loss": 0.6388,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.8205128205128205,
|
258 |
+
"grad_norm": 0.3048877888264376,
|
259 |
+
"learning_rate": 5e-06,
|
260 |
+
"loss": 0.6306,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.8433048433048433,
|
265 |
+
"grad_norm": 0.34334690821050184,
|
266 |
+
"learning_rate": 5e-06,
|
267 |
+
"loss": 0.6243,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.8660968660968661,
|
272 |
+
"grad_norm": 0.3134188238075275,
|
273 |
+
"learning_rate": 5e-06,
|
274 |
+
"loss": 0.6365,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.8888888888888888,
|
279 |
+
"grad_norm": 0.30566485805979765,
|
280 |
+
"learning_rate": 5e-06,
|
281 |
+
"loss": 0.6351,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.9116809116809117,
|
286 |
+
"grad_norm": 0.31666519162979606,
|
287 |
+
"learning_rate": 5e-06,
|
288 |
+
"loss": 0.6384,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.9344729344729344,
|
293 |
+
"grad_norm": 0.2794015692940556,
|
294 |
+
"learning_rate": 5e-06,
|
295 |
+
"loss": 0.6346,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.9572649572649573,
|
300 |
+
"grad_norm": 0.3050489727811934,
|
301 |
+
"learning_rate": 5e-06,
|
302 |
+
"loss": 0.6215,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.98005698005698,
|
307 |
+
"grad_norm": 0.34520329516921633,
|
308 |
+
"learning_rate": 5e-06,
|
309 |
+
"loss": 0.6346,
|
310 |
+
"step": 430
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.9982905982905983,
|
314 |
+
"eval_loss": 0.6251624226570129,
|
315 |
+
"eval_runtime": 445.1376,
|
316 |
+
"eval_samples_per_second": 26.56,
|
317 |
+
"eval_steps_per_second": 0.416,
|
318 |
+
"step": 438
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 1.0034188034188034,
|
322 |
+
"grad_norm": 0.3500234102689406,
|
323 |
+
"learning_rate": 5e-06,
|
324 |
+
"loss": 0.6473,
|
325 |
+
"step": 440
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 1.0262108262108263,
|
329 |
+
"grad_norm": 0.3135823115202442,
|
330 |
+
"learning_rate": 5e-06,
|
331 |
+
"loss": 0.602,
|
332 |
+
"step": 450
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.049002849002849,
|
336 |
+
"grad_norm": 0.32895439127731363,
|
337 |
+
"learning_rate": 5e-06,
|
338 |
+
"loss": 0.5954,
|
339 |
+
"step": 460
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.0717948717948718,
|
343 |
+
"grad_norm": 0.2980741864148205,
|
344 |
+
"learning_rate": 5e-06,
|
345 |
+
"loss": 0.5961,
|
346 |
+
"step": 470
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.0945868945868946,
|
350 |
+
"grad_norm": 0.3005539750743244,
|
351 |
+
"learning_rate": 5e-06,
|
352 |
+
"loss": 0.6035,
|
353 |
+
"step": 480
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.1173789173789175,
|
357 |
+
"grad_norm": 0.3193329083839523,
|
358 |
+
"learning_rate": 5e-06,
|
359 |
+
"loss": 0.6084,
|
360 |
+
"step": 490
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.1401709401709401,
|
364 |
+
"grad_norm": 0.2971789146327925,
|
365 |
+
"learning_rate": 5e-06,
|
366 |
+
"loss": 0.5983,
|
367 |
+
"step": 500
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.162962962962963,
|
371 |
+
"grad_norm": 0.3014133236150067,
|
372 |
+
"learning_rate": 5e-06,
|
373 |
+
"loss": 0.5961,
|
374 |
+
"step": 510
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.1857549857549858,
|
378 |
+
"grad_norm": 0.31061311315632684,
|
379 |
+
"learning_rate": 5e-06,
|
380 |
+
"loss": 0.6018,
|
381 |
+
"step": 520
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.2085470085470085,
|
385 |
+
"grad_norm": 0.3030494386702636,
|
386 |
+
"learning_rate": 5e-06,
|
387 |
+
"loss": 0.5948,
|
388 |
+
"step": 530
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.2313390313390313,
|
392 |
+
"grad_norm": 0.32399832658742117,
|
393 |
+
"learning_rate": 5e-06,
|
394 |
+
"loss": 0.6051,
|
395 |
+
"step": 540
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.2541310541310542,
|
399 |
+
"grad_norm": 0.28839198489010404,
|
400 |
+
"learning_rate": 5e-06,
|
401 |
+
"loss": 0.6017,
|
402 |
+
"step": 550
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.2769230769230768,
|
406 |
+
"grad_norm": 0.2964653938206201,
|
407 |
+
"learning_rate": 5e-06,
|
408 |
+
"loss": 0.6032,
|
409 |
+
"step": 560
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.2997150997150997,
|
413 |
+
"grad_norm": 0.28722558037585133,
|
414 |
+
"learning_rate": 5e-06,
|
415 |
+
"loss": 0.5973,
|
416 |
+
"step": 570
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.3225071225071225,
|
420 |
+
"grad_norm": 0.2923968412756558,
|
421 |
+
"learning_rate": 5e-06,
|
422 |
+
"loss": 0.5958,
|
423 |
+
"step": 580
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.3452991452991454,
|
427 |
+
"grad_norm": 0.28753838300402135,
|
428 |
+
"learning_rate": 5e-06,
|
429 |
+
"loss": 0.5955,
|
430 |
+
"step": 590
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.368091168091168,
|
434 |
+
"grad_norm": 0.3334994604865794,
|
435 |
+
"learning_rate": 5e-06,
|
436 |
+
"loss": 0.6011,
|
437 |
+
"step": 600
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.390883190883191,
|
441 |
+
"grad_norm": 0.2991486931963729,
|
442 |
+
"learning_rate": 5e-06,
|
443 |
+
"loss": 0.6012,
|
444 |
+
"step": 610
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.4136752136752135,
|
448 |
+
"grad_norm": 0.3073110980633579,
|
449 |
+
"learning_rate": 5e-06,
|
450 |
+
"loss": 0.6037,
|
451 |
+
"step": 620
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.4364672364672364,
|
455 |
+
"grad_norm": 0.3100450193104537,
|
456 |
+
"learning_rate": 5e-06,
|
457 |
+
"loss": 0.6018,
|
458 |
+
"step": 630
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.4592592592592593,
|
462 |
+
"grad_norm": 0.3055297206364041,
|
463 |
+
"learning_rate": 5e-06,
|
464 |
+
"loss": 0.5966,
|
465 |
+
"step": 640
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.4820512820512821,
|
469 |
+
"grad_norm": 0.3029784972136167,
|
470 |
+
"learning_rate": 5e-06,
|
471 |
+
"loss": 0.5946,
|
472 |
+
"step": 650
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.504843304843305,
|
476 |
+
"grad_norm": 0.2834424411606447,
|
477 |
+
"learning_rate": 5e-06,
|
478 |
+
"loss": 0.5942,
|
479 |
+
"step": 660
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.5276353276353276,
|
483 |
+
"grad_norm": 0.3194897462541008,
|
484 |
+
"learning_rate": 5e-06,
|
485 |
+
"loss": 0.6019,
|
486 |
+
"step": 670
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.5504273504273505,
|
490 |
+
"grad_norm": 0.29190992841354146,
|
491 |
+
"learning_rate": 5e-06,
|
492 |
+
"loss": 0.5904,
|
493 |
+
"step": 680
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 1.573219373219373,
|
497 |
+
"grad_norm": 0.31705729350194956,
|
498 |
+
"learning_rate": 5e-06,
|
499 |
+
"loss": 0.5944,
|
500 |
+
"step": 690
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.596011396011396,
|
504 |
+
"grad_norm": 0.29252625572912966,
|
505 |
+
"learning_rate": 5e-06,
|
506 |
+
"loss": 0.61,
|
507 |
+
"step": 700
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.6188034188034188,
|
511 |
+
"grad_norm": 0.31234731377862573,
|
512 |
+
"learning_rate": 5e-06,
|
513 |
+
"loss": 0.597,
|
514 |
+
"step": 710
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.6415954415954417,
|
518 |
+
"grad_norm": 0.3160189008473381,
|
519 |
+
"learning_rate": 5e-06,
|
520 |
+
"loss": 0.6016,
|
521 |
+
"step": 720
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.6643874643874645,
|
525 |
+
"grad_norm": 0.29544177148306744,
|
526 |
+
"learning_rate": 5e-06,
|
527 |
+
"loss": 0.5947,
|
528 |
+
"step": 730
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 1.6871794871794872,
|
532 |
+
"grad_norm": 0.30708751751912383,
|
533 |
+
"learning_rate": 5e-06,
|
534 |
+
"loss": 0.5957,
|
535 |
+
"step": 740
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 1.7099715099715098,
|
539 |
+
"grad_norm": 0.3048638695052697,
|
540 |
+
"learning_rate": 5e-06,
|
541 |
+
"loss": 0.5932,
|
542 |
+
"step": 750
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.7327635327635327,
|
546 |
+
"grad_norm": 0.3146316081703229,
|
547 |
+
"learning_rate": 5e-06,
|
548 |
+
"loss": 0.5971,
|
549 |
+
"step": 760
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 1.7555555555555555,
|
553 |
+
"grad_norm": 0.32002761544313474,
|
554 |
+
"learning_rate": 5e-06,
|
555 |
+
"loss": 0.5935,
|
556 |
+
"step": 770
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.7783475783475784,
|
560 |
+
"grad_norm": 0.30010567894497364,
|
561 |
+
"learning_rate": 5e-06,
|
562 |
+
"loss": 0.6007,
|
563 |
+
"step": 780
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.8011396011396013,
|
567 |
+
"grad_norm": 0.28285672159123876,
|
568 |
+
"learning_rate": 5e-06,
|
569 |
+
"loss": 0.5982,
|
570 |
+
"step": 790
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 1.823931623931624,
|
574 |
+
"grad_norm": 0.28611836059295176,
|
575 |
+
"learning_rate": 5e-06,
|
576 |
+
"loss": 0.5851,
|
577 |
+
"step": 800
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 1.8467236467236468,
|
581 |
+
"grad_norm": 0.30797592386487205,
|
582 |
+
"learning_rate": 5e-06,
|
583 |
+
"loss": 0.5929,
|
584 |
+
"step": 810
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.8695156695156694,
|
588 |
+
"grad_norm": 0.3063321918111546,
|
589 |
+
"learning_rate": 5e-06,
|
590 |
+
"loss": 0.5906,
|
591 |
+
"step": 820
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 1.8923076923076922,
|
595 |
+
"grad_norm": 0.30525107848276234,
|
596 |
+
"learning_rate": 5e-06,
|
597 |
+
"loss": 0.5945,
|
598 |
+
"step": 830
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.915099715099715,
|
602 |
+
"grad_norm": 0.29791867679830153,
|
603 |
+
"learning_rate": 5e-06,
|
604 |
+
"loss": 0.599,
|
605 |
+
"step": 840
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 1.937891737891738,
|
609 |
+
"grad_norm": 0.29637691821376655,
|
610 |
+
"learning_rate": 5e-06,
|
611 |
+
"loss": 0.5971,
|
612 |
+
"step": 850
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 1.9606837606837608,
|
616 |
+
"grad_norm": 0.30625195405550415,
|
617 |
+
"learning_rate": 5e-06,
|
618 |
+
"loss": 0.5983,
|
619 |
+
"step": 860
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 1.9834757834757835,
|
623 |
+
"grad_norm": 0.33176229383034617,
|
624 |
+
"learning_rate": 5e-06,
|
625 |
+
"loss": 0.5958,
|
626 |
+
"step": 870
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 1.9994301994301993,
|
630 |
+
"eval_loss": 0.618757426738739,
|
631 |
+
"eval_runtime": 445.8741,
|
632 |
+
"eval_samples_per_second": 26.516,
|
633 |
+
"eval_steps_per_second": 0.415,
|
634 |
+
"step": 877
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 2.006837606837607,
|
638 |
+
"grad_norm": 0.2936199686212669,
|
639 |
+
"learning_rate": 5e-06,
|
640 |
+
"loss": 0.6152,
|
641 |
+
"step": 880
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 2.0296296296296297,
|
645 |
+
"grad_norm": 0.32905123086930277,
|
646 |
+
"learning_rate": 5e-06,
|
647 |
+
"loss": 0.5547,
|
648 |
+
"step": 890
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 2.0524216524216525,
|
652 |
+
"grad_norm": 0.31597772907288135,
|
653 |
+
"learning_rate": 5e-06,
|
654 |
+
"loss": 0.5696,
|
655 |
+
"step": 900
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 2.0752136752136754,
|
659 |
+
"grad_norm": 0.3150594692282521,
|
660 |
+
"learning_rate": 5e-06,
|
661 |
+
"loss": 0.5676,
|
662 |
+
"step": 910
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.098005698005698,
|
666 |
+
"grad_norm": 0.3072197547874636,
|
667 |
+
"learning_rate": 5e-06,
|
668 |
+
"loss": 0.5706,
|
669 |
+
"step": 920
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 2.1207977207977207,
|
673 |
+
"grad_norm": 0.30005346574771413,
|
674 |
+
"learning_rate": 5e-06,
|
675 |
+
"loss": 0.5685,
|
676 |
+
"step": 930
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 2.1435897435897435,
|
680 |
+
"grad_norm": 0.3017795274737325,
|
681 |
+
"learning_rate": 5e-06,
|
682 |
+
"loss": 0.5632,
|
683 |
+
"step": 940
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 2.1663817663817664,
|
687 |
+
"grad_norm": 0.30206580494490604,
|
688 |
+
"learning_rate": 5e-06,
|
689 |
+
"loss": 0.5641,
|
690 |
+
"step": 950
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.1891737891737892,
|
694 |
+
"grad_norm": 0.2980530215049522,
|
695 |
+
"learning_rate": 5e-06,
|
696 |
+
"loss": 0.5691,
|
697 |
+
"step": 960
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 2.211965811965812,
|
701 |
+
"grad_norm": 0.31524358050102935,
|
702 |
+
"learning_rate": 5e-06,
|
703 |
+
"loss": 0.5686,
|
704 |
+
"step": 970
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.234757834757835,
|
708 |
+
"grad_norm": 0.3128509983082201,
|
709 |
+
"learning_rate": 5e-06,
|
710 |
+
"loss": 0.5583,
|
711 |
+
"step": 980
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 2.2575498575498574,
|
715 |
+
"grad_norm": 0.3140793309951936,
|
716 |
+
"learning_rate": 5e-06,
|
717 |
+
"loss": 0.5673,
|
718 |
+
"step": 990
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 2.2803418803418802,
|
722 |
+
"grad_norm": 0.28520834084454944,
|
723 |
+
"learning_rate": 5e-06,
|
724 |
+
"loss": 0.5676,
|
725 |
+
"step": 1000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 2.303133903133903,
|
729 |
+
"grad_norm": 0.29867824686812755,
|
730 |
+
"learning_rate": 5e-06,
|
731 |
+
"loss": 0.565,
|
732 |
+
"step": 1010
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.325925925925926,
|
736 |
+
"grad_norm": 0.3145208805177942,
|
737 |
+
"learning_rate": 5e-06,
|
738 |
+
"loss": 0.5682,
|
739 |
+
"step": 1020
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 2.348717948717949,
|
743 |
+
"grad_norm": 0.2902492701764916,
|
744 |
+
"learning_rate": 5e-06,
|
745 |
+
"loss": 0.5694,
|
746 |
+
"step": 1030
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 2.3715099715099717,
|
750 |
+
"grad_norm": 0.2956594814241214,
|
751 |
+
"learning_rate": 5e-06,
|
752 |
+
"loss": 0.5674,
|
753 |
+
"step": 1040
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 2.394301994301994,
|
757 |
+
"grad_norm": 0.31738434358751366,
|
758 |
+
"learning_rate": 5e-06,
|
759 |
+
"loss": 0.5668,
|
760 |
+
"step": 1050
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 2.417094017094017,
|
764 |
+
"grad_norm": 0.28908242561794056,
|
765 |
+
"learning_rate": 5e-06,
|
766 |
+
"loss": 0.5752,
|
767 |
+
"step": 1060
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 2.43988603988604,
|
771 |
+
"grad_norm": 0.2903170979095093,
|
772 |
+
"learning_rate": 5e-06,
|
773 |
+
"loss": 0.578,
|
774 |
+
"step": 1070
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 2.4626780626780627,
|
778 |
+
"grad_norm": 0.2852792499162689,
|
779 |
+
"learning_rate": 5e-06,
|
780 |
+
"loss": 0.5732,
|
781 |
+
"step": 1080
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 2.4854700854700855,
|
785 |
+
"grad_norm": 0.2753361670224193,
|
786 |
+
"learning_rate": 5e-06,
|
787 |
+
"loss": 0.5709,
|
788 |
+
"step": 1090
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.5082621082621084,
|
792 |
+
"grad_norm": 0.29187729007400126,
|
793 |
+
"learning_rate": 5e-06,
|
794 |
+
"loss": 0.5773,
|
795 |
+
"step": 1100
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 2.5310541310541312,
|
799 |
+
"grad_norm": 0.2948065365452112,
|
800 |
+
"learning_rate": 5e-06,
|
801 |
+
"loss": 0.5709,
|
802 |
+
"step": 1110
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 2.5538461538461537,
|
806 |
+
"grad_norm": 0.29233811433610235,
|
807 |
+
"learning_rate": 5e-06,
|
808 |
+
"loss": 0.569,
|
809 |
+
"step": 1120
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 2.5766381766381765,
|
813 |
+
"grad_norm": 0.29251338108992897,
|
814 |
+
"learning_rate": 5e-06,
|
815 |
+
"loss": 0.5684,
|
816 |
+
"step": 1130
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 2.5994301994301994,
|
820 |
+
"grad_norm": 0.28887301028922413,
|
821 |
+
"learning_rate": 5e-06,
|
822 |
+
"loss": 0.5681,
|
823 |
+
"step": 1140
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 2.6222222222222222,
|
827 |
+
"grad_norm": 0.3130706205394312,
|
828 |
+
"learning_rate": 5e-06,
|
829 |
+
"loss": 0.5684,
|
830 |
+
"step": 1150
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.645014245014245,
|
834 |
+
"grad_norm": 0.3098221144899901,
|
835 |
+
"learning_rate": 5e-06,
|
836 |
+
"loss": 0.5695,
|
837 |
+
"step": 1160
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 2.667806267806268,
|
841 |
+
"grad_norm": 0.28798485314235794,
|
842 |
+
"learning_rate": 5e-06,
|
843 |
+
"loss": 0.5723,
|
844 |
+
"step": 1170
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 2.690598290598291,
|
848 |
+
"grad_norm": 0.28437339107985654,
|
849 |
+
"learning_rate": 5e-06,
|
850 |
+
"loss": 0.5675,
|
851 |
+
"step": 1180
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 2.7133903133903132,
|
855 |
+
"grad_norm": 0.3036502139166253,
|
856 |
+
"learning_rate": 5e-06,
|
857 |
+
"loss": 0.5686,
|
858 |
+
"step": 1190
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 2.736182336182336,
|
862 |
+
"grad_norm": 0.301383160626782,
|
863 |
+
"learning_rate": 5e-06,
|
864 |
+
"loss": 0.5718,
|
865 |
+
"step": 1200
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 2.758974358974359,
|
869 |
+
"grad_norm": 0.3163849017521735,
|
870 |
+
"learning_rate": 5e-06,
|
871 |
+
"loss": 0.5752,
|
872 |
+
"step": 1210
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.781766381766382,
|
876 |
+
"grad_norm": 0.31117137034097503,
|
877 |
+
"learning_rate": 5e-06,
|
878 |
+
"loss": 0.5651,
|
879 |
+
"step": 1220
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 2.8045584045584047,
|
883 |
+
"grad_norm": 0.2930242603622392,
|
884 |
+
"learning_rate": 5e-06,
|
885 |
+
"loss": 0.5636,
|
886 |
+
"step": 1230
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 2.827350427350427,
|
890 |
+
"grad_norm": 0.3144851013348898,
|
891 |
+
"learning_rate": 5e-06,
|
892 |
+
"loss": 0.5784,
|
893 |
+
"step": 1240
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 2.8501424501424504,
|
897 |
+
"grad_norm": 0.2971023651878554,
|
898 |
+
"learning_rate": 5e-06,
|
899 |
+
"loss": 0.575,
|
900 |
+
"step": 1250
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 2.872934472934473,
|
904 |
+
"grad_norm": 0.31461051709792115,
|
905 |
+
"learning_rate": 5e-06,
|
906 |
+
"loss": 0.5722,
|
907 |
+
"step": 1260
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 2.8957264957264957,
|
911 |
+
"grad_norm": 0.31229107305530807,
|
912 |
+
"learning_rate": 5e-06,
|
913 |
+
"loss": 0.5731,
|
914 |
+
"step": 1270
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 2.9185185185185185,
|
918 |
+
"grad_norm": 0.30391491233086704,
|
919 |
+
"learning_rate": 5e-06,
|
920 |
+
"loss": 0.5633,
|
921 |
+
"step": 1280
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 2.9413105413105414,
|
925 |
+
"grad_norm": 0.3087650960617782,
|
926 |
+
"learning_rate": 5e-06,
|
927 |
+
"loss": 0.5635,
|
928 |
+
"step": 1290
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 2.9641025641025642,
|
932 |
+
"grad_norm": 0.2942869811591753,
|
933 |
+
"learning_rate": 5e-06,
|
934 |
+
"loss": 0.5646,
|
935 |
+
"step": 1300
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 2.9868945868945866,
|
939 |
+
"grad_norm": 0.31862561633033365,
|
940 |
+
"learning_rate": 5e-06,
|
941 |
+
"loss": 0.5744,
|
942 |
+
"step": 1310
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 2.996011396011396,
|
946 |
+
"eval_loss": 0.6188442707061768,
|
947 |
+
"eval_runtime": 444.3583,
|
948 |
+
"eval_samples_per_second": 26.607,
|
949 |
+
"eval_steps_per_second": 0.416,
|
950 |
+
"step": 1314
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 2.996011396011396,
|
954 |
+
"step": 1314,
|
955 |
+
"total_flos": 2755219238682624.0,
|
956 |
+
"train_loss": 0.6039808779909549,
|
957 |
+
"train_runtime": 71394.4326,
|
958 |
+
"train_samples_per_second": 9.439,
|
959 |
+
"train_steps_per_second": 0.018
|
960 |
+
}
|
961 |
+
],
|
962 |
+
"logging_steps": 10,
|
963 |
+
"max_steps": 1314,
|
964 |
+
"num_input_tokens_seen": 0,
|
965 |
+
"num_train_epochs": 3,
|
966 |
+
"save_steps": 500,
|
967 |
+
"stateful_callbacks": {
|
968 |
+
"TrainerControl": {
|
969 |
+
"args": {
|
970 |
+
"should_epoch_stop": false,
|
971 |
+
"should_evaluate": false,
|
972 |
+
"should_log": false,
|
973 |
+
"should_save": true,
|
974 |
+
"should_training_stop": true
|
975 |
+
},
|
976 |
+
"attributes": {}
|
977 |
+
}
|
978 |
+
},
|
979 |
+
"total_flos": 2755219238682624.0,
|
980 |
+
"train_batch_size": 8,
|
981 |
+
"trial_name": null,
|
982 |
+
"trial_params": null
|
983 |
+
}
|
training_eval_loss.png
ADDED
training_loss.png
ADDED