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 +948 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
|
|
4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
5 |
tags:
|
6 |
- llama-factory
|
|
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: llama3-1_8b_baseline_infinity_instruct
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# llama3-1_8b_baseline_infinity_instruct
|
17 |
|
18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.9010
|
21 |
|
|
|
4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
+
- full
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: llama3-1_8b_baseline_infinity_instruct
|
|
|
16 |
|
17 |
# llama3-1_8b_baseline_infinity_instruct
|
18 |
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the BAAI/Infinity-Instruct dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.9010
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.9010276198387146,
|
4 |
+
"eval_runtime": 39.042,
|
5 |
+
"eval_samples_per_second": 291.788,
|
6 |
+
"eval_steps_per_second": 1.153,
|
7 |
+
"total_flos": 5.9918252490593665e+19,
|
8 |
+
"train_loss": 0.8716646811452975,
|
9 |
+
"train_runtime": 8996.6792,
|
10 |
+
"train_samples_per_second": 72.17,
|
11 |
+
"train_steps_per_second": 0.141
|
12 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.9010276198387146,
|
4 |
+
"eval_runtime": 39.042,
|
5 |
+
"eval_samples_per_second": 291.788,
|
6 |
+
"eval_steps_per_second": 1.153
|
7 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"total_flos": 5.9918252490593665e+19,
|
4 |
+
"train_loss": 0.8716646811452975,
|
5 |
+
"train_runtime": 8996.6792,
|
6 |
+
"train_samples_per_second": 72.17,
|
7 |
+
"train_steps_per_second": 0.141
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,948 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1269,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02364066193853428,
|
13 |
+
"grad_norm": 1.7614086866378784,
|
14 |
+
"learning_rate": 5e-06,
|
15 |
+
"loss": 1.0709,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04728132387706856,
|
20 |
+
"grad_norm": 3.922980546951294,
|
21 |
+
"learning_rate": 5e-06,
|
22 |
+
"loss": 1.0131,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.07092198581560284,
|
27 |
+
"grad_norm": 1.108715295791626,
|
28 |
+
"learning_rate": 5e-06,
|
29 |
+
"loss": 0.9972,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.09456264775413711,
|
34 |
+
"grad_norm": 0.6008648872375488,
|
35 |
+
"learning_rate": 5e-06,
|
36 |
+
"loss": 0.983,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.1182033096926714,
|
41 |
+
"grad_norm": 0.5573455095291138,
|
42 |
+
"learning_rate": 5e-06,
|
43 |
+
"loss": 0.9748,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.14184397163120568,
|
48 |
+
"grad_norm": 0.6367310881614685,
|
49 |
+
"learning_rate": 5e-06,
|
50 |
+
"loss": 0.9644,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.16548463356973994,
|
55 |
+
"grad_norm": 0.5621835589408875,
|
56 |
+
"learning_rate": 5e-06,
|
57 |
+
"loss": 0.9609,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.18912529550827423,
|
62 |
+
"grad_norm": 0.6173996329307556,
|
63 |
+
"learning_rate": 5e-06,
|
64 |
+
"loss": 0.9607,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2127659574468085,
|
69 |
+
"grad_norm": 0.5042706727981567,
|
70 |
+
"learning_rate": 5e-06,
|
71 |
+
"loss": 0.9524,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.2364066193853428,
|
76 |
+
"grad_norm": 0.7688830494880676,
|
77 |
+
"learning_rate": 5e-06,
|
78 |
+
"loss": 0.9438,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.26004728132387706,
|
83 |
+
"grad_norm": 0.5911379456520081,
|
84 |
+
"learning_rate": 5e-06,
|
85 |
+
"loss": 0.9401,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.28368794326241137,
|
90 |
+
"grad_norm": 0.5532689690589905,
|
91 |
+
"learning_rate": 5e-06,
|
92 |
+
"loss": 0.9468,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.3073286052009456,
|
97 |
+
"grad_norm": 0.8925480246543884,
|
98 |
+
"learning_rate": 5e-06,
|
99 |
+
"loss": 0.9462,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.3309692671394799,
|
104 |
+
"grad_norm": 0.5422332882881165,
|
105 |
+
"learning_rate": 5e-06,
|
106 |
+
"loss": 0.94,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.3546099290780142,
|
111 |
+
"grad_norm": 0.5486394166946411,
|
112 |
+
"learning_rate": 5e-06,
|
113 |
+
"loss": 0.9344,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.37825059101654845,
|
118 |
+
"grad_norm": 0.5163227915763855,
|
119 |
+
"learning_rate": 5e-06,
|
120 |
+
"loss": 0.9281,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.40189125295508277,
|
125 |
+
"grad_norm": 0.53909832239151,
|
126 |
+
"learning_rate": 5e-06,
|
127 |
+
"loss": 0.9377,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.425531914893617,
|
132 |
+
"grad_norm": 0.500614583492279,
|
133 |
+
"learning_rate": 5e-06,
|
134 |
+
"loss": 0.9309,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.4491725768321513,
|
139 |
+
"grad_norm": 0.5055537819862366,
|
140 |
+
"learning_rate": 5e-06,
|
141 |
+
"loss": 0.9326,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.4728132387706856,
|
146 |
+
"grad_norm": 0.5739602446556091,
|
147 |
+
"learning_rate": 5e-06,
|
148 |
+
"loss": 0.9334,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.49645390070921985,
|
153 |
+
"grad_norm": 0.4969063103199005,
|
154 |
+
"learning_rate": 5e-06,
|
155 |
+
"loss": 0.9306,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5200945626477541,
|
160 |
+
"grad_norm": 0.4895598888397217,
|
161 |
+
"learning_rate": 5e-06,
|
162 |
+
"loss": 0.9326,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5437352245862884,
|
167 |
+
"grad_norm": 0.488599956035614,
|
168 |
+
"learning_rate": 5e-06,
|
169 |
+
"loss": 0.9251,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.5673758865248227,
|
174 |
+
"grad_norm": 0.5502417087554932,
|
175 |
+
"learning_rate": 5e-06,
|
176 |
+
"loss": 0.9233,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.5910165484633569,
|
181 |
+
"grad_norm": 0.5484869480133057,
|
182 |
+
"learning_rate": 5e-06,
|
183 |
+
"loss": 0.9177,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.6146572104018913,
|
188 |
+
"grad_norm": 0.70972740650177,
|
189 |
+
"learning_rate": 5e-06,
|
190 |
+
"loss": 0.9204,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.6382978723404256,
|
195 |
+
"grad_norm": 0.5443243980407715,
|
196 |
+
"learning_rate": 5e-06,
|
197 |
+
"loss": 0.9203,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.6619385342789598,
|
202 |
+
"grad_norm": 0.4656381607055664,
|
203 |
+
"learning_rate": 5e-06,
|
204 |
+
"loss": 0.9251,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.6855791962174941,
|
209 |
+
"grad_norm": 0.49396905303001404,
|
210 |
+
"learning_rate": 5e-06,
|
211 |
+
"loss": 0.9242,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.7092198581560284,
|
216 |
+
"grad_norm": 0.43112456798553467,
|
217 |
+
"learning_rate": 5e-06,
|
218 |
+
"loss": 0.9238,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7328605200945626,
|
223 |
+
"grad_norm": 0.4588732123374939,
|
224 |
+
"learning_rate": 5e-06,
|
225 |
+
"loss": 0.9206,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.7565011820330969,
|
230 |
+
"grad_norm": 0.5064387321472168,
|
231 |
+
"learning_rate": 5e-06,
|
232 |
+
"loss": 0.9177,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.7801418439716312,
|
237 |
+
"grad_norm": 0.51941978931427,
|
238 |
+
"learning_rate": 5e-06,
|
239 |
+
"loss": 0.9161,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.8037825059101655,
|
244 |
+
"grad_norm": 0.45160844922065735,
|
245 |
+
"learning_rate": 5e-06,
|
246 |
+
"loss": 0.9197,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.8274231678486997,
|
251 |
+
"grad_norm": 0.4652918875217438,
|
252 |
+
"learning_rate": 5e-06,
|
253 |
+
"loss": 0.9182,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.851063829787234,
|
258 |
+
"grad_norm": 0.49702754616737366,
|
259 |
+
"learning_rate": 5e-06,
|
260 |
+
"loss": 0.9115,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.8747044917257684,
|
265 |
+
"grad_norm": 0.6036341786384583,
|
266 |
+
"learning_rate": 5e-06,
|
267 |
+
"loss": 0.9195,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.8983451536643026,
|
272 |
+
"grad_norm": 0.4541695713996887,
|
273 |
+
"learning_rate": 5e-06,
|
274 |
+
"loss": 0.9144,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.9219858156028369,
|
279 |
+
"grad_norm": 0.5585927963256836,
|
280 |
+
"learning_rate": 5e-06,
|
281 |
+
"loss": 0.9139,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.9456264775413712,
|
286 |
+
"grad_norm": 0.4704740047454834,
|
287 |
+
"learning_rate": 5e-06,
|
288 |
+
"loss": 0.9107,
|
289 |
+
"step": 400
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.9692671394799054,
|
293 |
+
"grad_norm": 0.43893522024154663,
|
294 |
+
"learning_rate": 5e-06,
|
295 |
+
"loss": 0.9093,
|
296 |
+
"step": 410
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.9929078014184397,
|
300 |
+
"grad_norm": 0.4892677366733551,
|
301 |
+
"learning_rate": 5e-06,
|
302 |
+
"loss": 0.9018,
|
303 |
+
"step": 420
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.0,
|
307 |
+
"eval_loss": 0.9103471636772156,
|
308 |
+
"eval_runtime": 38.5799,
|
309 |
+
"eval_samples_per_second": 295.284,
|
310 |
+
"eval_steps_per_second": 1.166,
|
311 |
+
"step": 423
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 1.016548463356974,
|
315 |
+
"grad_norm": 0.5619480609893799,
|
316 |
+
"learning_rate": 5e-06,
|
317 |
+
"loss": 0.8787,
|
318 |
+
"step": 430
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 1.0401891252955082,
|
322 |
+
"grad_norm": 0.5610897541046143,
|
323 |
+
"learning_rate": 5e-06,
|
324 |
+
"loss": 0.8696,
|
325 |
+
"step": 440
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 1.0638297872340425,
|
329 |
+
"grad_norm": 0.4962644577026367,
|
330 |
+
"learning_rate": 5e-06,
|
331 |
+
"loss": 0.8629,
|
332 |
+
"step": 450
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.0874704491725768,
|
336 |
+
"grad_norm": 0.8102297782897949,
|
337 |
+
"learning_rate": 5e-06,
|
338 |
+
"loss": 0.8631,
|
339 |
+
"step": 460
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.1111111111111112,
|
343 |
+
"grad_norm": 0.4762827754020691,
|
344 |
+
"learning_rate": 5e-06,
|
345 |
+
"loss": 0.865,
|
346 |
+
"step": 470
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.1347517730496455,
|
350 |
+
"grad_norm": 0.5226008296012878,
|
351 |
+
"learning_rate": 5e-06,
|
352 |
+
"loss": 0.8588,
|
353 |
+
"step": 480
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.1583924349881798,
|
357 |
+
"grad_norm": 0.4529044032096863,
|
358 |
+
"learning_rate": 5e-06,
|
359 |
+
"loss": 0.8605,
|
360 |
+
"step": 490
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.1820330969267139,
|
364 |
+
"grad_norm": 0.48834407329559326,
|
365 |
+
"learning_rate": 5e-06,
|
366 |
+
"loss": 0.865,
|
367 |
+
"step": 500
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.2056737588652482,
|
371 |
+
"grad_norm": 0.5005617737770081,
|
372 |
+
"learning_rate": 5e-06,
|
373 |
+
"loss": 0.866,
|
374 |
+
"step": 510
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.2293144208037825,
|
378 |
+
"grad_norm": 0.4393448829650879,
|
379 |
+
"learning_rate": 5e-06,
|
380 |
+
"loss": 0.8652,
|
381 |
+
"step": 520
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.2529550827423168,
|
385 |
+
"grad_norm": 0.5248346328735352,
|
386 |
+
"learning_rate": 5e-06,
|
387 |
+
"loss": 0.8653,
|
388 |
+
"step": 530
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.2765957446808511,
|
392 |
+
"grad_norm": 0.5386662483215332,
|
393 |
+
"learning_rate": 5e-06,
|
394 |
+
"loss": 0.859,
|
395 |
+
"step": 540
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.3002364066193852,
|
399 |
+
"grad_norm": 0.48023349046707153,
|
400 |
+
"learning_rate": 5e-06,
|
401 |
+
"loss": 0.8639,
|
402 |
+
"step": 550
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.3238770685579198,
|
406 |
+
"grad_norm": 0.46678417921066284,
|
407 |
+
"learning_rate": 5e-06,
|
408 |
+
"loss": 0.8678,
|
409 |
+
"step": 560
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.3475177304964538,
|
413 |
+
"grad_norm": 0.5156953930854797,
|
414 |
+
"learning_rate": 5e-06,
|
415 |
+
"loss": 0.863,
|
416 |
+
"step": 570
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.3711583924349882,
|
420 |
+
"grad_norm": 0.4521232545375824,
|
421 |
+
"learning_rate": 5e-06,
|
422 |
+
"loss": 0.8661,
|
423 |
+
"step": 580
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.3947990543735225,
|
427 |
+
"grad_norm": 0.4961282014846802,
|
428 |
+
"learning_rate": 5e-06,
|
429 |
+
"loss": 0.8591,
|
430 |
+
"step": 590
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.4184397163120568,
|
434 |
+
"grad_norm": 0.4934581220149994,
|
435 |
+
"learning_rate": 5e-06,
|
436 |
+
"loss": 0.864,
|
437 |
+
"step": 600
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.442080378250591,
|
441 |
+
"grad_norm": 0.5448637008666992,
|
442 |
+
"learning_rate": 5e-06,
|
443 |
+
"loss": 0.8635,
|
444 |
+
"step": 610
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.4657210401891252,
|
448 |
+
"grad_norm": 0.4642185568809509,
|
449 |
+
"learning_rate": 5e-06,
|
450 |
+
"loss": 0.8631,
|
451 |
+
"step": 620
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.4893617021276595,
|
455 |
+
"grad_norm": 0.4816928803920746,
|
456 |
+
"learning_rate": 5e-06,
|
457 |
+
"loss": 0.8618,
|
458 |
+
"step": 630
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.5130023640661938,
|
462 |
+
"grad_norm": 0.4565974175930023,
|
463 |
+
"learning_rate": 5e-06,
|
464 |
+
"loss": 0.864,
|
465 |
+
"step": 640
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.5366430260047281,
|
469 |
+
"grad_norm": 0.580853283405304,
|
470 |
+
"learning_rate": 5e-06,
|
471 |
+
"loss": 0.8613,
|
472 |
+
"step": 650
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.5602836879432624,
|
476 |
+
"grad_norm": 0.5403729677200317,
|
477 |
+
"learning_rate": 5e-06,
|
478 |
+
"loss": 0.8636,
|
479 |
+
"step": 660
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.5839243498817965,
|
483 |
+
"grad_norm": 0.4570687711238861,
|
484 |
+
"learning_rate": 5e-06,
|
485 |
+
"loss": 0.8636,
|
486 |
+
"step": 670
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.607565011820331,
|
490 |
+
"grad_norm": 0.557025134563446,
|
491 |
+
"learning_rate": 5e-06,
|
492 |
+
"loss": 0.8634,
|
493 |
+
"step": 680
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 1.6312056737588652,
|
497 |
+
"grad_norm": 0.4970671534538269,
|
498 |
+
"learning_rate": 5e-06,
|
499 |
+
"loss": 0.8582,
|
500 |
+
"step": 690
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 1.6548463356973995,
|
504 |
+
"grad_norm": 0.5011308193206787,
|
505 |
+
"learning_rate": 5e-06,
|
506 |
+
"loss": 0.8615,
|
507 |
+
"step": 700
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 1.6784869976359338,
|
511 |
+
"grad_norm": 0.5732368230819702,
|
512 |
+
"learning_rate": 5e-06,
|
513 |
+
"loss": 0.8612,
|
514 |
+
"step": 710
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 1.702127659574468,
|
518 |
+
"grad_norm": 0.44940251111984253,
|
519 |
+
"learning_rate": 5e-06,
|
520 |
+
"loss": 0.8654,
|
521 |
+
"step": 720
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.7257683215130024,
|
525 |
+
"grad_norm": 0.4695453643798828,
|
526 |
+
"learning_rate": 5e-06,
|
527 |
+
"loss": 0.8655,
|
528 |
+
"step": 730
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 1.7494089834515365,
|
532 |
+
"grad_norm": 0.6582662463188171,
|
533 |
+
"learning_rate": 5e-06,
|
534 |
+
"loss": 0.863,
|
535 |
+
"step": 740
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 1.773049645390071,
|
539 |
+
"grad_norm": 0.5361992716789246,
|
540 |
+
"learning_rate": 5e-06,
|
541 |
+
"loss": 0.857,
|
542 |
+
"step": 750
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 1.7966903073286051,
|
546 |
+
"grad_norm": 0.4670429527759552,
|
547 |
+
"learning_rate": 5e-06,
|
548 |
+
"loss": 0.8614,
|
549 |
+
"step": 760
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 1.8203309692671394,
|
553 |
+
"grad_norm": 0.44174039363861084,
|
554 |
+
"learning_rate": 5e-06,
|
555 |
+
"loss": 0.8606,
|
556 |
+
"step": 770
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 1.8439716312056738,
|
560 |
+
"grad_norm": 0.4454022943973541,
|
561 |
+
"learning_rate": 5e-06,
|
562 |
+
"loss": 0.8603,
|
563 |
+
"step": 780
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 1.867612293144208,
|
567 |
+
"grad_norm": 0.46973222494125366,
|
568 |
+
"learning_rate": 5e-06,
|
569 |
+
"loss": 0.8624,
|
570 |
+
"step": 790
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 1.8912529550827424,
|
574 |
+
"grad_norm": 0.4946763515472412,
|
575 |
+
"learning_rate": 5e-06,
|
576 |
+
"loss": 0.8648,
|
577 |
+
"step": 800
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 1.9148936170212765,
|
581 |
+
"grad_norm": 0.4165429472923279,
|
582 |
+
"learning_rate": 5e-06,
|
583 |
+
"loss": 0.8584,
|
584 |
+
"step": 810
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.938534278959811,
|
588 |
+
"grad_norm": 0.44204238057136536,
|
589 |
+
"learning_rate": 5e-06,
|
590 |
+
"loss": 0.8615,
|
591 |
+
"step": 820
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 1.962174940898345,
|
595 |
+
"grad_norm": 0.4277856647968292,
|
596 |
+
"learning_rate": 5e-06,
|
597 |
+
"loss": 0.8603,
|
598 |
+
"step": 830
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 1.9858156028368794,
|
602 |
+
"grad_norm": 0.4897569715976715,
|
603 |
+
"learning_rate": 5e-06,
|
604 |
+
"loss": 0.8586,
|
605 |
+
"step": 840
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 2.0,
|
609 |
+
"eval_loss": 0.9001395106315613,
|
610 |
+
"eval_runtime": 38.3885,
|
611 |
+
"eval_samples_per_second": 296.756,
|
612 |
+
"eval_steps_per_second": 1.172,
|
613 |
+
"step": 846
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 2.0094562647754137,
|
617 |
+
"grad_norm": 0.673308789730072,
|
618 |
+
"learning_rate": 5e-06,
|
619 |
+
"loss": 0.8393,
|
620 |
+
"step": 850
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 2.033096926713948,
|
624 |
+
"grad_norm": 0.5594461560249329,
|
625 |
+
"learning_rate": 5e-06,
|
626 |
+
"loss": 0.8071,
|
627 |
+
"step": 860
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 2.0567375886524824,
|
631 |
+
"grad_norm": 0.4584490656852722,
|
632 |
+
"learning_rate": 5e-06,
|
633 |
+
"loss": 0.8083,
|
634 |
+
"step": 870
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 2.0803782505910164,
|
638 |
+
"grad_norm": 0.5544384121894836,
|
639 |
+
"learning_rate": 5e-06,
|
640 |
+
"loss": 0.8135,
|
641 |
+
"step": 880
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 2.104018912529551,
|
645 |
+
"grad_norm": 0.5173571705818176,
|
646 |
+
"learning_rate": 5e-06,
|
647 |
+
"loss": 0.8104,
|
648 |
+
"step": 890
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 2.127659574468085,
|
652 |
+
"grad_norm": 0.488302618265152,
|
653 |
+
"learning_rate": 5e-06,
|
654 |
+
"loss": 0.8155,
|
655 |
+
"step": 900
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 2.1513002364066196,
|
659 |
+
"grad_norm": 0.5209611058235168,
|
660 |
+
"learning_rate": 5e-06,
|
661 |
+
"loss": 0.8108,
|
662 |
+
"step": 910
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.1749408983451537,
|
666 |
+
"grad_norm": 0.51943439245224,
|
667 |
+
"learning_rate": 5e-06,
|
668 |
+
"loss": 0.808,
|
669 |
+
"step": 920
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 2.198581560283688,
|
673 |
+
"grad_norm": 0.5136656761169434,
|
674 |
+
"learning_rate": 5e-06,
|
675 |
+
"loss": 0.8152,
|
676 |
+
"step": 930
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 2.2222222222222223,
|
680 |
+
"grad_norm": 0.48146888613700867,
|
681 |
+
"learning_rate": 5e-06,
|
682 |
+
"loss": 0.8114,
|
683 |
+
"step": 940
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 2.2458628841607564,
|
687 |
+
"grad_norm": 0.5011332035064697,
|
688 |
+
"learning_rate": 5e-06,
|
689 |
+
"loss": 0.8133,
|
690 |
+
"step": 950
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.269503546099291,
|
694 |
+
"grad_norm": 0.5616235733032227,
|
695 |
+
"learning_rate": 5e-06,
|
696 |
+
"loss": 0.815,
|
697 |
+
"step": 960
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 2.293144208037825,
|
701 |
+
"grad_norm": 0.4666649401187897,
|
702 |
+
"learning_rate": 5e-06,
|
703 |
+
"loss": 0.8096,
|
704 |
+
"step": 970
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.3167848699763596,
|
708 |
+
"grad_norm": 0.5732521414756775,
|
709 |
+
"learning_rate": 5e-06,
|
710 |
+
"loss": 0.8098,
|
711 |
+
"step": 980
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 2.3404255319148937,
|
715 |
+
"grad_norm": 0.4544953405857086,
|
716 |
+
"learning_rate": 5e-06,
|
717 |
+
"loss": 0.8124,
|
718 |
+
"step": 990
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 2.3640661938534278,
|
722 |
+
"grad_norm": 0.44587448239326477,
|
723 |
+
"learning_rate": 5e-06,
|
724 |
+
"loss": 0.8095,
|
725 |
+
"step": 1000
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 2.3877068557919623,
|
729 |
+
"grad_norm": 0.484457403421402,
|
730 |
+
"learning_rate": 5e-06,
|
731 |
+
"loss": 0.8118,
|
732 |
+
"step": 1010
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.4113475177304964,
|
736 |
+
"grad_norm": 0.4641134440898895,
|
737 |
+
"learning_rate": 5e-06,
|
738 |
+
"loss": 0.8124,
|
739 |
+
"step": 1020
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 2.434988179669031,
|
743 |
+
"grad_norm": 0.49560511112213135,
|
744 |
+
"learning_rate": 5e-06,
|
745 |
+
"loss": 0.8129,
|
746 |
+
"step": 1030
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 2.458628841607565,
|
750 |
+
"grad_norm": 0.4686046540737152,
|
751 |
+
"learning_rate": 5e-06,
|
752 |
+
"loss": 0.814,
|
753 |
+
"step": 1040
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 2.482269503546099,
|
757 |
+
"grad_norm": 0.5736932158470154,
|
758 |
+
"learning_rate": 5e-06,
|
759 |
+
"loss": 0.809,
|
760 |
+
"step": 1050
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 2.5059101654846336,
|
764 |
+
"grad_norm": 0.5565879940986633,
|
765 |
+
"learning_rate": 5e-06,
|
766 |
+
"loss": 0.8192,
|
767 |
+
"step": 1060
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 2.5295508274231677,
|
771 |
+
"grad_norm": 0.5535584092140198,
|
772 |
+
"learning_rate": 5e-06,
|
773 |
+
"loss": 0.8177,
|
774 |
+
"step": 1070
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 2.5531914893617023,
|
778 |
+
"grad_norm": 0.49917906522750854,
|
779 |
+
"learning_rate": 5e-06,
|
780 |
+
"loss": 0.817,
|
781 |
+
"step": 1080
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 2.5768321513002364,
|
785 |
+
"grad_norm": 0.48814043402671814,
|
786 |
+
"learning_rate": 5e-06,
|
787 |
+
"loss": 0.8118,
|
788 |
+
"step": 1090
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 2.6004728132387704,
|
792 |
+
"grad_norm": 0.4942103326320648,
|
793 |
+
"learning_rate": 5e-06,
|
794 |
+
"loss": 0.8218,
|
795 |
+
"step": 1100
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 2.624113475177305,
|
799 |
+
"grad_norm": 0.5041037797927856,
|
800 |
+
"learning_rate": 5e-06,
|
801 |
+
"loss": 0.8142,
|
802 |
+
"step": 1110
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 2.6477541371158395,
|
806 |
+
"grad_norm": 0.4969462454319,
|
807 |
+
"learning_rate": 5e-06,
|
808 |
+
"loss": 0.8194,
|
809 |
+
"step": 1120
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 2.6713947990543736,
|
813 |
+
"grad_norm": 0.5635184049606323,
|
814 |
+
"learning_rate": 5e-06,
|
815 |
+
"loss": 0.8206,
|
816 |
+
"step": 1130
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 2.6950354609929077,
|
820 |
+
"grad_norm": 0.4972004294395447,
|
821 |
+
"learning_rate": 5e-06,
|
822 |
+
"loss": 0.8192,
|
823 |
+
"step": 1140
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 2.7186761229314422,
|
827 |
+
"grad_norm": 0.49688395857810974,
|
828 |
+
"learning_rate": 5e-06,
|
829 |
+
"loss": 0.8165,
|
830 |
+
"step": 1150
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 2.7423167848699763,
|
834 |
+
"grad_norm": 0.4726709723472595,
|
835 |
+
"learning_rate": 5e-06,
|
836 |
+
"loss": 0.8205,
|
837 |
+
"step": 1160
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 2.7659574468085104,
|
841 |
+
"grad_norm": 0.532228946685791,
|
842 |
+
"learning_rate": 5e-06,
|
843 |
+
"loss": 0.8139,
|
844 |
+
"step": 1170
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 2.789598108747045,
|
848 |
+
"grad_norm": 0.4629664421081543,
|
849 |
+
"learning_rate": 5e-06,
|
850 |
+
"loss": 0.8119,
|
851 |
+
"step": 1180
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 2.813238770685579,
|
855 |
+
"grad_norm": 0.4985387921333313,
|
856 |
+
"learning_rate": 5e-06,
|
857 |
+
"loss": 0.8206,
|
858 |
+
"step": 1190
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 2.8368794326241136,
|
862 |
+
"grad_norm": 0.48208263516426086,
|
863 |
+
"learning_rate": 5e-06,
|
864 |
+
"loss": 0.8144,
|
865 |
+
"step": 1200
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 2.8605200945626477,
|
869 |
+
"grad_norm": 0.5160050988197327,
|
870 |
+
"learning_rate": 5e-06,
|
871 |
+
"loss": 0.8179,
|
872 |
+
"step": 1210
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 2.884160756501182,
|
876 |
+
"grad_norm": 0.47810521721839905,
|
877 |
+
"learning_rate": 5e-06,
|
878 |
+
"loss": 0.8157,
|
879 |
+
"step": 1220
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 2.9078014184397163,
|
883 |
+
"grad_norm": 0.4839594066143036,
|
884 |
+
"learning_rate": 5e-06,
|
885 |
+
"loss": 0.8162,
|
886 |
+
"step": 1230
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 2.9314420803782504,
|
890 |
+
"grad_norm": 0.49858078360557556,
|
891 |
+
"learning_rate": 5e-06,
|
892 |
+
"loss": 0.8133,
|
893 |
+
"step": 1240
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 2.955082742316785,
|
897 |
+
"grad_norm": 0.5557030439376831,
|
898 |
+
"learning_rate": 5e-06,
|
899 |
+
"loss": 0.8167,
|
900 |
+
"step": 1250
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 2.978723404255319,
|
904 |
+
"grad_norm": 0.5793541073799133,
|
905 |
+
"learning_rate": 5e-06,
|
906 |
+
"loss": 0.8143,
|
907 |
+
"step": 1260
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 3.0,
|
911 |
+
"eval_loss": 0.9010276198387146,
|
912 |
+
"eval_runtime": 39.1845,
|
913 |
+
"eval_samples_per_second": 290.728,
|
914 |
+
"eval_steps_per_second": 1.148,
|
915 |
+
"step": 1269
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 3.0,
|
919 |
+
"step": 1269,
|
920 |
+
"total_flos": 5.9918252490593665e+19,
|
921 |
+
"train_loss": 0.8716646811452975,
|
922 |
+
"train_runtime": 8996.6792,
|
923 |
+
"train_samples_per_second": 72.17,
|
924 |
+
"train_steps_per_second": 0.141
|
925 |
+
}
|
926 |
+
],
|
927 |
+
"logging_steps": 10,
|
928 |
+
"max_steps": 1269,
|
929 |
+
"num_input_tokens_seen": 0,
|
930 |
+
"num_train_epochs": 3,
|
931 |
+
"save_steps": 500,
|
932 |
+
"stateful_callbacks": {
|
933 |
+
"TrainerControl": {
|
934 |
+
"args": {
|
935 |
+
"should_epoch_stop": false,
|
936 |
+
"should_evaluate": false,
|
937 |
+
"should_log": false,
|
938 |
+
"should_save": true,
|
939 |
+
"should_training_stop": true
|
940 |
+
},
|
941 |
+
"attributes": {}
|
942 |
+
}
|
943 |
+
},
|
944 |
+
"total_flos": 5.9918252490593665e+19,
|
945 |
+
"train_batch_size": 16,
|
946 |
+
"trial_name": null,
|
947 |
+
"trial_params": null
|
948 |
+
}
|
training_eval_loss.png
ADDED
training_loss.png
ADDED