MHGanainy/gpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-7
Browse files- README.md +2 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +868 -0
README.md
CHANGED
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# gpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-7
|
16 |
|
17 |
This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
15 |
# gpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-7
|
16 |
|
17 |
This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.9189
|
20 |
|
21 |
## Model description
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.918867826461792,
|
4 |
+
"eval_runtime": 118.6009,
|
5 |
+
"eval_samples_per_second": 21.695,
|
6 |
+
"eval_steps_per_second": 2.715,
|
7 |
+
"perplexity": 6.813240330567253,
|
8 |
+
"total_flos": 2.17890078425088e+17,
|
9 |
+
"train_loss": 1.9851969016204616,
|
10 |
+
"train_runtime": 3196.2319,
|
11 |
+
"train_samples_per_second": 7.443,
|
12 |
+
"train_steps_per_second": 3.722
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_loss": 1.918867826461792,
|
4 |
+
"eval_runtime": 118.6009,
|
5 |
+
"eval_samples_per_second": 21.695,
|
6 |
+
"eval_steps_per_second": 2.715,
|
7 |
+
"perplexity": 6.813240330567253
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 2.17890078425088e+17,
|
4 |
+
"train_loss": 1.9851969016204616,
|
5 |
+
"train_runtime": 3196.2319,
|
6 |
+
"train_samples_per_second": 7.443,
|
7 |
+
"train_steps_per_second": 3.722
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,868 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 11895,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.008406893652795292,
|
13 |
+
"grad_norm": 0.14043055474758148,
|
14 |
+
"learning_rate": 2.0000000000000003e-06,
|
15 |
+
"loss": 2.4104,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.016813787305590584,
|
20 |
+
"grad_norm": 0.2322196364402771,
|
21 |
+
"learning_rate": 4.000000000000001e-06,
|
22 |
+
"loss": 2.4058,
|
23 |
+
"step": 200
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.025220680958385876,
|
27 |
+
"grad_norm": 0.330422580242157,
|
28 |
+
"learning_rate": 6e-06,
|
29 |
+
"loss": 2.3956,
|
30 |
+
"step": 300
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.03362757461118117,
|
34 |
+
"grad_norm": 0.37281373143196106,
|
35 |
+
"learning_rate": 8.000000000000001e-06,
|
36 |
+
"loss": 2.3817,
|
37 |
+
"step": 400
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.042034468263976464,
|
41 |
+
"grad_norm": 0.4371340274810791,
|
42 |
+
"learning_rate": 1e-05,
|
43 |
+
"loss": 2.2819,
|
44 |
+
"step": 500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.05044136191677175,
|
48 |
+
"grad_norm": 0.5313137173652649,
|
49 |
+
"learning_rate": 1.2e-05,
|
50 |
+
"loss": 2.2971,
|
51 |
+
"step": 600
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.05884825556956705,
|
55 |
+
"grad_norm": 0.5993666648864746,
|
56 |
+
"learning_rate": 1.4e-05,
|
57 |
+
"loss": 2.2486,
|
58 |
+
"step": 700
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.06725514922236234,
|
62 |
+
"grad_norm": 0.885300874710083,
|
63 |
+
"learning_rate": 1.6000000000000003e-05,
|
64 |
+
"loss": 2.2134,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.07566204287515763,
|
69 |
+
"grad_norm": 0.7315155267715454,
|
70 |
+
"learning_rate": 1.8e-05,
|
71 |
+
"loss": 2.1677,
|
72 |
+
"step": 900
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.08406893652795293,
|
76 |
+
"grad_norm": 0.6705694794654846,
|
77 |
+
"learning_rate": 2e-05,
|
78 |
+
"loss": 2.1677,
|
79 |
+
"step": 1000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.09247583018074822,
|
83 |
+
"grad_norm": 0.6811093688011169,
|
84 |
+
"learning_rate": 1.999584295057038e-05,
|
85 |
+
"loss": 2.1539,
|
86 |
+
"step": 1100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.1008827238335435,
|
90 |
+
"grad_norm": 0.8088228702545166,
|
91 |
+
"learning_rate": 1.9983375258493504e-05,
|
92 |
+
"loss": 2.1099,
|
93 |
+
"step": 1200
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.1092896174863388,
|
97 |
+
"grad_norm": 0.6950477361679077,
|
98 |
+
"learning_rate": 1.996260728953182e-05,
|
99 |
+
"loss": 2.0899,
|
100 |
+
"step": 1300
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.1176965111391341,
|
104 |
+
"grad_norm": 0.746992290019989,
|
105 |
+
"learning_rate": 1.9933556310380036e-05,
|
106 |
+
"loss": 2.1047,
|
107 |
+
"step": 1400
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.12610340479192939,
|
111 |
+
"grad_norm": 0.9399320483207703,
|
112 |
+
"learning_rate": 1.9896246474309414e-05,
|
113 |
+
"loss": 2.0344,
|
114 |
+
"step": 1500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.13451029844472467,
|
118 |
+
"grad_norm": 0.8537988066673279,
|
119 |
+
"learning_rate": 1.9850708801086507e-05,
|
120 |
+
"loss": 2.0576,
|
121 |
+
"step": 1600
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.14291719209751996,
|
125 |
+
"grad_norm": 0.8270643949508667,
|
126 |
+
"learning_rate": 1.9796981151183013e-05,
|
127 |
+
"loss": 2.019,
|
128 |
+
"step": 1700
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.15132408575031525,
|
132 |
+
"grad_norm": 1.1590845584869385,
|
133 |
+
"learning_rate": 1.9735108194298206e-05,
|
134 |
+
"loss": 2.0348,
|
135 |
+
"step": 1800
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.15973097940311054,
|
139 |
+
"grad_norm": 0.8914215564727783,
|
140 |
+
"learning_rate": 1.9665141372220112e-05,
|
141 |
+
"loss": 2.0314,
|
142 |
+
"step": 1900
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.16813787305590586,
|
146 |
+
"grad_norm": 0.7579370141029358,
|
147 |
+
"learning_rate": 1.9587138856056303e-05,
|
148 |
+
"loss": 2.0636,
|
149 |
+
"step": 2000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.17654476670870115,
|
153 |
+
"grad_norm": 0.9895981550216675,
|
154 |
+
"learning_rate": 1.9501165497869832e-05,
|
155 |
+
"loss": 1.9961,
|
156 |
+
"step": 2100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.18495166036149643,
|
160 |
+
"grad_norm": 0.9374507069587708,
|
161 |
+
"learning_rate": 1.940729277676063e-05,
|
162 |
+
"loss": 1.9923,
|
163 |
+
"step": 2200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.19335855401429172,
|
167 |
+
"grad_norm": 0.9945927858352661,
|
168 |
+
"learning_rate": 1.930559873943704e-05,
|
169 |
+
"loss": 1.9944,
|
170 |
+
"step": 2300
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.201765447667087,
|
174 |
+
"grad_norm": 0.9538114070892334,
|
175 |
+
"learning_rate": 1.9196167935327036e-05,
|
176 |
+
"loss": 2.036,
|
177 |
+
"step": 2400
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.2101723413198823,
|
181 |
+
"grad_norm": 0.780885636806488,
|
182 |
+
"learning_rate": 1.9079091346282977e-05,
|
183 |
+
"loss": 1.9894,
|
184 |
+
"step": 2500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.2185792349726776,
|
188 |
+
"grad_norm": 1.2008519172668457,
|
189 |
+
"learning_rate": 1.8954466310938405e-05,
|
190 |
+
"loss": 1.9837,
|
191 |
+
"step": 2600
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.22698612862547288,
|
195 |
+
"grad_norm": 1.089125394821167,
|
196 |
+
"learning_rate": 1.8822396443779745e-05,
|
197 |
+
"loss": 2.016,
|
198 |
+
"step": 2700
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.2353930222782682,
|
202 |
+
"grad_norm": 1.087217092514038,
|
203 |
+
"learning_rate": 1.868299154900018e-05,
|
204 |
+
"loss": 2.0407,
|
205 |
+
"step": 2800
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.24379991593106348,
|
209 |
+
"grad_norm": 0.9000464677810669,
|
210 |
+
"learning_rate": 1.8536367529207375e-05,
|
211 |
+
"loss": 1.9954,
|
212 |
+
"step": 2900
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.25220680958385877,
|
216 |
+
"grad_norm": 0.7694302201271057,
|
217 |
+
"learning_rate": 1.83826462890609e-05,
|
218 |
+
"loss": 1.9973,
|
219 |
+
"step": 3000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.26061370323665406,
|
223 |
+
"grad_norm": 0.8629293441772461,
|
224 |
+
"learning_rate": 1.8221955633919495e-05,
|
225 |
+
"loss": 1.9994,
|
226 |
+
"step": 3100
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.26902059688944935,
|
230 |
+
"grad_norm": 0.839648962020874,
|
231 |
+
"learning_rate": 1.8054429163582415e-05,
|
232 |
+
"loss": 2.003,
|
233 |
+
"step": 3200
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.27742749054224464,
|
237 |
+
"grad_norm": 0.8285431861877441,
|
238 |
+
"learning_rate": 1.7880206161213255e-05,
|
239 |
+
"loss": 1.9925,
|
240 |
+
"step": 3300
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.2858343841950399,
|
244 |
+
"grad_norm": 0.837740421295166,
|
245 |
+
"learning_rate": 1.7699431477538534e-05,
|
246 |
+
"loss": 1.9801,
|
247 |
+
"step": 3400
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.2942412778478352,
|
251 |
+
"grad_norm": 0.8980201482772827,
|
252 |
+
"learning_rate": 1.7512255410417392e-05,
|
253 |
+
"loss": 1.9764,
|
254 |
+
"step": 3500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.3026481715006305,
|
258 |
+
"grad_norm": 1.3097134828567505,
|
259 |
+
"learning_rate": 1.731883357988244e-05,
|
260 |
+
"loss": 1.9771,
|
261 |
+
"step": 3600
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.3110550651534258,
|
265 |
+
"grad_norm": 0.7765768766403198,
|
266 |
+
"learning_rate": 1.7119326798755734e-05,
|
267 |
+
"loss": 1.9589,
|
268 |
+
"step": 3700
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.3194619588062211,
|
272 |
+
"grad_norm": 1.0500297546386719,
|
273 |
+
"learning_rate": 1.6913900938947417e-05,
|
274 |
+
"loss": 1.9478,
|
275 |
+
"step": 3800
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.32786885245901637,
|
279 |
+
"grad_norm": 0.9133660793304443,
|
280 |
+
"learning_rate": 1.6702726793548153e-05,
|
281 |
+
"loss": 1.9782,
|
282 |
+
"step": 3900
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.3362757461118117,
|
286 |
+
"grad_norm": 0.9790305495262146,
|
287 |
+
"learning_rate": 1.6485979934830084e-05,
|
288 |
+
"loss": 1.9712,
|
289 |
+
"step": 4000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.344682639764607,
|
293 |
+
"grad_norm": 1.1819267272949219,
|
294 |
+
"learning_rate": 1.626384056827429e-05,
|
295 |
+
"loss": 1.9597,
|
296 |
+
"step": 4100
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.3530895334174023,
|
300 |
+
"grad_norm": 1.196151852607727,
|
301 |
+
"learning_rate": 1.6036493382746178e-05,
|
302 |
+
"loss": 1.9571,
|
303 |
+
"step": 4200
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.3614964270701976,
|
307 |
+
"grad_norm": 0.8918384909629822,
|
308 |
+
"learning_rate": 1.580412739694333e-05,
|
309 |
+
"loss": 1.9769,
|
310 |
+
"step": 4300
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.36990332072299287,
|
314 |
+
"grad_norm": 2.0516951084136963,
|
315 |
+
"learning_rate": 1.5566935802243496e-05,
|
316 |
+
"loss": 1.9757,
|
317 |
+
"step": 4400
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.37831021437578816,
|
321 |
+
"grad_norm": 0.9879031777381897,
|
322 |
+
"learning_rate": 1.5325115802083373e-05,
|
323 |
+
"loss": 1.9893,
|
324 |
+
"step": 4500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.38671710802858345,
|
328 |
+
"grad_norm": 0.6235149502754211,
|
329 |
+
"learning_rate": 1.5078868448001704e-05,
|
330 |
+
"loss": 2.008,
|
331 |
+
"step": 4600
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.39512400168137873,
|
335 |
+
"grad_norm": 0.9613019824028015,
|
336 |
+
"learning_rate": 1.4828398472483057e-05,
|
337 |
+
"loss": 1.9669,
|
338 |
+
"step": 4700
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.403530895334174,
|
342 |
+
"grad_norm": 1.0296316146850586,
|
343 |
+
"learning_rate": 1.4573914118741201e-05,
|
344 |
+
"loss": 1.8964,
|
345 |
+
"step": 4800
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.4119377889869693,
|
349 |
+
"grad_norm": 0.8810610771179199,
|
350 |
+
"learning_rate": 1.4315626967583657e-05,
|
351 |
+
"loss": 1.9226,
|
352 |
+
"step": 4900
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.4203446826397646,
|
356 |
+
"grad_norm": 0.9355632066726685,
|
357 |
+
"learning_rate": 1.40537517615013e-05,
|
358 |
+
"loss": 1.9678,
|
359 |
+
"step": 5000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.4287515762925599,
|
363 |
+
"grad_norm": 0.7143288850784302,
|
364 |
+
"learning_rate": 1.3788506226129348e-05,
|
365 |
+
"loss": 1.9328,
|
366 |
+
"step": 5100
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.4371584699453552,
|
370 |
+
"grad_norm": 0.987920880317688,
|
371 |
+
"learning_rate": 1.3520110889228104e-05,
|
372 |
+
"loss": 1.8968,
|
373 |
+
"step": 5200
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.44556536359815047,
|
377 |
+
"grad_norm": 0.8306659460067749,
|
378 |
+
"learning_rate": 1.3248788897334005e-05,
|
379 |
+
"loss": 1.9294,
|
380 |
+
"step": 5300
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.45397225725094575,
|
384 |
+
"grad_norm": 1.0377694368362427,
|
385 |
+
"learning_rate": 1.2974765830233383e-05,
|
386 |
+
"loss": 1.9835,
|
387 |
+
"step": 5400
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.46237915090374104,
|
391 |
+
"grad_norm": 0.9360339641571045,
|
392 |
+
"learning_rate": 1.269826951341319e-05,
|
393 |
+
"loss": 1.9121,
|
394 |
+
"step": 5500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.4707860445565364,
|
398 |
+
"grad_norm": 1.0214323997497559,
|
399 |
+
"learning_rate": 1.2419529828644661e-05,
|
400 |
+
"loss": 1.9133,
|
401 |
+
"step": 5600
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.4791929382093317,
|
405 |
+
"grad_norm": 1.1800683736801147,
|
406 |
+
"learning_rate": 1.2138778522857307e-05,
|
407 |
+
"loss": 1.934,
|
408 |
+
"step": 5700
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.48759983186212696,
|
412 |
+
"grad_norm": 1.0064023733139038,
|
413 |
+
"learning_rate": 1.1856249015462242e-05,
|
414 |
+
"loss": 1.9665,
|
415 |
+
"step": 5800
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.49600672551492225,
|
419 |
+
"grad_norm": 1.3952449560165405,
|
420 |
+
"learning_rate": 1.1572176204284986e-05,
|
421 |
+
"loss": 1.9426,
|
422 |
+
"step": 5900
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.5044136191677175,
|
426 |
+
"grad_norm": 1.0473861694335938,
|
427 |
+
"learning_rate": 1.1286796270269076e-05,
|
428 |
+
"loss": 1.9559,
|
429 |
+
"step": 6000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.5128205128205128,
|
433 |
+
"grad_norm": 1.101931095123291,
|
434 |
+
"learning_rate": 1.1000346481112887e-05,
|
435 |
+
"loss": 1.9103,
|
436 |
+
"step": 6100
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.5212274064733081,
|
440 |
+
"grad_norm": 1.0466363430023193,
|
441 |
+
"learning_rate": 1.0713064994002956e-05,
|
442 |
+
"loss": 1.9395,
|
443 |
+
"step": 6200
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.5296343001261034,
|
447 |
+
"grad_norm": 0.9257377982139587,
|
448 |
+
"learning_rate": 1.0425190657607702e-05,
|
449 |
+
"loss": 1.9141,
|
450 |
+
"step": 6300
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.5380411937788987,
|
454 |
+
"grad_norm": 0.779354453086853,
|
455 |
+
"learning_rate": 1.0136962813496306e-05,
|
456 |
+
"loss": 1.9647,
|
457 |
+
"step": 6400
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.546448087431694,
|
461 |
+
"grad_norm": 0.8354730606079102,
|
462 |
+
"learning_rate": 9.848621097147772e-06,
|
463 |
+
"loss": 2.0283,
|
464 |
+
"step": 6500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.5548549810844893,
|
468 |
+
"grad_norm": 1.0222142934799194,
|
469 |
+
"learning_rate": 9.560405238715588e-06,
|
470 |
+
"loss": 1.9444,
|
471 |
+
"step": 6600
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.5632618747372846,
|
475 |
+
"grad_norm": 1.3046057224273682,
|
476 |
+
"learning_rate": 9.272554863713739e-06,
|
477 |
+
"loss": 1.9555,
|
478 |
+
"step": 6700
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.5716687683900799,
|
482 |
+
"grad_norm": 0.8095905184745789,
|
483 |
+
"learning_rate": 8.985309293789662e-06,
|
484 |
+
"loss": 1.9761,
|
485 |
+
"step": 6800
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.5800756620428752,
|
489 |
+
"grad_norm": 1.0805299282073975,
|
490 |
+
"learning_rate": 8.698907347749885e-06,
|
491 |
+
"loss": 1.9043,
|
492 |
+
"step": 6900
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.5884825556956704,
|
496 |
+
"grad_norm": 1.3454480171203613,
|
497 |
+
"learning_rate": 8.413587143003691e-06,
|
498 |
+
"loss": 1.902,
|
499 |
+
"step": 7000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.5968894493484658,
|
503 |
+
"grad_norm": 1.1316404342651367,
|
504 |
+
"learning_rate": 8.129585897589964e-06,
|
505 |
+
"loss": 1.942,
|
506 |
+
"step": 7100
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.605296343001261,
|
510 |
+
"grad_norm": 0.9173849821090698,
|
511 |
+
"learning_rate": 7.847139732951751e-06,
|
512 |
+
"loss": 1.9336,
|
513 |
+
"step": 7200
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.6137032366540563,
|
517 |
+
"grad_norm": 0.8359085321426392,
|
518 |
+
"learning_rate": 7.566483477622577e-06,
|
519 |
+
"loss": 1.9584,
|
520 |
+
"step": 7300
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.6221101303068516,
|
524 |
+
"grad_norm": 1.6915035247802734,
|
525 |
+
"learning_rate": 7.28785047198767e-06,
|
526 |
+
"loss": 1.9113,
|
527 |
+
"step": 7400
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.6305170239596469,
|
531 |
+
"grad_norm": 0.8478715419769287,
|
532 |
+
"learning_rate": 7.011472374282457e-06,
|
533 |
+
"loss": 1.9362,
|
534 |
+
"step": 7500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.6389239176124422,
|
538 |
+
"grad_norm": 1.5024291276931763,
|
539 |
+
"learning_rate": 6.737578967989626e-06,
|
540 |
+
"loss": 1.9636,
|
541 |
+
"step": 7600
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.6473308112652375,
|
545 |
+
"grad_norm": 0.7754480242729187,
|
546 |
+
"learning_rate": 6.466397970794855e-06,
|
547 |
+
"loss": 1.9107,
|
548 |
+
"step": 7700
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.6557377049180327,
|
552 |
+
"grad_norm": 0.7962978482246399,
|
553 |
+
"learning_rate": 6.198154845260089e-06,
|
554 |
+
"loss": 1.8819,
|
555 |
+
"step": 7800
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.6641445985708281,
|
559 |
+
"grad_norm": 0.9278832077980042,
|
560 |
+
"learning_rate": 5.933072611371725e-06,
|
561 |
+
"loss": 1.9741,
|
562 |
+
"step": 7900
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.6725514922236234,
|
566 |
+
"grad_norm": 1.244887351989746,
|
567 |
+
"learning_rate": 5.671371661119609e-06,
|
568 |
+
"loss": 2.0055,
|
569 |
+
"step": 8000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.6809583858764187,
|
573 |
+
"grad_norm": 1.1086173057556152,
|
574 |
+
"learning_rate": 5.415832074569403e-06,
|
575 |
+
"loss": 1.8962,
|
576 |
+
"step": 8100
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.689365279529214,
|
580 |
+
"grad_norm": 1.0748802423477173,
|
581 |
+
"learning_rate": 5.161504255249876e-06,
|
582 |
+
"loss": 1.9434,
|
583 |
+
"step": 8200
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.6977721731820092,
|
587 |
+
"grad_norm": 0.7687519788742065,
|
588 |
+
"learning_rate": 4.911199209125536e-06,
|
589 |
+
"loss": 1.95,
|
590 |
+
"step": 8300
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.7061790668348046,
|
594 |
+
"grad_norm": 0.9328936338424683,
|
595 |
+
"learning_rate": 4.665125042286226e-06,
|
596 |
+
"loss": 1.9271,
|
597 |
+
"step": 8400
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.7145859604875998,
|
601 |
+
"grad_norm": 1.0116279125213623,
|
602 |
+
"learning_rate": 4.423486343226934e-06,
|
603 |
+
"loss": 1.8916,
|
604 |
+
"step": 8500
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.7229928541403952,
|
608 |
+
"grad_norm": 0.9574350714683533,
|
609 |
+
"learning_rate": 4.186484012750876e-06,
|
610 |
+
"loss": 2.0135,
|
611 |
+
"step": 8600
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.7313997477931904,
|
615 |
+
"grad_norm": 1.5315290689468384,
|
616 |
+
"learning_rate": 3.954315096938598e-06,
|
617 |
+
"loss": 1.9159,
|
618 |
+
"step": 8700
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.7398066414459857,
|
622 |
+
"grad_norm": 1.2323825359344482,
|
623 |
+
"learning_rate": 3.7271726233219098e-06,
|
624 |
+
"loss": 1.9175,
|
625 |
+
"step": 8800
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.748213535098781,
|
629 |
+
"grad_norm": 0.7751179933547974,
|
630 |
+
"learning_rate": 3.50524544039889e-06,
|
631 |
+
"loss": 1.9278,
|
632 |
+
"step": 8900
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.7566204287515763,
|
636 |
+
"grad_norm": 1.096082329750061,
|
637 |
+
"learning_rate": 3.288718060623376e-06,
|
638 |
+
"loss": 1.9253,
|
639 |
+
"step": 9000
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.7650273224043715,
|
643 |
+
"grad_norm": 0.9929354786872864,
|
644 |
+
"learning_rate": 3.077770506999487e-06,
|
645 |
+
"loss": 1.9252,
|
646 |
+
"step": 9100
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.7734342160571669,
|
650 |
+
"grad_norm": 0.8709311485290527,
|
651 |
+
"learning_rate": 2.872578163408717e-06,
|
652 |
+
"loss": 1.9219,
|
653 |
+
"step": 9200
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.7818411097099621,
|
657 |
+
"grad_norm": 1.3237998485565186,
|
658 |
+
"learning_rate": 2.673311628794043e-06,
|
659 |
+
"loss": 1.9318,
|
660 |
+
"step": 9300
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.7902480033627575,
|
664 |
+
"grad_norm": 1.3490018844604492,
|
665 |
+
"learning_rate": 2.4801365753222795e-06,
|
666 |
+
"loss": 1.9017,
|
667 |
+
"step": 9400
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.7986548970155527,
|
671 |
+
"grad_norm": 1.5231995582580566,
|
672 |
+
"learning_rate": 2.293213610642594e-06,
|
673 |
+
"loss": 1.8539,
|
674 |
+
"step": 9500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.807061790668348,
|
678 |
+
"grad_norm": 0.9112081527709961,
|
679 |
+
"learning_rate": 2.1126981443557303e-06,
|
680 |
+
"loss": 1.9095,
|
681 |
+
"step": 9600
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.8154686843211434,
|
685 |
+
"grad_norm": 1.3989226818084717,
|
686 |
+
"learning_rate": 1.9387402588049167e-06,
|
687 |
+
"loss": 1.9411,
|
688 |
+
"step": 9700
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.8238755779739386,
|
692 |
+
"grad_norm": 0.9119231104850769,
|
693 |
+
"learning_rate": 1.7714845842959415e-06,
|
694 |
+
"loss": 1.8862,
|
695 |
+
"step": 9800
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.832282471626734,
|
699 |
+
"grad_norm": 1.1409211158752441,
|
700 |
+
"learning_rate": 1.6110701788500682e-06,
|
701 |
+
"loss": 1.897,
|
702 |
+
"step": 9900
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.8406893652795292,
|
706 |
+
"grad_norm": 1.3277921676635742,
|
707 |
+
"learning_rate": 1.4576304125898234e-06,
|
708 |
+
"loss": 1.9049,
|
709 |
+
"step": 10000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.8490962589323245,
|
713 |
+
"grad_norm": 1.3236161470413208,
|
714 |
+
"learning_rate": 1.311292856853772e-06,
|
715 |
+
"loss": 1.8771,
|
716 |
+
"step": 10100
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.8575031525851198,
|
720 |
+
"grad_norm": 1.0454002618789673,
|
721 |
+
"learning_rate": 1.1721791781324343e-06,
|
722 |
+
"loss": 1.9074,
|
723 |
+
"step": 10200
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.8659100462379151,
|
727 |
+
"grad_norm": 1.196260929107666,
|
728 |
+
"learning_rate": 1.0404050369135698e-06,
|
729 |
+
"loss": 1.9241,
|
730 |
+
"step": 10300
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.8743169398907104,
|
734 |
+
"grad_norm": 1.2088180780410767,
|
735 |
+
"learning_rate": 9.160799915208962e-07,
|
736 |
+
"loss": 1.9161,
|
737 |
+
"step": 10400
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.8827238335435057,
|
741 |
+
"grad_norm": 1.2079304456710815,
|
742 |
+
"learning_rate": 7.993074070262185e-07,
|
743 |
+
"loss": 1.9722,
|
744 |
+
"step": 10500
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.8911307271963009,
|
748 |
+
"grad_norm": 0.9400559067726135,
|
749 |
+
"learning_rate": 6.901843693106935e-07,
|
750 |
+
"loss": 1.972,
|
751 |
+
"step": 10600
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.8995376208490963,
|
755 |
+
"grad_norm": 1.1368870735168457,
|
756 |
+
"learning_rate": 5.888016043466583e-07,
|
757 |
+
"loss": 1.9051,
|
758 |
+
"step": 10700
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.9079445145018915,
|
762 |
+
"grad_norm": 1.0495091676712036,
|
763 |
+
"learning_rate": 4.952434027671659e-07,
|
764 |
+
"loss": 1.8549,
|
765 |
+
"step": 10800
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.9163514081546869,
|
769 |
+
"grad_norm": 0.832502007484436,
|
770 |
+
"learning_rate": 4.095875497859192e-07,
|
771 |
+
"loss": 1.9349,
|
772 |
+
"step": 10900
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.9247583018074821,
|
776 |
+
"grad_norm": 1.295791745185852,
|
777 |
+
"learning_rate": 3.3190526052587545e-07,
|
778 |
+
"loss": 1.9073,
|
779 |
+
"step": 11000
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.9331651954602774,
|
783 |
+
"grad_norm": 0.9404931664466858,
|
784 |
+
"learning_rate": 2.6226112081028544e-07,
|
785 |
+
"loss": 1.9349,
|
786 |
+
"step": 11100
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.9415720891130728,
|
790 |
+
"grad_norm": 0.8282467722892761,
|
791 |
+
"learning_rate": 2.0071303346540505e-07,
|
792 |
+
"loss": 1.9868,
|
793 |
+
"step": 11200
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.949978982765868,
|
797 |
+
"grad_norm": 1.1069015264511108,
|
798 |
+
"learning_rate": 1.473121701795144e-07,
|
799 |
+
"loss": 1.8612,
|
800 |
+
"step": 11300
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.9583858764186634,
|
804 |
+
"grad_norm": 1.072883129119873,
|
805 |
+
"learning_rate": 1.0210292895826423e-07,
|
806 |
+
"loss": 1.8956,
|
807 |
+
"step": 11400
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.9667927700714586,
|
811 |
+
"grad_norm": 1.38330078125,
|
812 |
+
"learning_rate": 6.512289721174126e-08,
|
813 |
+
"loss": 1.9686,
|
814 |
+
"step": 11500
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.9751996637242539,
|
818 |
+
"grad_norm": 1.1821762323379517,
|
819 |
+
"learning_rate": 3.640282050392241e-08,
|
820 |
+
"loss": 1.9082,
|
821 |
+
"step": 11600
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.9836065573770492,
|
825 |
+
"grad_norm": 1.2466627359390259,
|
826 |
+
"learning_rate": 1.5966576990507078e-08,
|
827 |
+
"loss": 1.896,
|
828 |
+
"step": 11700
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.9920134510298445,
|
832 |
+
"grad_norm": 1.2905254364013672,
|
833 |
+
"learning_rate": 3.83115756638297e-09,
|
834 |
+
"loss": 1.9837,
|
835 |
+
"step": 11800
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 1.0,
|
839 |
+
"step": 11895,
|
840 |
+
"total_flos": 2.17890078425088e+17,
|
841 |
+
"train_loss": 1.9851969016204616,
|
842 |
+
"train_runtime": 3196.2319,
|
843 |
+
"train_samples_per_second": 7.443,
|
844 |
+
"train_steps_per_second": 3.722
|
845 |
+
}
|
846 |
+
],
|
847 |
+
"logging_steps": 100,
|
848 |
+
"max_steps": 11895,
|
849 |
+
"num_input_tokens_seen": 0,
|
850 |
+
"num_train_epochs": 1,
|
851 |
+
"save_steps": 500,
|
852 |
+
"stateful_callbacks": {
|
853 |
+
"TrainerControl": {
|
854 |
+
"args": {
|
855 |
+
"should_epoch_stop": false,
|
856 |
+
"should_evaluate": false,
|
857 |
+
"should_log": false,
|
858 |
+
"should_save": true,
|
859 |
+
"should_training_stop": true
|
860 |
+
},
|
861 |
+
"attributes": {}
|
862 |
+
}
|
863 |
+
},
|
864 |
+
"total_flos": 2.17890078425088e+17,
|
865 |
+
"train_batch_size": 2,
|
866 |
+
"trial_name": null,
|
867 |
+
"trial_params": null
|
868 |
+
}
|