End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +588 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: llama3-1_8b_multiple_samples_random_numina_aime
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# llama3-1_8b_multiple_samples_random_numina_aime
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: llama3-1_8b_multiple_samples_random_numina_aime
|
|
|
|
| 16 |
|
| 17 |
# llama3-1_8b_multiple_samples_random_numina_aime
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/multiple_samples_random_numina_aime dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.962025316455696,
|
| 3 |
+
"total_flos": 75607304601600.0,
|
| 4 |
+
"train_loss": 0.8077984360548166,
|
| 5 |
+
"train_runtime": 1430.59,
|
| 6 |
+
"train_samples_per_second": 5.243,
|
| 7 |
+
"train_steps_per_second": 0.055
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.962025316455696,
|
| 3 |
+
"total_flos": 75607304601600.0,
|
| 4 |
+
"train_loss": 0.8077984360548166,
|
| 5 |
+
"train_runtime": 1430.59,
|
| 6 |
+
"train_samples_per_second": 5.243,
|
| 7 |
+
"train_steps_per_second": 0.055
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,588 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.962025316455696,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 78,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0379746835443038,
|
| 13 |
+
"grad_norm": 7.233742025484269,
|
| 14 |
+
"learning_rate": 1.25e-06,
|
| 15 |
+
"loss": 1.1454,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0759493670886076,
|
| 20 |
+
"grad_norm": 6.785754420499863,
|
| 21 |
+
"learning_rate": 2.5e-06,
|
| 22 |
+
"loss": 1.0457,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.11392405063291139,
|
| 27 |
+
"grad_norm": 6.873560922195714,
|
| 28 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 29 |
+
"loss": 1.1087,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1518987341772152,
|
| 34 |
+
"grad_norm": 6.070068194853726,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 1.0456,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.189873417721519,
|
| 41 |
+
"grad_norm": 4.899244783161146,
|
| 42 |
+
"learning_rate": 6.25e-06,
|
| 43 |
+
"loss": 1.057,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.22784810126582278,
|
| 48 |
+
"grad_norm": 2.734094670545256,
|
| 49 |
+
"learning_rate": 7.500000000000001e-06,
|
| 50 |
+
"loss": 0.9376,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.26582278481012656,
|
| 55 |
+
"grad_norm": 5.184706319498115,
|
| 56 |
+
"learning_rate": 8.750000000000001e-06,
|
| 57 |
+
"loss": 1.005,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.3037974683544304,
|
| 62 |
+
"grad_norm": 5.1930383025881985,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 1.0426,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.34177215189873417,
|
| 69 |
+
"grad_norm": 5.102463875196109,
|
| 70 |
+
"learning_rate": 9.994965332706574e-06,
|
| 71 |
+
"loss": 0.9493,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.379746835443038,
|
| 76 |
+
"grad_norm": 5.025744107415969,
|
| 77 |
+
"learning_rate": 9.979871469976197e-06,
|
| 78 |
+
"loss": 1.0027,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4177215189873418,
|
| 83 |
+
"grad_norm": 3.296364051224896,
|
| 84 |
+
"learning_rate": 9.954748808839675e-06,
|
| 85 |
+
"loss": 0.964,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.45569620253164556,
|
| 90 |
+
"grad_norm": 2.1787192069360835,
|
| 91 |
+
"learning_rate": 9.91964794299315e-06,
|
| 92 |
+
"loss": 0.8481,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4936708860759494,
|
| 97 |
+
"grad_norm": 2.465515260993728,
|
| 98 |
+
"learning_rate": 9.874639560909118e-06,
|
| 99 |
+
"loss": 0.8781,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5316455696202531,
|
| 104 |
+
"grad_norm": 2.26642714838209,
|
| 105 |
+
"learning_rate": 9.819814303479268e-06,
|
| 106 |
+
"loss": 0.8506,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.569620253164557,
|
| 111 |
+
"grad_norm": 1.685223036374424,
|
| 112 |
+
"learning_rate": 9.755282581475769e-06,
|
| 113 |
+
"loss": 0.8877,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6075949367088608,
|
| 118 |
+
"grad_norm": 1.8107951485066331,
|
| 119 |
+
"learning_rate": 9.681174353198687e-06,
|
| 120 |
+
"loss": 0.8791,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6455696202531646,
|
| 125 |
+
"grad_norm": 1.9474784785519363,
|
| 126 |
+
"learning_rate": 9.597638862757255e-06,
|
| 127 |
+
"loss": 0.868,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6835443037974683,
|
| 132 |
+
"grad_norm": 1.3097181398173738,
|
| 133 |
+
"learning_rate": 9.504844339512096e-06,
|
| 134 |
+
"loss": 0.8441,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7215189873417721,
|
| 139 |
+
"grad_norm": 1.1972264295529598,
|
| 140 |
+
"learning_rate": 9.40297765928369e-06,
|
| 141 |
+
"loss": 0.835,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.759493670886076,
|
| 146 |
+
"grad_norm": 1.2739805854924195,
|
| 147 |
+
"learning_rate": 9.292243968009332e-06,
|
| 148 |
+
"loss": 0.8192,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7974683544303798,
|
| 153 |
+
"grad_norm": 0.943212312683219,
|
| 154 |
+
"learning_rate": 9.172866268606514e-06,
|
| 155 |
+
"loss": 0.8329,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8354430379746836,
|
| 160 |
+
"grad_norm": 0.848387324073507,
|
| 161 |
+
"learning_rate": 9.045084971874738e-06,
|
| 162 |
+
"loss": 0.851,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8734177215189873,
|
| 167 |
+
"grad_norm": 0.8721315678974946,
|
| 168 |
+
"learning_rate": 8.90915741234015e-06,
|
| 169 |
+
"loss": 0.7609,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9113924050632911,
|
| 174 |
+
"grad_norm": 0.8412362369012817,
|
| 175 |
+
"learning_rate": 8.765357330018056e-06,
|
| 176 |
+
"loss": 0.7978,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9493670886075949,
|
| 181 |
+
"grad_norm": 0.7847676879285055,
|
| 182 |
+
"learning_rate": 8.613974319136959e-06,
|
| 183 |
+
"loss": 0.778,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.9873417721518988,
|
| 188 |
+
"grad_norm": 0.8562323541981702,
|
| 189 |
+
"learning_rate": 8.455313244934324e-06,
|
| 190 |
+
"loss": 0.7742,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0253164556962024,
|
| 195 |
+
"grad_norm": 1.2393087482576586,
|
| 196 |
+
"learning_rate": 8.289693629698564e-06,
|
| 197 |
+
"loss": 1.2449,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.0632911392405062,
|
| 202 |
+
"grad_norm": 0.7079703595122016,
|
| 203 |
+
"learning_rate": 8.117449009293668e-06,
|
| 204 |
+
"loss": 0.7647,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.1012658227848102,
|
| 209 |
+
"grad_norm": 0.6381254299067906,
|
| 210 |
+
"learning_rate": 7.938926261462366e-06,
|
| 211 |
+
"loss": 0.7681,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.139240506329114,
|
| 216 |
+
"grad_norm": 0.5592906812359777,
|
| 217 |
+
"learning_rate": 7.754484907260513e-06,
|
| 218 |
+
"loss": 0.7634,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.1772151898734178,
|
| 223 |
+
"grad_norm": 0.6690288012490828,
|
| 224 |
+
"learning_rate": 7.564496387029532e-06,
|
| 225 |
+
"loss": 0.7772,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.2151898734177216,
|
| 230 |
+
"grad_norm": 0.5551831494766208,
|
| 231 |
+
"learning_rate": 7.369343312364994e-06,
|
| 232 |
+
"loss": 0.7518,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.2531645569620253,
|
| 237 |
+
"grad_norm": 0.682247888876666,
|
| 238 |
+
"learning_rate": 7.169418695587791e-06,
|
| 239 |
+
"loss": 0.8852,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.2911392405063291,
|
| 244 |
+
"grad_norm": 0.49353460164668184,
|
| 245 |
+
"learning_rate": 6.965125158269619e-06,
|
| 246 |
+
"loss": 0.6812,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.3291139240506329,
|
| 251 |
+
"grad_norm": 0.4852974078578067,
|
| 252 |
+
"learning_rate": 6.7568741204067145e-06,
|
| 253 |
+
"loss": 0.7192,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.3670886075949367,
|
| 258 |
+
"grad_norm": 0.6729026623142048,
|
| 259 |
+
"learning_rate": 6.545084971874738e-06,
|
| 260 |
+
"loss": 0.823,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.4050632911392404,
|
| 265 |
+
"grad_norm": 0.5868998382593021,
|
| 266 |
+
"learning_rate": 6.330184227833376e-06,
|
| 267 |
+
"loss": 0.6688,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.4430379746835442,
|
| 272 |
+
"grad_norm": 0.5900143860620642,
|
| 273 |
+
"learning_rate": 6.112604669781572e-06,
|
| 274 |
+
"loss": 0.7767,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.481012658227848,
|
| 279 |
+
"grad_norm": 0.520696165551,
|
| 280 |
+
"learning_rate": 5.892784473993184e-06,
|
| 281 |
+
"loss": 0.8102,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.518987341772152,
|
| 286 |
+
"grad_norm": 0.5849614948848969,
|
| 287 |
+
"learning_rate": 5.671166329088278e-06,
|
| 288 |
+
"loss": 0.7481,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.5569620253164556,
|
| 293 |
+
"grad_norm": 0.4842009922615296,
|
| 294 |
+
"learning_rate": 5.448196544517168e-06,
|
| 295 |
+
"loss": 0.7064,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.5949367088607596,
|
| 300 |
+
"grad_norm": 0.6090712826518998,
|
| 301 |
+
"learning_rate": 5.224324151752575e-06,
|
| 302 |
+
"loss": 0.7456,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.6329113924050633,
|
| 307 |
+
"grad_norm": 0.49266162920233386,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.6681,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.6708860759493671,
|
| 314 |
+
"grad_norm": 0.5613984339121264,
|
| 315 |
+
"learning_rate": 4.775675848247427e-06,
|
| 316 |
+
"loss": 0.7413,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.7088607594936709,
|
| 321 |
+
"grad_norm": 0.5648308497308961,
|
| 322 |
+
"learning_rate": 4.551803455482833e-06,
|
| 323 |
+
"loss": 0.8398,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.7468354430379747,
|
| 328 |
+
"grad_norm": 0.5334838340280534,
|
| 329 |
+
"learning_rate": 4.3288336709117246e-06,
|
| 330 |
+
"loss": 0.759,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.7848101265822784,
|
| 335 |
+
"grad_norm": 0.5447346237199453,
|
| 336 |
+
"learning_rate": 4.107215526006818e-06,
|
| 337 |
+
"loss": 0.718,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.8227848101265822,
|
| 342 |
+
"grad_norm": 0.4865524447115485,
|
| 343 |
+
"learning_rate": 3.887395330218429e-06,
|
| 344 |
+
"loss": 0.7301,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.8607594936708862,
|
| 349 |
+
"grad_norm": 0.47825378497206067,
|
| 350 |
+
"learning_rate": 3.669815772166625e-06,
|
| 351 |
+
"loss": 0.7541,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.8987341772151898,
|
| 356 |
+
"grad_norm": 0.5921763533888591,
|
| 357 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 358 |
+
"loss": 0.7953,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.9367088607594938,
|
| 363 |
+
"grad_norm": 0.4829282828230368,
|
| 364 |
+
"learning_rate": 3.2431258795932863e-06,
|
| 365 |
+
"loss": 0.6552,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.9746835443037973,
|
| 370 |
+
"grad_norm": 0.5114037014726881,
|
| 371 |
+
"learning_rate": 3.0348748417303826e-06,
|
| 372 |
+
"loss": 0.8745,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.0126582278481013,
|
| 377 |
+
"grad_norm": 0.7859262170640012,
|
| 378 |
+
"learning_rate": 2.83058130441221e-06,
|
| 379 |
+
"loss": 1.0096,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.050632911392405,
|
| 384 |
+
"grad_norm": 0.46684696405174964,
|
| 385 |
+
"learning_rate": 2.6306566876350072e-06,
|
| 386 |
+
"loss": 0.7132,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.088607594936709,
|
| 391 |
+
"grad_norm": 0.517786067233843,
|
| 392 |
+
"learning_rate": 2.43550361297047e-06,
|
| 393 |
+
"loss": 0.854,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.1265822784810124,
|
| 398 |
+
"grad_norm": 0.455128154085124,
|
| 399 |
+
"learning_rate": 2.245515092739488e-06,
|
| 400 |
+
"loss": 0.6703,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.1645569620253164,
|
| 405 |
+
"grad_norm": 0.4407016628670742,
|
| 406 |
+
"learning_rate": 2.061073738537635e-06,
|
| 407 |
+
"loss": 0.7363,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.2025316455696204,
|
| 412 |
+
"grad_norm": 0.4403792631608705,
|
| 413 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 414 |
+
"loss": 0.7298,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.240506329113924,
|
| 419 |
+
"grad_norm": 0.4623680749681796,
|
| 420 |
+
"learning_rate": 1.7103063703014372e-06,
|
| 421 |
+
"loss": 0.7518,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.278481012658228,
|
| 426 |
+
"grad_norm": 0.44326842914736825,
|
| 427 |
+
"learning_rate": 1.544686755065677e-06,
|
| 428 |
+
"loss": 0.7075,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.3164556962025316,
|
| 433 |
+
"grad_norm": 0.4283289272602202,
|
| 434 |
+
"learning_rate": 1.3860256808630429e-06,
|
| 435 |
+
"loss": 0.7032,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.3544303797468356,
|
| 440 |
+
"grad_norm": 0.5041856093680451,
|
| 441 |
+
"learning_rate": 1.234642669981946e-06,
|
| 442 |
+
"loss": 0.7191,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.392405063291139,
|
| 447 |
+
"grad_norm": 0.4741511129487454,
|
| 448 |
+
"learning_rate": 1.0908425876598512e-06,
|
| 449 |
+
"loss": 0.7263,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.430379746835443,
|
| 454 |
+
"grad_norm": 0.4363770783544496,
|
| 455 |
+
"learning_rate": 9.549150281252633e-07,
|
| 456 |
+
"loss": 0.7362,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.4683544303797467,
|
| 461 |
+
"grad_norm": 0.43255109702632855,
|
| 462 |
+
"learning_rate": 8.271337313934869e-07,
|
| 463 |
+
"loss": 0.681,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.5063291139240507,
|
| 468 |
+
"grad_norm": 0.4066191475356962,
|
| 469 |
+
"learning_rate": 7.077560319906696e-07,
|
| 470 |
+
"loss": 0.7316,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.5443037974683547,
|
| 475 |
+
"grad_norm": 0.40393602082830354,
|
| 476 |
+
"learning_rate": 5.9702234071631e-07,
|
| 477 |
+
"loss": 0.6585,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.5822784810126582,
|
| 482 |
+
"grad_norm": 0.4378157851570328,
|
| 483 |
+
"learning_rate": 4.951556604879049e-07,
|
| 484 |
+
"loss": 0.7468,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.620253164556962,
|
| 489 |
+
"grad_norm": 0.39439431826838517,
|
| 490 |
+
"learning_rate": 4.0236113724274716e-07,
|
| 491 |
+
"loss": 0.6613,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.6582278481012658,
|
| 496 |
+
"grad_norm": 0.43181499146604313,
|
| 497 |
+
"learning_rate": 3.18825646801314e-07,
|
| 498 |
+
"loss": 0.7306,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.6962025316455698,
|
| 503 |
+
"grad_norm": 0.42106461119949756,
|
| 504 |
+
"learning_rate": 2.447174185242324e-07,
|
| 505 |
+
"loss": 0.7387,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.7341772151898733,
|
| 510 |
+
"grad_norm": 0.4140210199949433,
|
| 511 |
+
"learning_rate": 1.801856965207338e-07,
|
| 512 |
+
"loss": 0.7686,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.7721518987341773,
|
| 517 |
+
"grad_norm": 0.43164253148923615,
|
| 518 |
+
"learning_rate": 1.253604390908819e-07,
|
| 519 |
+
"loss": 0.7474,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.810126582278481,
|
| 524 |
+
"grad_norm": 0.366892032697455,
|
| 525 |
+
"learning_rate": 8.035205700685167e-08,
|
| 526 |
+
"loss": 0.6236,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.848101265822785,
|
| 531 |
+
"grad_norm": 0.3812258333922781,
|
| 532 |
+
"learning_rate": 4.52511911603265e-08,
|
| 533 |
+
"loss": 0.7079,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.8860759493670884,
|
| 538 |
+
"grad_norm": 0.40957061725247956,
|
| 539 |
+
"learning_rate": 2.012853002380466e-08,
|
| 540 |
+
"loss": 0.7319,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.9240506329113924,
|
| 545 |
+
"grad_norm": 0.3707924195450794,
|
| 546 |
+
"learning_rate": 5.034667293427053e-09,
|
| 547 |
+
"loss": 0.7077,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.962025316455696,
|
| 552 |
+
"grad_norm": 0.4328169844138338,
|
| 553 |
+
"learning_rate": 0.0,
|
| 554 |
+
"loss": 0.7367,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.962025316455696,
|
| 559 |
+
"step": 78,
|
| 560 |
+
"total_flos": 75607304601600.0,
|
| 561 |
+
"train_loss": 0.8077984360548166,
|
| 562 |
+
"train_runtime": 1430.59,
|
| 563 |
+
"train_samples_per_second": 5.243,
|
| 564 |
+
"train_steps_per_second": 0.055
|
| 565 |
+
}
|
| 566 |
+
],
|
| 567 |
+
"logging_steps": 1,
|
| 568 |
+
"max_steps": 78,
|
| 569 |
+
"num_input_tokens_seen": 0,
|
| 570 |
+
"num_train_epochs": 3,
|
| 571 |
+
"save_steps": 500,
|
| 572 |
+
"stateful_callbacks": {
|
| 573 |
+
"TrainerControl": {
|
| 574 |
+
"args": {
|
| 575 |
+
"should_epoch_stop": false,
|
| 576 |
+
"should_evaluate": false,
|
| 577 |
+
"should_log": false,
|
| 578 |
+
"should_save": true,
|
| 579 |
+
"should_training_stop": true
|
| 580 |
+
},
|
| 581 |
+
"attributes": {}
|
| 582 |
+
}
|
| 583 |
+
},
|
| 584 |
+
"total_flos": 75607304601600.0,
|
| 585 |
+
"train_batch_size": 1,
|
| 586 |
+
"trial_name": null,
|
| 587 |
+
"trial_params": null
|
| 588 |
+
}
|
training_loss.png
ADDED
|