FastPlus125m Geodesic Backup checkpoint-600 at global step 600
Browse files- checkpoint-600/config.json +20 -0
- checkpoint-600/generation_config.json +6 -0
- checkpoint-600/model.safetensors +3 -0
- checkpoint-600/optimizer.pt +3 -0
- checkpoint-600/scaler.pt +3 -0
- checkpoint-600/scheduler.pt +3 -0
- checkpoint-600/tokenizer.json +0 -0
- checkpoint-600/tokenizer_config.json +13 -0
- checkpoint-600/trainer_state.json +514 -0
checkpoint-600/config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"FastPlus125mForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"hidden_size": 768,
|
| 7 |
+
"hyperbolic_dim": 16,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"intermediate_size": 2048,
|
| 10 |
+
"kd_alpha": 0.4,
|
| 11 |
+
"kd_temperature": 2.5,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "fastplus_125m",
|
| 14 |
+
"num_attention_heads": 12,
|
| 15 |
+
"num_hidden_layers": 16,
|
| 16 |
+
"tie_word_embeddings": false,
|
| 17 |
+
"transformers_version": "5.13.1",
|
| 18 |
+
"use_cache": false,
|
| 19 |
+
"vocab_size": 31776
|
| 20 |
+
}
|
checkpoint-600/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"output_attentions": false,
|
| 4 |
+
"output_hidden_states": false,
|
| 5 |
+
"transformers_version": "5.13.1"
|
| 6 |
+
}
|
checkpoint-600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c54c2086530c6139766b3280c460bb04cb4dad7915c29b2c6c457f5adddaf81
|
| 3 |
+
size 574958720
|
checkpoint-600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96802a8745447d7005b3e6b5a355cfafcfb30f3316b63274ab271b45a29d42df
|
| 3 |
+
size 1138512619
|
checkpoint-600/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83d454595949e51bcf2a631b4e8b9ff94c37c1b3987b96e770018bf7d507c9c3
|
| 3 |
+
size 1383
|
checkpoint-600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be266c6d929d57556ab62418e35d934e31d6641e9a01459a606de43e9f20ad50
|
| 3 |
+
size 8953
|
checkpoint-600/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-600/tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"extra_special_tokens": [
|
| 6 |
+
"<|user|>",
|
| 7 |
+
"<|assistant|>"
|
| 8 |
+
],
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"tokenizer_class": "TokenizersBackend",
|
| 12 |
+
"unk_token": "<unk>"
|
| 13 |
+
}
|
checkpoint-600/trainer_state.json
ADDED
|
@@ -0,0 +1,514 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.022021715858693988,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 600,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0003670285976448998,
|
| 14 |
+
"grad_norm": 681.37451171875,
|
| 15 |
+
"learning_rate": 1.4999999999999998e-06,
|
| 16 |
+
"lorentz_dist_loss": 14.6063,
|
| 17 |
+
"loss": 14.6063,
|
| 18 |
+
"step": 10
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.0007340571952897996,
|
| 22 |
+
"grad_norm": 435.6217041015625,
|
| 23 |
+
"learning_rate": 4.499999999999999e-06,
|
| 24 |
+
"lorentz_dist_loss": 13.8718,
|
| 25 |
+
"loss": 13.8719,
|
| 26 |
+
"step": 20
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.0011010857929346996,
|
| 30 |
+
"grad_norm": 145.8190155029297,
|
| 31 |
+
"learning_rate": 7.499999999999999e-06,
|
| 32 |
+
"lorentz_dist_loss": 13.0863,
|
| 33 |
+
"loss": 13.0864,
|
| 34 |
+
"step": 30
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.0014681143905795992,
|
| 38 |
+
"grad_norm": 65.10393524169922,
|
| 39 |
+
"learning_rate": 1.05e-05,
|
| 40 |
+
"lorentz_dist_loss": 12.7917,
|
| 41 |
+
"loss": 12.7918,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.001835142988224499,
|
| 46 |
+
"grad_norm": 66.46527862548828,
|
| 47 |
+
"learning_rate": 1.3499999999999998e-05,
|
| 48 |
+
"lorentz_dist_loss": 12.5774,
|
| 49 |
+
"loss": 12.5774,
|
| 50 |
+
"step": 50
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.002202171585869399,
|
| 54 |
+
"grad_norm": 441.29400634765625,
|
| 55 |
+
"learning_rate": 1.6499999999999998e-05,
|
| 56 |
+
"lorentz_dist_loss": 12.2898,
|
| 57 |
+
"loss": 12.2898,
|
| 58 |
+
"step": 60
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.002569200183514299,
|
| 62 |
+
"grad_norm": 640.6945190429688,
|
| 63 |
+
"learning_rate": 1.95e-05,
|
| 64 |
+
"lorentz_dist_loss": 11.7915,
|
| 65 |
+
"loss": 11.7915,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0029362287811591985,
|
| 70 |
+
"grad_norm": 1081.7047119140625,
|
| 71 |
+
"learning_rate": 2.2199999999999998e-05,
|
| 72 |
+
"lorentz_dist_loss": 11.021,
|
| 73 |
+
"loss": 11.021,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.0033032573788040983,
|
| 78 |
+
"grad_norm": 970.2308959960938,
|
| 79 |
+
"learning_rate": 2.52e-05,
|
| 80 |
+
"lorentz_dist_loss": 10.5144,
|
| 81 |
+
"loss": 10.5144,
|
| 82 |
+
"step": 90
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.003670285976448998,
|
| 86 |
+
"grad_norm": 652.1952514648438,
|
| 87 |
+
"learning_rate": 2.8199999999999998e-05,
|
| 88 |
+
"lorentz_dist_loss": 10.2136,
|
| 89 |
+
"loss": 10.2137,
|
| 90 |
+
"step": 100
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.0040373145740938985,
|
| 94 |
+
"grad_norm": 786.8927001953125,
|
| 95 |
+
"learning_rate": 3.119999999999999e-05,
|
| 96 |
+
"lorentz_dist_loss": 10.0538,
|
| 97 |
+
"loss": 10.0539,
|
| 98 |
+
"step": 110
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.004404343171738798,
|
| 102 |
+
"grad_norm": 752.5087280273438,
|
| 103 |
+
"learning_rate": 3.42e-05,
|
| 104 |
+
"lorentz_dist_loss": 10.0275,
|
| 105 |
+
"loss": 10.0275,
|
| 106 |
+
"step": 120
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.004771371769383698,
|
| 110 |
+
"grad_norm": 771.0545654296875,
|
| 111 |
+
"learning_rate": 3.7199999999999996e-05,
|
| 112 |
+
"lorentz_dist_loss": 9.9781,
|
| 113 |
+
"loss": 9.9781,
|
| 114 |
+
"step": 130
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.005138400367028598,
|
| 118 |
+
"grad_norm": 661.6411743164062,
|
| 119 |
+
"learning_rate": 4.02e-05,
|
| 120 |
+
"lorentz_dist_loss": 9.9007,
|
| 121 |
+
"loss": 9.9007,
|
| 122 |
+
"step": 140
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.005505428964673497,
|
| 126 |
+
"grad_norm": 797.857421875,
|
| 127 |
+
"learning_rate": 4.319999999999999e-05,
|
| 128 |
+
"lorentz_dist_loss": 9.9161,
|
| 129 |
+
"loss": 9.9162,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.005872457562318397,
|
| 134 |
+
"grad_norm": 745.4788208007812,
|
| 135 |
+
"learning_rate": 4.62e-05,
|
| 136 |
+
"lorentz_dist_loss": 9.8578,
|
| 137 |
+
"loss": 9.8578,
|
| 138 |
+
"step": 160
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.006239486159963297,
|
| 142 |
+
"grad_norm": 848.5892944335938,
|
| 143 |
+
"learning_rate": 4.9199999999999997e-05,
|
| 144 |
+
"lorentz_dist_loss": 9.8015,
|
| 145 |
+
"loss": 9.8015,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.006606514757608197,
|
| 150 |
+
"grad_norm": 737.6754760742188,
|
| 151 |
+
"learning_rate": 5.1899999999999994e-05,
|
| 152 |
+
"lorentz_dist_loss": 9.7546,
|
| 153 |
+
"loss": 9.7546,
|
| 154 |
+
"step": 180
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.0069735433552530965,
|
| 158 |
+
"grad_norm": 863.2762451171875,
|
| 159 |
+
"learning_rate": 5.489999999999999e-05,
|
| 160 |
+
"lorentz_dist_loss": 9.7037,
|
| 161 |
+
"loss": 9.7037,
|
| 162 |
+
"step": 190
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.007340571952897996,
|
| 166 |
+
"grad_norm": 797.9078369140625,
|
| 167 |
+
"learning_rate": 5.79e-05,
|
| 168 |
+
"lorentz_dist_loss": 9.6112,
|
| 169 |
+
"loss": 9.6112,
|
| 170 |
+
"step": 200
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.007707600550542896,
|
| 174 |
+
"grad_norm": 690.6722412109375,
|
| 175 |
+
"learning_rate": 6.0899999999999996e-05,
|
| 176 |
+
"lorentz_dist_loss": 9.4947,
|
| 177 |
+
"loss": 9.4947,
|
| 178 |
+
"step": 210
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.008074629148187797,
|
| 182 |
+
"grad_norm": 776.2643432617188,
|
| 183 |
+
"learning_rate": 6.39e-05,
|
| 184 |
+
"lorentz_dist_loss": 9.5267,
|
| 185 |
+
"loss": 9.5268,
|
| 186 |
+
"step": 220
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.008441657745832696,
|
| 190 |
+
"grad_norm": 648.8978271484375,
|
| 191 |
+
"learning_rate": 6.69e-05,
|
| 192 |
+
"lorentz_dist_loss": 9.4173,
|
| 193 |
+
"loss": 9.4173,
|
| 194 |
+
"step": 230
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.008808686343477597,
|
| 198 |
+
"grad_norm": 665.095458984375,
|
| 199 |
+
"learning_rate": 6.989999999999999e-05,
|
| 200 |
+
"lorentz_dist_loss": 9.4442,
|
| 201 |
+
"loss": 9.4443,
|
| 202 |
+
"step": 240
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.009175714941122496,
|
| 206 |
+
"grad_norm": 643.8400268554688,
|
| 207 |
+
"learning_rate": 7.29e-05,
|
| 208 |
+
"lorentz_dist_loss": 9.3834,
|
| 209 |
+
"loss": 9.3834,
|
| 210 |
+
"step": 250
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.009542743538767396,
|
| 214 |
+
"grad_norm": 637.7966918945312,
|
| 215 |
+
"learning_rate": 7.589999999999999e-05,
|
| 216 |
+
"lorentz_dist_loss": 9.2921,
|
| 217 |
+
"loss": 9.2921,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.009909772136412295,
|
| 222 |
+
"grad_norm": 540.0435791015625,
|
| 223 |
+
"learning_rate": 7.89e-05,
|
| 224 |
+
"lorentz_dist_loss": 9.2803,
|
| 225 |
+
"loss": 9.2803,
|
| 226 |
+
"step": 270
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.010276800734057196,
|
| 230 |
+
"grad_norm": 510.450927734375,
|
| 231 |
+
"learning_rate": 8.19e-05,
|
| 232 |
+
"lorentz_dist_loss": 9.1877,
|
| 233 |
+
"loss": 9.1877,
|
| 234 |
+
"step": 280
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.010643829331702095,
|
| 238 |
+
"grad_norm": 634.0109252929688,
|
| 239 |
+
"learning_rate": 8.489999999999999e-05,
|
| 240 |
+
"lorentz_dist_loss": 9.1635,
|
| 241 |
+
"loss": 9.1635,
|
| 242 |
+
"step": 290
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.011010857929346994,
|
| 246 |
+
"grad_norm": 535.3104248046875,
|
| 247 |
+
"learning_rate": 8.789999999999998e-05,
|
| 248 |
+
"lorentz_dist_loss": 9.0436,
|
| 249 |
+
"loss": 9.0436,
|
| 250 |
+
"step": 300
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.011377886526991895,
|
| 254 |
+
"grad_norm": 831.6660766601562,
|
| 255 |
+
"learning_rate": 9.089999999999999e-05,
|
| 256 |
+
"lorentz_dist_loss": 8.9789,
|
| 257 |
+
"loss": 8.9789,
|
| 258 |
+
"step": 310
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.011744915124636794,
|
| 262 |
+
"grad_norm": 582.4743041992188,
|
| 263 |
+
"learning_rate": 9.389999999999999e-05,
|
| 264 |
+
"lorentz_dist_loss": 8.9264,
|
| 265 |
+
"loss": 8.9264,
|
| 266 |
+
"step": 320
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.012111943722281695,
|
| 270 |
+
"grad_norm": 661.2618408203125,
|
| 271 |
+
"learning_rate": 9.69e-05,
|
| 272 |
+
"lorentz_dist_loss": 8.8603,
|
| 273 |
+
"loss": 8.8603,
|
| 274 |
+
"step": 330
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.012478972319926594,
|
| 278 |
+
"grad_norm": 741.7787475585938,
|
| 279 |
+
"learning_rate": 9.99e-05,
|
| 280 |
+
"lorentz_dist_loss": 8.7898,
|
| 281 |
+
"loss": 8.7898,
|
| 282 |
+
"step": 340
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.012846000917571494,
|
| 286 |
+
"grad_norm": 568.54931640625,
|
| 287 |
+
"learning_rate": 0.0001029,
|
| 288 |
+
"lorentz_dist_loss": 8.7997,
|
| 289 |
+
"loss": 8.7998,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.013213029515216393,
|
| 294 |
+
"grad_norm": 953.4234008789062,
|
| 295 |
+
"learning_rate": 0.00010589999999999999,
|
| 296 |
+
"lorentz_dist_loss": 8.796,
|
| 297 |
+
"loss": 8.7961,
|
| 298 |
+
"step": 360
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.013580058112861294,
|
| 302 |
+
"grad_norm": 675.1668701171875,
|
| 303 |
+
"learning_rate": 0.00010889999999999999,
|
| 304 |
+
"lorentz_dist_loss": 8.7294,
|
| 305 |
+
"loss": 8.7294,
|
| 306 |
+
"step": 370
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.013947086710506193,
|
| 310 |
+
"grad_norm": 628.8242797851562,
|
| 311 |
+
"learning_rate": 0.0001119,
|
| 312 |
+
"lorentz_dist_loss": 8.6696,
|
| 313 |
+
"loss": 8.6696,
|
| 314 |
+
"step": 380
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.014314115308151094,
|
| 318 |
+
"grad_norm": 431.89910888671875,
|
| 319 |
+
"learning_rate": 0.00011489999999999999,
|
| 320 |
+
"lorentz_dist_loss": 8.5873,
|
| 321 |
+
"loss": 8.5873,
|
| 322 |
+
"step": 390
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.014681143905795993,
|
| 326 |
+
"grad_norm": 834.5965576171875,
|
| 327 |
+
"learning_rate": 0.00011789999999999999,
|
| 328 |
+
"lorentz_dist_loss": 8.5694,
|
| 329 |
+
"loss": 8.5695,
|
| 330 |
+
"step": 400
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.015048172503440893,
|
| 334 |
+
"grad_norm": 512.3103637695312,
|
| 335 |
+
"learning_rate": 0.0001209,
|
| 336 |
+
"lorentz_dist_loss": 8.5211,
|
| 337 |
+
"loss": 8.5211,
|
| 338 |
+
"step": 410
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.015415201101085792,
|
| 342 |
+
"grad_norm": 646.5181274414062,
|
| 343 |
+
"learning_rate": 0.00012389999999999998,
|
| 344 |
+
"lorentz_dist_loss": 8.4105,
|
| 345 |
+
"loss": 8.4105,
|
| 346 |
+
"step": 420
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.015782229698730693,
|
| 350 |
+
"grad_norm": 473.6522216796875,
|
| 351 |
+
"learning_rate": 0.0001269,
|
| 352 |
+
"lorentz_dist_loss": 8.4044,
|
| 353 |
+
"loss": 8.4044,
|
| 354 |
+
"step": 430
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.016149258296375594,
|
| 358 |
+
"grad_norm": 449.62054443359375,
|
| 359 |
+
"learning_rate": 0.00012989999999999999,
|
| 360 |
+
"lorentz_dist_loss": 8.3709,
|
| 361 |
+
"loss": 8.3709,
|
| 362 |
+
"step": 440
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.01651628689402049,
|
| 366 |
+
"grad_norm": 412.67559814453125,
|
| 367 |
+
"learning_rate": 0.00013289999999999998,
|
| 368 |
+
"lorentz_dist_loss": 8.313,
|
| 369 |
+
"loss": 8.313,
|
| 370 |
+
"step": 450
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.016883315491665392,
|
| 374 |
+
"grad_norm": 376.6106872558594,
|
| 375 |
+
"learning_rate": 0.0001359,
|
| 376 |
+
"lorentz_dist_loss": 8.2483,
|
| 377 |
+
"loss": 8.2484,
|
| 378 |
+
"step": 460
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.017250344089310293,
|
| 382 |
+
"grad_norm": 362.41845703125,
|
| 383 |
+
"learning_rate": 0.0001389,
|
| 384 |
+
"lorentz_dist_loss": 8.2301,
|
| 385 |
+
"loss": 8.2301,
|
| 386 |
+
"step": 470
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.017617372686955193,
|
| 390 |
+
"grad_norm": 534.7227783203125,
|
| 391 |
+
"learning_rate": 0.00014189999999999998,
|
| 392 |
+
"lorentz_dist_loss": 8.1632,
|
| 393 |
+
"loss": 8.1632,
|
| 394 |
+
"step": 480
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.01798440128460009,
|
| 398 |
+
"grad_norm": 477.5787353515625,
|
| 399 |
+
"learning_rate": 0.00014489999999999997,
|
| 400 |
+
"lorentz_dist_loss": 8.0754,
|
| 401 |
+
"loss": 8.0754,
|
| 402 |
+
"step": 490
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.01835142988224499,
|
| 406 |
+
"grad_norm": 595.6251831054688,
|
| 407 |
+
"learning_rate": 0.0001479,
|
| 408 |
+
"lorentz_dist_loss": 8.0402,
|
| 409 |
+
"loss": 8.0402,
|
| 410 |
+
"step": 500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.018718458479889892,
|
| 414 |
+
"grad_norm": 404.488525390625,
|
| 415 |
+
"learning_rate": 0.00015089999999999998,
|
| 416 |
+
"lorentz_dist_loss": 8.0425,
|
| 417 |
+
"loss": 8.0426,
|
| 418 |
+
"step": 510
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.019085487077534793,
|
| 422 |
+
"grad_norm": 413.10333251953125,
|
| 423 |
+
"learning_rate": 0.0001539,
|
| 424 |
+
"lorentz_dist_loss": 8.0348,
|
| 425 |
+
"loss": 8.0348,
|
| 426 |
+
"step": 520
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.01945251567517969,
|
| 430 |
+
"grad_norm": 435.5134582519531,
|
| 431 |
+
"learning_rate": 0.0001569,
|
| 432 |
+
"lorentz_dist_loss": 7.918,
|
| 433 |
+
"loss": 7.918,
|
| 434 |
+
"step": 530
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.01981954427282459,
|
| 438 |
+
"grad_norm": 645.5552368164062,
|
| 439 |
+
"learning_rate": 0.00015989999999999998,
|
| 440 |
+
"lorentz_dist_loss": 7.9234,
|
| 441 |
+
"loss": 7.9234,
|
| 442 |
+
"step": 540
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.02018657287046949,
|
| 446 |
+
"grad_norm": 555.9960327148438,
|
| 447 |
+
"learning_rate": 0.0001629,
|
| 448 |
+
"lorentz_dist_loss": 7.9365,
|
| 449 |
+
"loss": 7.9365,
|
| 450 |
+
"step": 550
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.020553601468114392,
|
| 454 |
+
"grad_norm": 459.4711608886719,
|
| 455 |
+
"learning_rate": 0.0001659,
|
| 456 |
+
"lorentz_dist_loss": 7.8408,
|
| 457 |
+
"loss": 7.8408,
|
| 458 |
+
"step": 560
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.02092063006575929,
|
| 462 |
+
"grad_norm": 537.4147338867188,
|
| 463 |
+
"learning_rate": 0.00016889999999999996,
|
| 464 |
+
"lorentz_dist_loss": 7.7659,
|
| 465 |
+
"loss": 7.766,
|
| 466 |
+
"step": 570
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.02128765866340419,
|
| 470 |
+
"grad_norm": 340.6890563964844,
|
| 471 |
+
"learning_rate": 0.00017189999999999998,
|
| 472 |
+
"lorentz_dist_loss": 7.7269,
|
| 473 |
+
"loss": 7.727,
|
| 474 |
+
"step": 580
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.02165468726104909,
|
| 478 |
+
"grad_norm": 666.5643920898438,
|
| 479 |
+
"learning_rate": 0.00017489999999999997,
|
| 480 |
+
"lorentz_dist_loss": 7.7274,
|
| 481 |
+
"loss": 7.7274,
|
| 482 |
+
"step": 590
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.022021715858693988,
|
| 486 |
+
"grad_norm": 418.54901123046875,
|
| 487 |
+
"learning_rate": 0.0001779,
|
| 488 |
+
"lorentz_dist_loss": 7.6529,
|
| 489 |
+
"loss": 7.6529,
|
| 490 |
+
"step": 600
|
| 491 |
+
}
|
| 492 |
+
],
|
| 493 |
+
"logging_steps": 10,
|
| 494 |
+
"max_steps": 54492,
|
| 495 |
+
"num_input_tokens_seen": 0,
|
| 496 |
+
"num_train_epochs": 2,
|
| 497 |
+
"save_steps": 200,
|
| 498 |
+
"stateful_callbacks": {
|
| 499 |
+
"TrainerControl": {
|
| 500 |
+
"args": {
|
| 501 |
+
"should_epoch_stop": false,
|
| 502 |
+
"should_evaluate": false,
|
| 503 |
+
"should_log": false,
|
| 504 |
+
"should_save": true,
|
| 505 |
+
"should_training_stop": false
|
| 506 |
+
},
|
| 507 |
+
"attributes": {}
|
| 508 |
+
}
|
| 509 |
+
},
|
| 510 |
+
"total_flos": 1.4607882683006976e+16,
|
| 511 |
+
"train_batch_size": 12,
|
| 512 |
+
"trial_name": null,
|
| 513 |
+
"trial_params": null
|
| 514 |
+
}
|