Upload 8 files
Browse files- checkpoint-30000/config.json +41 -0
- checkpoint-30000/generation_config.json +6 -0
- checkpoint-30000/model.safetensors +3 -0
- checkpoint-30000/optimizer.pt +3 -0
- checkpoint-30000/rng_state.pth +3 -0
- checkpoint-30000/scheduler.pt +3 -0
- checkpoint-30000/trainer_state.json +441 -0
- checkpoint-30000/training_args.bin +3 -0
checkpoint-30000/config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2-medium",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 1024,
|
| 16 |
+
"n_head": 16,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 24,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"n_special": 0,
|
| 21 |
+
"predict_special_tokens": true,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.40.1",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50257
|
| 41 |
+
}
|
checkpoint-30000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.40.1"
|
| 6 |
+
}
|
checkpoint-30000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8a064467bba093f4444cd8968436585a9fa01fccccc3a4e66b500a70f78a996
|
| 3 |
+
size 1419322880
|
checkpoint-30000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8eab8775c475ee2a2cc0d24bee903f1973853a384f9cf0cacd20cd21b8ffec7
|
| 3 |
+
size 2838821114
|
checkpoint-30000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7fe6156eef579c116432975c77518c313115b2a974a0ecb7fc2cf5edf6599e3
|
| 3 |
+
size 13990
|
checkpoint-30000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc715503f2e2827c00e1f5118462c86a239e5f587ae7b95f7aa541b84f5f36da
|
| 3 |
+
size 1064
|
checkpoint-30000/trainer_state.json
ADDED
|
@@ -0,0 +1,441 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.8333333333333334,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 30000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.013888888888888888,
|
| 13 |
+
"grad_norm": 33.87594223022461,
|
| 14 |
+
"learning_rate": 4.930555555555556e-05,
|
| 15 |
+
"loss": 2.5607,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.027777777777777776,
|
| 20 |
+
"grad_norm": 19.041858673095703,
|
| 21 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 22 |
+
"loss": 2.3205,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.041666666666666664,
|
| 27 |
+
"grad_norm": 22.798561096191406,
|
| 28 |
+
"learning_rate": 4.791666666666667e-05,
|
| 29 |
+
"loss": 2.2861,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05555555555555555,
|
| 34 |
+
"grad_norm": 26.49089241027832,
|
| 35 |
+
"learning_rate": 4.722222222222222e-05,
|
| 36 |
+
"loss": 2.256,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06944444444444445,
|
| 41 |
+
"grad_norm": 19.455162048339844,
|
| 42 |
+
"learning_rate": 4.652777777777778e-05,
|
| 43 |
+
"loss": 2.2464,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.08333333333333333,
|
| 48 |
+
"grad_norm": 19.90087890625,
|
| 49 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 50 |
+
"loss": 2.2445,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09722222222222222,
|
| 55 |
+
"grad_norm": 15.378240585327148,
|
| 56 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 57 |
+
"loss": 2.2345,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1111111111111111,
|
| 62 |
+
"grad_norm": 17.459095001220703,
|
| 63 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 64 |
+
"loss": 2.2252,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.125,
|
| 69 |
+
"grad_norm": 23.182748794555664,
|
| 70 |
+
"learning_rate": 4.375e-05,
|
| 71 |
+
"loss": 2.2134,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1388888888888889,
|
| 76 |
+
"grad_norm": 19.53196144104004,
|
| 77 |
+
"learning_rate": 4.305555555555556e-05,
|
| 78 |
+
"loss": 2.2168,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.1527777777777778,
|
| 83 |
+
"grad_norm": 15.988591194152832,
|
| 84 |
+
"learning_rate": 4.236111111111111e-05,
|
| 85 |
+
"loss": 2.2232,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.16666666666666666,
|
| 90 |
+
"grad_norm": 16.655384063720703,
|
| 91 |
+
"learning_rate": 4.166666666666667e-05,
|
| 92 |
+
"loss": 2.2147,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.18055555555555555,
|
| 97 |
+
"grad_norm": 14.632539749145508,
|
| 98 |
+
"learning_rate": 4.0972222222222225e-05,
|
| 99 |
+
"loss": 2.1922,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.19444444444444445,
|
| 104 |
+
"grad_norm": 13.886147499084473,
|
| 105 |
+
"learning_rate": 4.027777777777778e-05,
|
| 106 |
+
"loss": 2.2036,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.20833333333333334,
|
| 111 |
+
"grad_norm": 13.439935684204102,
|
| 112 |
+
"learning_rate": 3.958333333333333e-05,
|
| 113 |
+
"loss": 2.1865,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2222222222222222,
|
| 118 |
+
"grad_norm": 10.455207824707031,
|
| 119 |
+
"learning_rate": 3.888888888888889e-05,
|
| 120 |
+
"loss": 2.1794,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.2361111111111111,
|
| 125 |
+
"grad_norm": 17.11553382873535,
|
| 126 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 127 |
+
"loss": 2.2025,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.25,
|
| 132 |
+
"grad_norm": 14.08956527709961,
|
| 133 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 134 |
+
"loss": 2.1867,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2638888888888889,
|
| 139 |
+
"grad_norm": 13.953351020812988,
|
| 140 |
+
"learning_rate": 3.6805555555555556e-05,
|
| 141 |
+
"loss": 2.1651,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2777777777777778,
|
| 146 |
+
"grad_norm": 10.86223030090332,
|
| 147 |
+
"learning_rate": 3.611111111111111e-05,
|
| 148 |
+
"loss": 2.1835,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2916666666666667,
|
| 153 |
+
"grad_norm": 10.25207805633545,
|
| 154 |
+
"learning_rate": 3.541666666666667e-05,
|
| 155 |
+
"loss": 2.1831,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.3055555555555556,
|
| 160 |
+
"grad_norm": 10.212087631225586,
|
| 161 |
+
"learning_rate": 3.472222222222222e-05,
|
| 162 |
+
"loss": 2.1699,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3194444444444444,
|
| 167 |
+
"grad_norm": 8.576708793640137,
|
| 168 |
+
"learning_rate": 3.402777777777778e-05,
|
| 169 |
+
"loss": 2.1689,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3333333333333333,
|
| 174 |
+
"grad_norm": 7.758203506469727,
|
| 175 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 176 |
+
"loss": 2.1726,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3472222222222222,
|
| 181 |
+
"grad_norm": 10.195472717285156,
|
| 182 |
+
"learning_rate": 3.263888888888889e-05,
|
| 183 |
+
"loss": 2.1753,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3611111111111111,
|
| 188 |
+
"grad_norm": 7.407456398010254,
|
| 189 |
+
"learning_rate": 3.194444444444444e-05,
|
| 190 |
+
"loss": 2.1825,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.375,
|
| 195 |
+
"grad_norm": 8.167924880981445,
|
| 196 |
+
"learning_rate": 3.125e-05,
|
| 197 |
+
"loss": 2.1762,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3888888888888889,
|
| 202 |
+
"grad_norm": 7.759510517120361,
|
| 203 |
+
"learning_rate": 3.055555555555556e-05,
|
| 204 |
+
"loss": 2.1687,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.4027777777777778,
|
| 209 |
+
"grad_norm": 8.27856731414795,
|
| 210 |
+
"learning_rate": 2.9861111111111113e-05,
|
| 211 |
+
"loss": 2.18,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.4166666666666667,
|
| 216 |
+
"grad_norm": 8.577377319335938,
|
| 217 |
+
"learning_rate": 2.916666666666667e-05,
|
| 218 |
+
"loss": 2.1718,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4305555555555556,
|
| 223 |
+
"grad_norm": 7.465952396392822,
|
| 224 |
+
"learning_rate": 2.8472222222222223e-05,
|
| 225 |
+
"loss": 2.1778,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4444444444444444,
|
| 230 |
+
"grad_norm": 6.5437331199646,
|
| 231 |
+
"learning_rate": 2.777777777777778e-05,
|
| 232 |
+
"loss": 2.1756,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4583333333333333,
|
| 237 |
+
"grad_norm": 9.449009895324707,
|
| 238 |
+
"learning_rate": 2.7083333333333332e-05,
|
| 239 |
+
"loss": 2.1608,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4722222222222222,
|
| 244 |
+
"grad_norm": 5.527251243591309,
|
| 245 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 246 |
+
"loss": 2.1742,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4861111111111111,
|
| 251 |
+
"grad_norm": 6.589778423309326,
|
| 252 |
+
"learning_rate": 2.5694444444444445e-05,
|
| 253 |
+
"loss": 2.1754,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5,
|
| 258 |
+
"grad_norm": 7.19509744644165,
|
| 259 |
+
"learning_rate": 2.5e-05,
|
| 260 |
+
"loss": 2.1715,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5138888888888888,
|
| 265 |
+
"grad_norm": 6.292264938354492,
|
| 266 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 267 |
+
"loss": 2.1555,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5277777777777778,
|
| 272 |
+
"grad_norm": 7.13681697845459,
|
| 273 |
+
"learning_rate": 2.361111111111111e-05,
|
| 274 |
+
"loss": 2.1603,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5416666666666666,
|
| 279 |
+
"grad_norm": 6.618354320526123,
|
| 280 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 281 |
+
"loss": 2.1636,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5555555555555556,
|
| 286 |
+
"grad_norm": 6.527144908905029,
|
| 287 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 288 |
+
"loss": 2.1617,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5694444444444444,
|
| 293 |
+
"grad_norm": 6.159780502319336,
|
| 294 |
+
"learning_rate": 2.152777777777778e-05,
|
| 295 |
+
"loss": 2.1589,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5833333333333334,
|
| 300 |
+
"grad_norm": 4.256960391998291,
|
| 301 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 302 |
+
"loss": 2.1598,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5972222222222222,
|
| 307 |
+
"grad_norm": 7.228523254394531,
|
| 308 |
+
"learning_rate": 2.013888888888889e-05,
|
| 309 |
+
"loss": 2.1534,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6111111111111112,
|
| 314 |
+
"grad_norm": 8.4286470413208,
|
| 315 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 316 |
+
"loss": 2.153,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.625,
|
| 321 |
+
"grad_norm": 5.6604461669921875,
|
| 322 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 323 |
+
"loss": 2.1584,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6388888888888888,
|
| 328 |
+
"grad_norm": 6.379817485809326,
|
| 329 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 330 |
+
"loss": 2.1542,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6527777777777778,
|
| 335 |
+
"grad_norm": 8.91696834564209,
|
| 336 |
+
"learning_rate": 1.736111111111111e-05,
|
| 337 |
+
"loss": 2.1728,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6666666666666666,
|
| 342 |
+
"grad_norm": 7.987995624542236,
|
| 343 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 344 |
+
"loss": 2.1625,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6805555555555556,
|
| 349 |
+
"grad_norm": 5.483871936798096,
|
| 350 |
+
"learning_rate": 1.597222222222222e-05,
|
| 351 |
+
"loss": 2.1683,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6944444444444444,
|
| 356 |
+
"grad_norm": 4.560003757476807,
|
| 357 |
+
"learning_rate": 1.527777777777778e-05,
|
| 358 |
+
"loss": 2.1594,
|
| 359 |
+
"step": 25000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.7083333333333334,
|
| 363 |
+
"grad_norm": 6.414097785949707,
|
| 364 |
+
"learning_rate": 1.4583333333333335e-05,
|
| 365 |
+
"loss": 2.1591,
|
| 366 |
+
"step": 25500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7222222222222222,
|
| 370 |
+
"grad_norm": 6.280707836151123,
|
| 371 |
+
"learning_rate": 1.388888888888889e-05,
|
| 372 |
+
"loss": 2.1606,
|
| 373 |
+
"step": 26000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7361111111111112,
|
| 377 |
+
"grad_norm": 5.258241653442383,
|
| 378 |
+
"learning_rate": 1.3194444444444446e-05,
|
| 379 |
+
"loss": 2.1626,
|
| 380 |
+
"step": 26500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.75,
|
| 384 |
+
"grad_norm": 6.5570549964904785,
|
| 385 |
+
"learning_rate": 1.25e-05,
|
| 386 |
+
"loss": 2.1371,
|
| 387 |
+
"step": 27000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7638888888888888,
|
| 391 |
+
"grad_norm": 6.682789325714111,
|
| 392 |
+
"learning_rate": 1.1805555555555555e-05,
|
| 393 |
+
"loss": 2.1568,
|
| 394 |
+
"step": 27500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7777777777777778,
|
| 398 |
+
"grad_norm": 5.776541233062744,
|
| 399 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 400 |
+
"loss": 2.1568,
|
| 401 |
+
"step": 28000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7916666666666666,
|
| 405 |
+
"grad_norm": 10.050359725952148,
|
| 406 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 407 |
+
"loss": 2.1528,
|
| 408 |
+
"step": 28500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.8055555555555556,
|
| 412 |
+
"grad_norm": 7.241547584533691,
|
| 413 |
+
"learning_rate": 9.722222222222223e-06,
|
| 414 |
+
"loss": 2.1493,
|
| 415 |
+
"step": 29000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8194444444444444,
|
| 419 |
+
"grad_norm": 6.834393501281738,
|
| 420 |
+
"learning_rate": 9.027777777777777e-06,
|
| 421 |
+
"loss": 2.1535,
|
| 422 |
+
"step": 29500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8333333333333334,
|
| 426 |
+
"grad_norm": 7.608417510986328,
|
| 427 |
+
"learning_rate": 8.333333333333334e-06,
|
| 428 |
+
"loss": 2.1525,
|
| 429 |
+
"step": 30000
|
| 430 |
+
}
|
| 431 |
+
],
|
| 432 |
+
"logging_steps": 500,
|
| 433 |
+
"max_steps": 36000,
|
| 434 |
+
"num_input_tokens_seen": 0,
|
| 435 |
+
"num_train_epochs": 1,
|
| 436 |
+
"save_steps": 10000,
|
| 437 |
+
"total_flos": 2.786102083584e+16,
|
| 438 |
+
"train_batch_size": 4,
|
| 439 |
+
"trial_name": null,
|
| 440 |
+
"trial_params": null
|
| 441 |
+
}
|
checkpoint-30000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cabe9bd8e4e952736226f3c44920004d0e323de0d8b75d30aa99981c05b9cd6e
|
| 3 |
+
size 4984
|