Upload folder using huggingface_hub
Browse files- checkpoint-900/config.json +17 -0
- checkpoint-900/generation_config.json +6 -0
- checkpoint-900/hybrid_tokenizer_mapping.json +0 -0
- checkpoint-900/model.safetensors +3 -0
- checkpoint-900/optimizer.pt +3 -0
- checkpoint-900/rng_state.pth +3 -0
- checkpoint-900/scaler.pt +3 -0
- checkpoint-900/scheduler.pt +3 -0
- checkpoint-900/tokenizer_config.json +9 -0
- checkpoint-900/trainer_state.json +664 -0
- checkpoint-900/training_args.bin +3 -0
checkpoint-900/config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"FastHyperNet125mForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"hidden_size": 768,
|
| 7 |
+
"hyperbolic_dim": 16,
|
| 8 |
+
"initializer_range": 0.02,
|
| 9 |
+
"intermediate_size": 2048,
|
| 10 |
+
"max_position_embeddings": 512,
|
| 11 |
+
"model_type": "fasthypernet_125m_tagless",
|
| 12 |
+
"num_attention_heads": 12,
|
| 13 |
+
"num_hidden_layers": 16,
|
| 14 |
+
"transformers_version": "5.13.1",
|
| 15 |
+
"use_cache": false,
|
| 16 |
+
"vocab_size": 8192
|
| 17 |
+
}
|
checkpoint-900/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-900/hybrid_tokenizer_mapping.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-900/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cd53365341ce5e783c1a14c43b3794bb610d3ccc9f79966438bc0c328191598
|
| 3 |
+
size 501888768
|
checkpoint-900/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:988487de631a0af44c39097f7f472021348ebf6052b51cad59b69955d660d85d
|
| 3 |
+
size 254046859
|
checkpoint-900/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edce308af81af2560edb81b5473da1f6129211b0a75c4ac5f56fb3c3eb55b52f
|
| 3 |
+
size 14645
|
checkpoint-900/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a24589a40bcaf06f47275eb976bd5640a73bf4b2e473671c8b209e7c9652ad1
|
| 3 |
+
size 1383
|
checkpoint-900/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e83500d8ccdd229927c689e268002045a455873fae880c9f29789ae21a984f93
|
| 3 |
+
size 1465
|
checkpoint-900/tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "HFCompatibleHybridTokenizer",
|
| 3 |
+
"vocab_size": 8192,
|
| 4 |
+
"model_max_length": 512,
|
| 5 |
+
"bos_token": "<bos>",
|
| 6 |
+
"eos_token": "<eos>",
|
| 7 |
+
"unk_token": "<unk>",
|
| 8 |
+
"pad_token": "<pad>"
|
| 9 |
+
}
|
checkpoint-900/trainer_state.json
ADDED
|
@@ -0,0 +1,664 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.047603305785123964,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 900,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0005289256198347108,
|
| 14 |
+
"grad_norm": 14983.798828125,
|
| 15 |
+
"learning_rate": 2.4e-07,
|
| 16 |
+
"loss": 17.1865,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0010578512396694215,
|
| 21 |
+
"grad_norm": 2818.19287109375,
|
| 22 |
+
"learning_rate": 1.04e-06,
|
| 23 |
+
"loss": 16.2669,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0015867768595041322,
|
| 28 |
+
"grad_norm": 2148.98486328125,
|
| 29 |
+
"learning_rate": 1.84e-06,
|
| 30 |
+
"loss": 15.5605,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.002115702479338843,
|
| 35 |
+
"grad_norm": 2309.862548828125,
|
| 36 |
+
"learning_rate": 2.64e-06,
|
| 37 |
+
"loss": 15.2203,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.002644628099173554,
|
| 42 |
+
"grad_norm": 2205.408935546875,
|
| 43 |
+
"learning_rate": 3.44e-06,
|
| 44 |
+
"loss": 14.9347,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0031735537190082643,
|
| 49 |
+
"grad_norm": 2530.3701171875,
|
| 50 |
+
"learning_rate": 4.24e-06,
|
| 51 |
+
"loss": 14.8024,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0037024793388429752,
|
| 56 |
+
"grad_norm": 1678.7281494140625,
|
| 57 |
+
"learning_rate": 5.04e-06,
|
| 58 |
+
"loss": 14.6196,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.004231404958677686,
|
| 63 |
+
"grad_norm": 2254.43798828125,
|
| 64 |
+
"learning_rate": 5.84e-06,
|
| 65 |
+
"loss": 14.4786,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.004760330578512397,
|
| 70 |
+
"grad_norm": 2226.012939453125,
|
| 71 |
+
"learning_rate": 6.640000000000001e-06,
|
| 72 |
+
"loss": 14.3674,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.005289256198347108,
|
| 77 |
+
"grad_norm": 2211.912353515625,
|
| 78 |
+
"learning_rate": 7.44e-06,
|
| 79 |
+
"loss": 14.1906,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.005818181818181818,
|
| 84 |
+
"grad_norm": 3070.8232421875,
|
| 85 |
+
"learning_rate": 8.24e-06,
|
| 86 |
+
"loss": 14.1344,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.006347107438016529,
|
| 91 |
+
"grad_norm": 2257.41455078125,
|
| 92 |
+
"learning_rate": 9.04e-06,
|
| 93 |
+
"loss": 14.0681,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.00687603305785124,
|
| 98 |
+
"grad_norm": 2274.346435546875,
|
| 99 |
+
"learning_rate": 9.84e-06,
|
| 100 |
+
"loss": 13.9746,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0074049586776859504,
|
| 105 |
+
"grad_norm": 2632.0341796875,
|
| 106 |
+
"learning_rate": 1.064e-05,
|
| 107 |
+
"loss": 13.9974,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.007933884297520661,
|
| 112 |
+
"grad_norm": 1979.03857421875,
|
| 113 |
+
"learning_rate": 1.144e-05,
|
| 114 |
+
"loss": 13.6573,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.008462809917355372,
|
| 119 |
+
"grad_norm": 1911.6646728515625,
|
| 120 |
+
"learning_rate": 1.216e-05,
|
| 121 |
+
"loss": 13.5115,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.008991735537190083,
|
| 126 |
+
"grad_norm": 1221.2379150390625,
|
| 127 |
+
"learning_rate": 1.296e-05,
|
| 128 |
+
"loss": 13.4189,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.009520661157024794,
|
| 133 |
+
"grad_norm": 1295.5301513671875,
|
| 134 |
+
"learning_rate": 1.376e-05,
|
| 135 |
+
"loss": 13.1649,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.010049586776859505,
|
| 140 |
+
"grad_norm": 1181.076904296875,
|
| 141 |
+
"learning_rate": 1.4480000000000002e-05,
|
| 142 |
+
"loss": 13.0769,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.010578512396694216,
|
| 147 |
+
"grad_norm": 1546.213623046875,
|
| 148 |
+
"learning_rate": 1.528e-05,
|
| 149 |
+
"loss": 12.981,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.011107438016528925,
|
| 154 |
+
"grad_norm": 1649.0814208984375,
|
| 155 |
+
"learning_rate": 1.6080000000000002e-05,
|
| 156 |
+
"loss": 12.9791,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.011636363636363636,
|
| 161 |
+
"grad_norm": 1149.5986328125,
|
| 162 |
+
"learning_rate": 1.688e-05,
|
| 163 |
+
"loss": 12.9944,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.012165289256198347,
|
| 168 |
+
"grad_norm": 1094.528564453125,
|
| 169 |
+
"learning_rate": 1.7680000000000004e-05,
|
| 170 |
+
"loss": 12.712,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.012694214876033057,
|
| 175 |
+
"grad_norm": 1151.943603515625,
|
| 176 |
+
"learning_rate": 1.848e-05,
|
| 177 |
+
"loss": 12.7007,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.013223140495867768,
|
| 182 |
+
"grad_norm": 756.9489135742188,
|
| 183 |
+
"learning_rate": 1.9280000000000002e-05,
|
| 184 |
+
"loss": 12.6777,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.01375206611570248,
|
| 189 |
+
"grad_norm": 1089.9005126953125,
|
| 190 |
+
"learning_rate": 2.008e-05,
|
| 191 |
+
"loss": 12.551,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.01428099173553719,
|
| 196 |
+
"grad_norm": 1578.2489013671875,
|
| 197 |
+
"learning_rate": 2.0880000000000003e-05,
|
| 198 |
+
"loss": 12.6069,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.014809917355371901,
|
| 203 |
+
"grad_norm": 622.3321533203125,
|
| 204 |
+
"learning_rate": 2.168e-05,
|
| 205 |
+
"loss": 12.4807,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.015338842975206612,
|
| 210 |
+
"grad_norm": 653.3980712890625,
|
| 211 |
+
"learning_rate": 2.248e-05,
|
| 212 |
+
"loss": 12.2924,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.015867768595041323,
|
| 217 |
+
"grad_norm": 580.5093994140625,
|
| 218 |
+
"learning_rate": 2.328e-05,
|
| 219 |
+
"loss": 12.2673,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.016396694214876033,
|
| 224 |
+
"grad_norm": 870.7935791015625,
|
| 225 |
+
"learning_rate": 2.408e-05,
|
| 226 |
+
"loss": 11.8822,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.016925619834710744,
|
| 231 |
+
"grad_norm": 451.5616760253906,
|
| 232 |
+
"learning_rate": 2.488e-05,
|
| 233 |
+
"loss": 11.7939,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.017454545454545455,
|
| 238 |
+
"grad_norm": 1039.074462890625,
|
| 239 |
+
"learning_rate": 2.5679999999999998e-05,
|
| 240 |
+
"loss": 11.7623,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.017983471074380166,
|
| 245 |
+
"grad_norm": 826.6625366210938,
|
| 246 |
+
"learning_rate": 2.648e-05,
|
| 247 |
+
"loss": 11.5301,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.018512396694214877,
|
| 252 |
+
"grad_norm": 375.2585144042969,
|
| 253 |
+
"learning_rate": 2.728e-05,
|
| 254 |
+
"loss": 11.6941,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.019041322314049588,
|
| 259 |
+
"grad_norm": 535.522705078125,
|
| 260 |
+
"learning_rate": 2.8080000000000002e-05,
|
| 261 |
+
"loss": 11.3719,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.0195702479338843,
|
| 266 |
+
"grad_norm": 608.0570678710938,
|
| 267 |
+
"learning_rate": 2.888e-05,
|
| 268 |
+
"loss": 11.2682,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.02009917355371901,
|
| 273 |
+
"grad_norm": 678.4328002929688,
|
| 274 |
+
"learning_rate": 2.9680000000000004e-05,
|
| 275 |
+
"loss": 11.3097,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.02062809917355372,
|
| 280 |
+
"grad_norm": 567.5283203125,
|
| 281 |
+
"learning_rate": 3.0480000000000003e-05,
|
| 282 |
+
"loss": 11.2014,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.02115702479338843,
|
| 287 |
+
"grad_norm": 382.2688293457031,
|
| 288 |
+
"learning_rate": 3.1280000000000005e-05,
|
| 289 |
+
"loss": 10.9673,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.021685950413223142,
|
| 294 |
+
"grad_norm": 599.6221923828125,
|
| 295 |
+
"learning_rate": 3.208e-05,
|
| 296 |
+
"loss": 10.981,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.02221487603305785,
|
| 301 |
+
"grad_norm": 382.1618957519531,
|
| 302 |
+
"learning_rate": 3.288e-05,
|
| 303 |
+
"loss": 10.9526,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.02274380165289256,
|
| 308 |
+
"grad_norm": 1082.0447998046875,
|
| 309 |
+
"learning_rate": 3.368e-05,
|
| 310 |
+
"loss": 10.9535,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.02327272727272727,
|
| 315 |
+
"grad_norm": 360.10101318359375,
|
| 316 |
+
"learning_rate": 3.448e-05,
|
| 317 |
+
"loss": 10.7087,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.023801652892561982,
|
| 322 |
+
"grad_norm": 460.0298156738281,
|
| 323 |
+
"learning_rate": 3.528e-05,
|
| 324 |
+
"loss": 10.8773,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.024330578512396693,
|
| 329 |
+
"grad_norm": 389.6498107910156,
|
| 330 |
+
"learning_rate": 3.608e-05,
|
| 331 |
+
"loss": 10.7515,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.024859504132231404,
|
| 336 |
+
"grad_norm": 511.04937744140625,
|
| 337 |
+
"learning_rate": 3.6880000000000006e-05,
|
| 338 |
+
"loss": 10.4311,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.025388429752066115,
|
| 343 |
+
"grad_norm": 277.2391052246094,
|
| 344 |
+
"learning_rate": 3.7680000000000005e-05,
|
| 345 |
+
"loss": 10.3949,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.025917355371900826,
|
| 350 |
+
"grad_norm": 345.6590270996094,
|
| 351 |
+
"learning_rate": 3.848e-05,
|
| 352 |
+
"loss": 10.3248,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.026446280991735537,
|
| 357 |
+
"grad_norm": 354.5246887207031,
|
| 358 |
+
"learning_rate": 3.9280000000000003e-05,
|
| 359 |
+
"loss": 10.4081,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.026975206611570247,
|
| 364 |
+
"grad_norm": 383.70745849609375,
|
| 365 |
+
"learning_rate": 4.008e-05,
|
| 366 |
+
"loss": 10.3949,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.02750413223140496,
|
| 371 |
+
"grad_norm": 661.0210571289062,
|
| 372 |
+
"learning_rate": 4.088e-05,
|
| 373 |
+
"loss": 10.3027,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.02803305785123967,
|
| 378 |
+
"grad_norm": 417.7251892089844,
|
| 379 |
+
"learning_rate": 4.168e-05,
|
| 380 |
+
"loss": 10.1894,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.02856198347107438,
|
| 385 |
+
"grad_norm": 282.77117919921875,
|
| 386 |
+
"learning_rate": 4.248e-05,
|
| 387 |
+
"loss": 10.0761,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.02909090909090909,
|
| 392 |
+
"grad_norm": 271.8935546875,
|
| 393 |
+
"learning_rate": 4.3280000000000006e-05,
|
| 394 |
+
"loss": 10.083,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.029619834710743802,
|
| 399 |
+
"grad_norm": 308.1956787109375,
|
| 400 |
+
"learning_rate": 4.4080000000000005e-05,
|
| 401 |
+
"loss": 10.0744,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.030148760330578513,
|
| 406 |
+
"grad_norm": 331.1837463378906,
|
| 407 |
+
"learning_rate": 4.488e-05,
|
| 408 |
+
"loss": 9.9295,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.030677685950413223,
|
| 413 |
+
"grad_norm": 341.76824951171875,
|
| 414 |
+
"learning_rate": 4.568e-05,
|
| 415 |
+
"loss": 10.005,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.031206611570247934,
|
| 420 |
+
"grad_norm": 403.6604919433594,
|
| 421 |
+
"learning_rate": 4.648e-05,
|
| 422 |
+
"loss": 9.9016,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.031735537190082645,
|
| 427 |
+
"grad_norm": 246.0824432373047,
|
| 428 |
+
"learning_rate": 4.728e-05,
|
| 429 |
+
"loss": 10.0205,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.032264462809917356,
|
| 434 |
+
"grad_norm": 259.1653137207031,
|
| 435 |
+
"learning_rate": 4.808e-05,
|
| 436 |
+
"loss": 9.9739,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.03279338842975207,
|
| 441 |
+
"grad_norm": 222.7213592529297,
|
| 442 |
+
"learning_rate": 4.8880000000000006e-05,
|
| 443 |
+
"loss": 9.8544,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.03332231404958678,
|
| 448 |
+
"grad_norm": 314.3382568359375,
|
| 449 |
+
"learning_rate": 4.9680000000000005e-05,
|
| 450 |
+
"loss": 9.7755,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.03385123966942149,
|
| 455 |
+
"grad_norm": 287.65570068359375,
|
| 456 |
+
"learning_rate": 5.0480000000000005e-05,
|
| 457 |
+
"loss": 9.7856,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.0343801652892562,
|
| 462 |
+
"grad_norm": 273.3498229980469,
|
| 463 |
+
"learning_rate": 5.1280000000000004e-05,
|
| 464 |
+
"loss": 9.6916,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.03490909090909091,
|
| 469 |
+
"grad_norm": 196.19595336914062,
|
| 470 |
+
"learning_rate": 5.208000000000001e-05,
|
| 471 |
+
"loss": 9.7167,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.03543801652892562,
|
| 476 |
+
"grad_norm": 370.2161865234375,
|
| 477 |
+
"learning_rate": 5.288000000000001e-05,
|
| 478 |
+
"loss": 9.4405,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.03596694214876033,
|
| 483 |
+
"grad_norm": 235.0204620361328,
|
| 484 |
+
"learning_rate": 5.368000000000001e-05,
|
| 485 |
+
"loss": 9.7401,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.03649586776859504,
|
| 490 |
+
"grad_norm": 250.4844207763672,
|
| 491 |
+
"learning_rate": 5.448e-05,
|
| 492 |
+
"loss": 9.5492,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.037024793388429754,
|
| 497 |
+
"grad_norm": 209.03860473632812,
|
| 498 |
+
"learning_rate": 5.528e-05,
|
| 499 |
+
"loss": 9.4078,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.037553719008264465,
|
| 504 |
+
"grad_norm": 167.85450744628906,
|
| 505 |
+
"learning_rate": 5.608e-05,
|
| 506 |
+
"loss": 9.3101,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.038082644628099176,
|
| 511 |
+
"grad_norm": 298.79559326171875,
|
| 512 |
+
"learning_rate": 5.688e-05,
|
| 513 |
+
"loss": 9.3794,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.03861157024793389,
|
| 518 |
+
"grad_norm": 265.5390930175781,
|
| 519 |
+
"learning_rate": 5.7680000000000003e-05,
|
| 520 |
+
"loss": 9.4477,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.0391404958677686,
|
| 525 |
+
"grad_norm": 198.37477111816406,
|
| 526 |
+
"learning_rate": 5.848e-05,
|
| 527 |
+
"loss": 9.4195,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.03966942148760331,
|
| 532 |
+
"grad_norm": 187.0157928466797,
|
| 533 |
+
"learning_rate": 5.928e-05,
|
| 534 |
+
"loss": 9.2161,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.04019834710743802,
|
| 539 |
+
"grad_norm": 173.72056579589844,
|
| 540 |
+
"learning_rate": 6.008e-05,
|
| 541 |
+
"loss": 9.1256,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.04072727272727273,
|
| 546 |
+
"grad_norm": 162.06800842285156,
|
| 547 |
+
"learning_rate": 6.088000000000001e-05,
|
| 548 |
+
"loss": 9.1191,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.04125619834710744,
|
| 553 |
+
"grad_norm": 179.91448974609375,
|
| 554 |
+
"learning_rate": 6.168e-05,
|
| 555 |
+
"loss": 8.9709,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.04178512396694215,
|
| 560 |
+
"grad_norm": 184.7924041748047,
|
| 561 |
+
"learning_rate": 6.248000000000001e-05,
|
| 562 |
+
"loss": 8.9353,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.04231404958677686,
|
| 567 |
+
"grad_norm": 176.74302673339844,
|
| 568 |
+
"learning_rate": 6.328e-05,
|
| 569 |
+
"loss": 9.2596,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.042842975206611573,
|
| 574 |
+
"grad_norm": 219.0215606689453,
|
| 575 |
+
"learning_rate": 6.408000000000001e-05,
|
| 576 |
+
"loss": 9.2463,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.043371900826446284,
|
| 581 |
+
"grad_norm": 198.78744506835938,
|
| 582 |
+
"learning_rate": 6.488e-05,
|
| 583 |
+
"loss": 9.1807,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.04390082644628099,
|
| 588 |
+
"grad_norm": 198.19236755371094,
|
| 589 |
+
"learning_rate": 6.568000000000001e-05,
|
| 590 |
+
"loss": 8.9577,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.0444297520661157,
|
| 595 |
+
"grad_norm": 251.5718536376953,
|
| 596 |
+
"learning_rate": 6.648e-05,
|
| 597 |
+
"loss": 8.9896,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.04495867768595041,
|
| 602 |
+
"grad_norm": 150.52122497558594,
|
| 603 |
+
"learning_rate": 6.727999999999999e-05,
|
| 604 |
+
"loss": 9.1038,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.04548760330578512,
|
| 609 |
+
"grad_norm": 138.3586883544922,
|
| 610 |
+
"learning_rate": 6.808e-05,
|
| 611 |
+
"loss": 8.8381,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.04601652892561983,
|
| 616 |
+
"grad_norm": 168.50901794433594,
|
| 617 |
+
"learning_rate": 6.888e-05,
|
| 618 |
+
"loss": 8.9202,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.04654545454545454,
|
| 623 |
+
"grad_norm": 155.10060119628906,
|
| 624 |
+
"learning_rate": 6.968e-05,
|
| 625 |
+
"loss": 8.7342,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.047074380165289254,
|
| 630 |
+
"grad_norm": 153.4683074951172,
|
| 631 |
+
"learning_rate": 7.048e-05,
|
| 632 |
+
"loss": 8.7278,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.047603305785123964,
|
| 637 |
+
"grad_norm": 123.66954803466797,
|
| 638 |
+
"learning_rate": 7.128000000000001e-05,
|
| 639 |
+
"loss": 8.8143,
|
| 640 |
+
"step": 900
|
| 641 |
+
}
|
| 642 |
+
],
|
| 643 |
+
"logging_steps": 10,
|
| 644 |
+
"max_steps": 10000000,
|
| 645 |
+
"num_input_tokens_seen": 0,
|
| 646 |
+
"num_train_epochs": 529,
|
| 647 |
+
"save_steps": 100,
|
| 648 |
+
"stateful_callbacks": {
|
| 649 |
+
"TrainerControl": {
|
| 650 |
+
"args": {
|
| 651 |
+
"should_epoch_stop": false,
|
| 652 |
+
"should_evaluate": false,
|
| 653 |
+
"should_log": false,
|
| 654 |
+
"should_save": true,
|
| 655 |
+
"should_training_stop": false
|
| 656 |
+
},
|
| 657 |
+
"attributes": {}
|
| 658 |
+
}
|
| 659 |
+
},
|
| 660 |
+
"total_flos": 1.5138521874432e+16,
|
| 661 |
+
"train_batch_size": 8,
|
| 662 |
+
"trial_name": null,
|
| 663 |
+
"trial_params": null
|
| 664 |
+
}
|
checkpoint-900/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5623a138829268598233d481b5532c5c6b7e4686976472a3d219e1ab580f03e5
|
| 3 |
+
size 5201
|