Upload folder using huggingface_hub
Browse files- checkpoint/config.json +29 -0
- checkpoint/generation_config.json +6 -0
- checkpoint/merges.txt +0 -0
- checkpoint/model.safetensors +3 -0
- checkpoint/optimizer.pt +3 -0
- checkpoint/rng_state_0.pth +3 -0
- checkpoint/rng_state_1.pth +3 -0
- checkpoint/rng_state_2.pth +3 -0
- checkpoint/rng_state_3.pth +3 -0
- checkpoint/rng_state_4.pth +3 -0
- checkpoint/rng_state_5.pth +3 -0
- checkpoint/rng_state_6.pth +3 -0
- checkpoint/rng_state_7.pth +3 -0
- checkpoint/rng_state_8.pth +3 -0
- checkpoint/rng_state_9.pth +3 -0
- checkpoint/scheduler.pt +3 -0
- checkpoint/special_tokens_map.json +43 -0
- checkpoint/tokenizer.json +0 -0
- checkpoint/tokenizer_config.json +169 -0
- checkpoint/trainer_state.json +3629 -0
- checkpoint/training_args.bin +3 -0
- checkpoint/vocab.json +0 -0
checkpoint/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Trelis/TrelisLM-100M-layer-hidden-pruned",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 660,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1760,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 15,
|
| 18 |
+
"num_hidden_layers": 16,
|
| 19 |
+
"num_key_value_heads": 5,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.44.2",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 49152
|
| 29 |
+
}
|
checkpoint/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.44.2"
|
| 6 |
+
}
|
checkpoint/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3fbfaf48c48c1697e20904015fb2507ceba67d19126f29a4714ee02437314be
|
| 3 |
+
size 213625344
|
checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6c659795d8520a40b5bb0a62a29a674d6c4ffbb08af66480ffe057b9794d5e9
|
| 3 |
+
size 427334458
|
checkpoint/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72aed7659a4568e39ea9a56bdc92196603df7d730a90c6411d24926b5d12ad03
|
| 3 |
+
size 16433
|
checkpoint/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ccb7aad33c882b66b79a28ece740dc71664d087d1f12ad61b65b18df1beca55
|
| 3 |
+
size 16433
|
checkpoint/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf3954ab65b1da5768888e4c50598bd4c761244f7027ce8da56d21582e829948
|
| 3 |
+
size 16433
|
checkpoint/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9373b1a76204778613e7dd6b7f31b34c6bb969dbb0b802f9f62ca911909492f2
|
| 3 |
+
size 16433
|
checkpoint/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1fc04b2ab887669d463a51ba4296461e18e6793bbf2221bc603bff1af03a7a6
|
| 3 |
+
size 16433
|
checkpoint/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81879e4ef695491cab2ffd4ab75ee6208dd18e8e7339d7b4aff8a08580e999d0
|
| 3 |
+
size 16433
|
checkpoint/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0af269f614eb79e3ee82816f8d169e28a4fa1006f684260473e683e7ccea9d58
|
| 3 |
+
size 16433
|
checkpoint/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e9f29cd3c33bc4028b8be6ed5e960831203bf34fb31356c09cdb29b4c851d3f
|
| 3 |
+
size 16433
|
checkpoint/rng_state_8.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62adbe536ff6dcfa7fb600a17a73fb0c108c33b017287d093401133eb29bb6d4
|
| 3 |
+
size 16433
|
checkpoint/rng_state_9.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b7dd71e7a0ba4defb86d5997709ee80f19a9326e37319a19a3ae8c437ad97fa
|
| 3 |
+
size 16433
|
checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7716d62ae95750c7d24c8c932a395f410b1a85a222da192df6e5730b3390f56f
|
| 3 |
+
size 1064
|
checkpoint/special_tokens_map.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|im_start|>",
|
| 5 |
+
"<|im_end|>",
|
| 6 |
+
"<repo_name>",
|
| 7 |
+
"<reponame>",
|
| 8 |
+
"<file_sep>",
|
| 9 |
+
"<filename>",
|
| 10 |
+
"<gh_stars>",
|
| 11 |
+
"<issue_start>",
|
| 12 |
+
"<issue_comment>",
|
| 13 |
+
"<issue_closed>",
|
| 14 |
+
"<jupyter_start>",
|
| 15 |
+
"<jupyter_text>",
|
| 16 |
+
"<jupyter_code>",
|
| 17 |
+
"<jupyter_output>",
|
| 18 |
+
"<jupyter_script>",
|
| 19 |
+
"<empty_output>"
|
| 20 |
+
],
|
| 21 |
+
"bos_token": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"eos_token": {
|
| 29 |
+
"content": "<|endoftext|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"pad_token": "<|endoftext|>",
|
| 36 |
+
"unk_token": {
|
| 37 |
+
"content": "<|endoftext|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false
|
| 42 |
+
}
|
| 43 |
+
}
|
checkpoint/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,169 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_eos_token": true,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "<repo_name>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"4": {
|
| 38 |
+
"content": "<reponame>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"5": {
|
| 46 |
+
"content": "<file_sep>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"6": {
|
| 54 |
+
"content": "<filename>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"7": {
|
| 62 |
+
"content": "<gh_stars>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"8": {
|
| 70 |
+
"content": "<issue_start>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"9": {
|
| 78 |
+
"content": "<issue_comment>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"10": {
|
| 86 |
+
"content": "<issue_closed>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"11": {
|
| 94 |
+
"content": "<jupyter_start>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"12": {
|
| 102 |
+
"content": "<jupyter_text>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"13": {
|
| 110 |
+
"content": "<jupyter_code>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"14": {
|
| 118 |
+
"content": "<jupyter_output>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": true
|
| 124 |
+
},
|
| 125 |
+
"15": {
|
| 126 |
+
"content": "<jupyter_script>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": true
|
| 132 |
+
},
|
| 133 |
+
"16": {
|
| 134 |
+
"content": "<empty_output>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": true
|
| 140 |
+
}
|
| 141 |
+
},
|
| 142 |
+
"additional_special_tokens": [
|
| 143 |
+
"<|endoftext|>",
|
| 144 |
+
"<|im_start|>",
|
| 145 |
+
"<|im_end|>",
|
| 146 |
+
"<repo_name>",
|
| 147 |
+
"<reponame>",
|
| 148 |
+
"<file_sep>",
|
| 149 |
+
"<filename>",
|
| 150 |
+
"<gh_stars>",
|
| 151 |
+
"<issue_start>",
|
| 152 |
+
"<issue_comment>",
|
| 153 |
+
"<issue_closed>",
|
| 154 |
+
"<jupyter_start>",
|
| 155 |
+
"<jupyter_text>",
|
| 156 |
+
"<jupyter_code>",
|
| 157 |
+
"<jupyter_output>",
|
| 158 |
+
"<jupyter_script>",
|
| 159 |
+
"<empty_output>"
|
| 160 |
+
],
|
| 161 |
+
"bos_token": "<|endoftext|>",
|
| 162 |
+
"clean_up_tokenization_spaces": false,
|
| 163 |
+
"eos_token": "<|endoftext|>",
|
| 164 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 165 |
+
"pad_token": "<|endoftext|>",
|
| 166 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 167 |
+
"unk_token": "<|endoftext|>",
|
| 168 |
+
"vocab_size": 49152
|
| 169 |
+
}
|
checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,3629 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.49997953419835456,
|
| 5 |
+
"eval_steps": 4886,
|
| 6 |
+
"global_step": 24430,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0009823584789816217,
|
| 13 |
+
"grad_norm": 640.0,
|
| 14 |
+
"learning_rate": 0.001,
|
| 15 |
+
"loss": 11885.6341,
|
| 16 |
+
"step": 48
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0019647169579632435,
|
| 20 |
+
"grad_norm": 454.0,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"loss": 8966.3691,
|
| 23 |
+
"step": 96
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0029470754369448652,
|
| 27 |
+
"grad_norm": 572.0,
|
| 28 |
+
"learning_rate": 0.001,
|
| 29 |
+
"loss": 7738.5072,
|
| 30 |
+
"step": 144
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.003929433915926487,
|
| 34 |
+
"grad_norm": 636.0,
|
| 35 |
+
"learning_rate": 0.001,
|
| 36 |
+
"loss": 7036.127,
|
| 37 |
+
"step": 192
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.004911792394908109,
|
| 41 |
+
"grad_norm": 748.0,
|
| 42 |
+
"learning_rate": 0.001,
|
| 43 |
+
"loss": 6540.5202,
|
| 44 |
+
"step": 240
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0058941508738897305,
|
| 48 |
+
"grad_norm": 556.0,
|
| 49 |
+
"learning_rate": 0.001,
|
| 50 |
+
"loss": 6263.0488,
|
| 51 |
+
"step": 288
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.006876509352871352,
|
| 55 |
+
"grad_norm": 532.0,
|
| 56 |
+
"learning_rate": 0.001,
|
| 57 |
+
"loss": 5950.1823,
|
| 58 |
+
"step": 336
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.007858867831852974,
|
| 62 |
+
"grad_norm": 928.0,
|
| 63 |
+
"learning_rate": 0.001,
|
| 64 |
+
"loss": 5705.2292,
|
| 65 |
+
"step": 384
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.008841226310834595,
|
| 69 |
+
"grad_norm": 444.0,
|
| 70 |
+
"learning_rate": 0.001,
|
| 71 |
+
"loss": 5496.4583,
|
| 72 |
+
"step": 432
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.009823584789816217,
|
| 76 |
+
"grad_norm": 656.0,
|
| 77 |
+
"learning_rate": 0.001,
|
| 78 |
+
"loss": 5272.5752,
|
| 79 |
+
"step": 480
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.010805943268797838,
|
| 83 |
+
"grad_norm": 612.0,
|
| 84 |
+
"learning_rate": 0.001,
|
| 85 |
+
"loss": 5051.2663,
|
| 86 |
+
"step": 528
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.011788301747779461,
|
| 90 |
+
"grad_norm": 608.0,
|
| 91 |
+
"learning_rate": 0.001,
|
| 92 |
+
"loss": 4938.0895,
|
| 93 |
+
"step": 576
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.012770660226761082,
|
| 97 |
+
"grad_norm": 466.0,
|
| 98 |
+
"learning_rate": 0.001,
|
| 99 |
+
"loss": 4740.762,
|
| 100 |
+
"step": 624
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.013753018705742704,
|
| 104 |
+
"grad_norm": 438.0,
|
| 105 |
+
"learning_rate": 0.001,
|
| 106 |
+
"loss": 4573.4443,
|
| 107 |
+
"step": 672
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.014735377184724325,
|
| 111 |
+
"grad_norm": 696.0,
|
| 112 |
+
"learning_rate": 0.001,
|
| 113 |
+
"loss": 4539.9521,
|
| 114 |
+
"step": 720
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.015717735663705948,
|
| 118 |
+
"grad_norm": 892.0,
|
| 119 |
+
"learning_rate": 0.001,
|
| 120 |
+
"loss": 4435.4001,
|
| 121 |
+
"step": 768
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.01670009414268757,
|
| 125 |
+
"grad_norm": 704.0,
|
| 126 |
+
"learning_rate": 0.001,
|
| 127 |
+
"loss": 4239.0426,
|
| 128 |
+
"step": 816
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.01768245262166919,
|
| 132 |
+
"grad_norm": 548.0,
|
| 133 |
+
"learning_rate": 0.001,
|
| 134 |
+
"loss": 4189.9281,
|
| 135 |
+
"step": 864
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.018664811100650814,
|
| 139 |
+
"grad_norm": 540.0,
|
| 140 |
+
"learning_rate": 0.001,
|
| 141 |
+
"loss": 4104.7835,
|
| 142 |
+
"step": 912
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.019647169579632435,
|
| 146 |
+
"grad_norm": 592.0,
|
| 147 |
+
"learning_rate": 0.001,
|
| 148 |
+
"loss": 4044.3369,
|
| 149 |
+
"step": 960
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.020629528058614056,
|
| 153 |
+
"grad_norm": 536.0,
|
| 154 |
+
"learning_rate": 0.001,
|
| 155 |
+
"loss": 3936.5283,
|
| 156 |
+
"step": 1008
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.021611886537595677,
|
| 160 |
+
"grad_norm": 604.0,
|
| 161 |
+
"learning_rate": 0.001,
|
| 162 |
+
"loss": 3915.6911,
|
| 163 |
+
"step": 1056
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.0225942450165773,
|
| 167 |
+
"grad_norm": 458.0,
|
| 168 |
+
"learning_rate": 0.001,
|
| 169 |
+
"loss": 3759.7747,
|
| 170 |
+
"step": 1104
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.023576603495558922,
|
| 174 |
+
"grad_norm": 636.0,
|
| 175 |
+
"learning_rate": 0.001,
|
| 176 |
+
"loss": 3760.4476,
|
| 177 |
+
"step": 1152
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.024558961974540543,
|
| 181 |
+
"grad_norm": 672.0,
|
| 182 |
+
"learning_rate": 0.001,
|
| 183 |
+
"loss": 3672.9059,
|
| 184 |
+
"step": 1200
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.025541320453522164,
|
| 188 |
+
"grad_norm": 592.0,
|
| 189 |
+
"learning_rate": 0.001,
|
| 190 |
+
"loss": 3645.0697,
|
| 191 |
+
"step": 1248
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.026523678932503784,
|
| 195 |
+
"grad_norm": 552.0,
|
| 196 |
+
"learning_rate": 0.001,
|
| 197 |
+
"loss": 3528.9896,
|
| 198 |
+
"step": 1296
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.02750603741148541,
|
| 202 |
+
"grad_norm": 470.0,
|
| 203 |
+
"learning_rate": 0.001,
|
| 204 |
+
"loss": 3488.8187,
|
| 205 |
+
"step": 1344
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.02848839589046703,
|
| 209 |
+
"grad_norm": 580.0,
|
| 210 |
+
"learning_rate": 0.001,
|
| 211 |
+
"loss": 3466.627,
|
| 212 |
+
"step": 1392
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.02947075436944865,
|
| 216 |
+
"grad_norm": 584.0,
|
| 217 |
+
"learning_rate": 0.001,
|
| 218 |
+
"loss": 3399.1475,
|
| 219 |
+
"step": 1440
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.03045311284843027,
|
| 223 |
+
"grad_norm": 732.0,
|
| 224 |
+
"learning_rate": 0.001,
|
| 225 |
+
"loss": 3363.9762,
|
| 226 |
+
"step": 1488
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.031435471327411896,
|
| 230 |
+
"grad_norm": 616.0,
|
| 231 |
+
"learning_rate": 0.001,
|
| 232 |
+
"loss": 3337.4564,
|
| 233 |
+
"step": 1536
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.03241782980639352,
|
| 237 |
+
"grad_norm": 540.0,
|
| 238 |
+
"learning_rate": 0.001,
|
| 239 |
+
"loss": 3298.4583,
|
| 240 |
+
"step": 1584
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.03340018828537514,
|
| 244 |
+
"grad_norm": 512.0,
|
| 245 |
+
"learning_rate": 0.001,
|
| 246 |
+
"loss": 3212.2949,
|
| 247 |
+
"step": 1632
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.03438254676435676,
|
| 251 |
+
"grad_norm": 512.0,
|
| 252 |
+
"learning_rate": 0.001,
|
| 253 |
+
"loss": 3217.6631,
|
| 254 |
+
"step": 1680
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.03536490524333838,
|
| 258 |
+
"grad_norm": 624.0,
|
| 259 |
+
"learning_rate": 0.001,
|
| 260 |
+
"loss": 3175.7318,
|
| 261 |
+
"step": 1728
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.03634726372232,
|
| 265 |
+
"grad_norm": 520.0,
|
| 266 |
+
"learning_rate": 0.001,
|
| 267 |
+
"loss": 3140.3923,
|
| 268 |
+
"step": 1776
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.03732962220130163,
|
| 272 |
+
"grad_norm": 664.0,
|
| 273 |
+
"learning_rate": 0.001,
|
| 274 |
+
"loss": 3099.8044,
|
| 275 |
+
"step": 1824
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.03831198068028325,
|
| 279 |
+
"grad_norm": 604.0,
|
| 280 |
+
"learning_rate": 0.001,
|
| 281 |
+
"loss": 3114.8079,
|
| 282 |
+
"step": 1872
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.03929433915926487,
|
| 286 |
+
"grad_norm": 478.0,
|
| 287 |
+
"learning_rate": 0.001,
|
| 288 |
+
"loss": 3048.9001,
|
| 289 |
+
"step": 1920
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.04027669763824649,
|
| 293 |
+
"grad_norm": 520.0,
|
| 294 |
+
"learning_rate": 0.001,
|
| 295 |
+
"loss": 3018.8714,
|
| 296 |
+
"step": 1968
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.04125905611722811,
|
| 300 |
+
"grad_norm": 456.0,
|
| 301 |
+
"learning_rate": 0.001,
|
| 302 |
+
"loss": 2981.1152,
|
| 303 |
+
"step": 2016
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.04224141459620973,
|
| 307 |
+
"grad_norm": 628.0,
|
| 308 |
+
"learning_rate": 0.001,
|
| 309 |
+
"loss": 2999.249,
|
| 310 |
+
"step": 2064
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.04322377307519135,
|
| 314 |
+
"grad_norm": 804.0,
|
| 315 |
+
"learning_rate": 0.001,
|
| 316 |
+
"loss": 2942.3376,
|
| 317 |
+
"step": 2112
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.044206131554172974,
|
| 321 |
+
"grad_norm": 600.0,
|
| 322 |
+
"learning_rate": 0.001,
|
| 323 |
+
"loss": 2890.7354,
|
| 324 |
+
"step": 2160
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.0451884900331546,
|
| 328 |
+
"grad_norm": 632.0,
|
| 329 |
+
"learning_rate": 0.001,
|
| 330 |
+
"loss": 2896.4242,
|
| 331 |
+
"step": 2208
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.04617084851213622,
|
| 335 |
+
"grad_norm": 536.0,
|
| 336 |
+
"learning_rate": 0.001,
|
| 337 |
+
"loss": 2874.8643,
|
| 338 |
+
"step": 2256
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.047153206991117844,
|
| 342 |
+
"grad_norm": 494.0,
|
| 343 |
+
"learning_rate": 0.001,
|
| 344 |
+
"loss": 2807.6911,
|
| 345 |
+
"step": 2304
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.048135565470099465,
|
| 349 |
+
"grad_norm": 548.0,
|
| 350 |
+
"learning_rate": 0.001,
|
| 351 |
+
"loss": 2820.04,
|
| 352 |
+
"step": 2352
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.049117923949081085,
|
| 356 |
+
"grad_norm": 636.0,
|
| 357 |
+
"learning_rate": 0.001,
|
| 358 |
+
"loss": 2787.0247,
|
| 359 |
+
"step": 2400
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.050100282428062706,
|
| 363 |
+
"grad_norm": 624.0,
|
| 364 |
+
"learning_rate": 0.001,
|
| 365 |
+
"loss": 2782.2428,
|
| 366 |
+
"step": 2448
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.05108264090704433,
|
| 370 |
+
"grad_norm": 628.0,
|
| 371 |
+
"learning_rate": 0.001,
|
| 372 |
+
"loss": 2725.3781,
|
| 373 |
+
"step": 2496
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.05206499938602595,
|
| 377 |
+
"grad_norm": 540.0,
|
| 378 |
+
"learning_rate": 0.001,
|
| 379 |
+
"loss": 2755.7458,
|
| 380 |
+
"step": 2544
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.05304735786500757,
|
| 384 |
+
"grad_norm": 568.0,
|
| 385 |
+
"learning_rate": 0.001,
|
| 386 |
+
"loss": 2699.16,
|
| 387 |
+
"step": 2592
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.0540297163439892,
|
| 391 |
+
"grad_norm": 808.0,
|
| 392 |
+
"learning_rate": 0.001,
|
| 393 |
+
"loss": 2680.3232,
|
| 394 |
+
"step": 2640
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.05501207482297082,
|
| 398 |
+
"grad_norm": 564.0,
|
| 399 |
+
"learning_rate": 0.001,
|
| 400 |
+
"loss": 2669.6646,
|
| 401 |
+
"step": 2688
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.05599443330195244,
|
| 405 |
+
"grad_norm": 552.0,
|
| 406 |
+
"learning_rate": 0.001,
|
| 407 |
+
"loss": 2683.8433,
|
| 408 |
+
"step": 2736
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.05697679178093406,
|
| 412 |
+
"grad_norm": 636.0,
|
| 413 |
+
"learning_rate": 0.001,
|
| 414 |
+
"loss": 2643.8172,
|
| 415 |
+
"step": 2784
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.05795915025991568,
|
| 419 |
+
"grad_norm": 580.0,
|
| 420 |
+
"learning_rate": 0.001,
|
| 421 |
+
"loss": 2649.0441,
|
| 422 |
+
"step": 2832
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.0589415087388973,
|
| 426 |
+
"grad_norm": 512.0,
|
| 427 |
+
"learning_rate": 0.001,
|
| 428 |
+
"loss": 2615.9657,
|
| 429 |
+
"step": 2880
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.05992386721787892,
|
| 433 |
+
"grad_norm": 688.0,
|
| 434 |
+
"learning_rate": 0.001,
|
| 435 |
+
"loss": 2608.1457,
|
| 436 |
+
"step": 2928
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.06090622569686054,
|
| 440 |
+
"grad_norm": 696.0,
|
| 441 |
+
"learning_rate": 0.001,
|
| 442 |
+
"loss": 2590.1567,
|
| 443 |
+
"step": 2976
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.06188858417584217,
|
| 447 |
+
"grad_norm": 704.0,
|
| 448 |
+
"learning_rate": 0.001,
|
| 449 |
+
"loss": 2627.8358,
|
| 450 |
+
"step": 3024
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.06287094265482379,
|
| 454 |
+
"grad_norm": 704.0,
|
| 455 |
+
"learning_rate": 0.001,
|
| 456 |
+
"loss": 2538.9543,
|
| 457 |
+
"step": 3072
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.06385330113380541,
|
| 461 |
+
"grad_norm": 568.0,
|
| 462 |
+
"learning_rate": 0.001,
|
| 463 |
+
"loss": 2482.9673,
|
| 464 |
+
"step": 3120
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.06483565961278703,
|
| 468 |
+
"grad_norm": 548.0,
|
| 469 |
+
"learning_rate": 0.001,
|
| 470 |
+
"loss": 2530.4771,
|
| 471 |
+
"step": 3168
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.06581801809176865,
|
| 475 |
+
"grad_norm": 456.0,
|
| 476 |
+
"learning_rate": 0.001,
|
| 477 |
+
"loss": 2496.41,
|
| 478 |
+
"step": 3216
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.06680037657075028,
|
| 482 |
+
"grad_norm": 684.0,
|
| 483 |
+
"learning_rate": 0.001,
|
| 484 |
+
"loss": 2518.8866,
|
| 485 |
+
"step": 3264
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.0677827350497319,
|
| 489 |
+
"grad_norm": 664.0,
|
| 490 |
+
"learning_rate": 0.001,
|
| 491 |
+
"loss": 2475.0793,
|
| 492 |
+
"step": 3312
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.06876509352871352,
|
| 496 |
+
"grad_norm": 812.0,
|
| 497 |
+
"learning_rate": 0.001,
|
| 498 |
+
"loss": 2461.3527,
|
| 499 |
+
"step": 3360
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.06974745200769514,
|
| 503 |
+
"grad_norm": 490.0,
|
| 504 |
+
"learning_rate": 0.001,
|
| 505 |
+
"loss": 2467.4508,
|
| 506 |
+
"step": 3408
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.07072981048667676,
|
| 510 |
+
"grad_norm": 648.0,
|
| 511 |
+
"learning_rate": 0.001,
|
| 512 |
+
"loss": 2443.8037,
|
| 513 |
+
"step": 3456
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.07171216896565838,
|
| 517 |
+
"grad_norm": 664.0,
|
| 518 |
+
"learning_rate": 0.001,
|
| 519 |
+
"loss": 2445.9336,
|
| 520 |
+
"step": 3504
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.07269452744464,
|
| 524 |
+
"grad_norm": 524.0,
|
| 525 |
+
"learning_rate": 0.001,
|
| 526 |
+
"loss": 2411.4482,
|
| 527 |
+
"step": 3552
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.07367688592362164,
|
| 531 |
+
"grad_norm": 608.0,
|
| 532 |
+
"learning_rate": 0.001,
|
| 533 |
+
"loss": 2417.4673,
|
| 534 |
+
"step": 3600
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.07465924440260326,
|
| 538 |
+
"grad_norm": 504.0,
|
| 539 |
+
"learning_rate": 0.001,
|
| 540 |
+
"loss": 2420.4196,
|
| 541 |
+
"step": 3648
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.07564160288158488,
|
| 545 |
+
"grad_norm": 564.0,
|
| 546 |
+
"learning_rate": 0.001,
|
| 547 |
+
"loss": 2390.8983,
|
| 548 |
+
"step": 3696
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.0766239613605665,
|
| 552 |
+
"grad_norm": 664.0,
|
| 553 |
+
"learning_rate": 0.001,
|
| 554 |
+
"loss": 2377.8607,
|
| 555 |
+
"step": 3744
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.07760631983954812,
|
| 559 |
+
"grad_norm": 616.0,
|
| 560 |
+
"learning_rate": 0.001,
|
| 561 |
+
"loss": 2359.1242,
|
| 562 |
+
"step": 3792
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.07858867831852974,
|
| 566 |
+
"grad_norm": 636.0,
|
| 567 |
+
"learning_rate": 0.001,
|
| 568 |
+
"loss": 2385.3102,
|
| 569 |
+
"step": 3840
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.07957103679751136,
|
| 573 |
+
"grad_norm": 454.0,
|
| 574 |
+
"learning_rate": 0.001,
|
| 575 |
+
"loss": 2373.0225,
|
| 576 |
+
"step": 3888
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.08055339527649298,
|
| 580 |
+
"grad_norm": 502.0,
|
| 581 |
+
"learning_rate": 0.001,
|
| 582 |
+
"loss": 2361.2386,
|
| 583 |
+
"step": 3936
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.0815357537554746,
|
| 587 |
+
"grad_norm": 506.0,
|
| 588 |
+
"learning_rate": 0.001,
|
| 589 |
+
"loss": 2341.1328,
|
| 590 |
+
"step": 3984
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.08251811223445622,
|
| 594 |
+
"grad_norm": 472.0,
|
| 595 |
+
"learning_rate": 0.001,
|
| 596 |
+
"loss": 2308.069,
|
| 597 |
+
"step": 4032
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.08350047071343784,
|
| 601 |
+
"grad_norm": 472.0,
|
| 602 |
+
"learning_rate": 0.001,
|
| 603 |
+
"loss": 2305.2542,
|
| 604 |
+
"step": 4080
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.08448282919241946,
|
| 608 |
+
"grad_norm": 502.0,
|
| 609 |
+
"learning_rate": 0.001,
|
| 610 |
+
"loss": 2338.4048,
|
| 611 |
+
"step": 4128
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.08546518767140109,
|
| 615 |
+
"grad_norm": 628.0,
|
| 616 |
+
"learning_rate": 0.001,
|
| 617 |
+
"loss": 2307.96,
|
| 618 |
+
"step": 4176
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.0864475461503827,
|
| 622 |
+
"grad_norm": 516.0,
|
| 623 |
+
"learning_rate": 0.001,
|
| 624 |
+
"loss": 2314.313,
|
| 625 |
+
"step": 4224
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.08742990462936433,
|
| 629 |
+
"grad_norm": 748.0,
|
| 630 |
+
"learning_rate": 0.001,
|
| 631 |
+
"loss": 2270.4917,
|
| 632 |
+
"step": 4272
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.08841226310834595,
|
| 636 |
+
"grad_norm": 576.0,
|
| 637 |
+
"learning_rate": 0.001,
|
| 638 |
+
"loss": 2292.9497,
|
| 639 |
+
"step": 4320
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.08939462158732757,
|
| 643 |
+
"grad_norm": 604.0,
|
| 644 |
+
"learning_rate": 0.001,
|
| 645 |
+
"loss": 2274.6584,
|
| 646 |
+
"step": 4368
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.0903769800663092,
|
| 650 |
+
"grad_norm": 580.0,
|
| 651 |
+
"learning_rate": 0.001,
|
| 652 |
+
"loss": 2275.2266,
|
| 653 |
+
"step": 4416
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.09135933854529082,
|
| 657 |
+
"grad_norm": 548.0,
|
| 658 |
+
"learning_rate": 0.001,
|
| 659 |
+
"loss": 2262.757,
|
| 660 |
+
"step": 4464
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.09234169702427245,
|
| 664 |
+
"grad_norm": 628.0,
|
| 665 |
+
"learning_rate": 0.001,
|
| 666 |
+
"loss": 2257.687,
|
| 667 |
+
"step": 4512
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.09332405550325407,
|
| 671 |
+
"grad_norm": 544.0,
|
| 672 |
+
"learning_rate": 0.001,
|
| 673 |
+
"loss": 2259.9118,
|
| 674 |
+
"step": 4560
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.09430641398223569,
|
| 678 |
+
"grad_norm": 580.0,
|
| 679 |
+
"learning_rate": 0.001,
|
| 680 |
+
"loss": 2224.4427,
|
| 681 |
+
"step": 4608
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.09528877246121731,
|
| 685 |
+
"grad_norm": 628.0,
|
| 686 |
+
"learning_rate": 0.001,
|
| 687 |
+
"loss": 2248.397,
|
| 688 |
+
"step": 4656
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.09627113094019893,
|
| 692 |
+
"grad_norm": 600.0,
|
| 693 |
+
"learning_rate": 0.001,
|
| 694 |
+
"loss": 2203.2843,
|
| 695 |
+
"step": 4704
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.09725348941918055,
|
| 699 |
+
"grad_norm": 780.0,
|
| 700 |
+
"learning_rate": 0.001,
|
| 701 |
+
"loss": 2223.5656,
|
| 702 |
+
"step": 4752
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.09823584789816217,
|
| 706 |
+
"grad_norm": 536.0,
|
| 707 |
+
"learning_rate": 0.001,
|
| 708 |
+
"loss": 2169.4321,
|
| 709 |
+
"step": 4800
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.09921820637714379,
|
| 713 |
+
"grad_norm": 516.0,
|
| 714 |
+
"learning_rate": 0.001,
|
| 715 |
+
"loss": 2183.4987,
|
| 716 |
+
"step": 4848
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.09999590683967091,
|
| 720 |
+
"eval_loss": 2087.82763671875,
|
| 721 |
+
"eval_runtime": 9.0001,
|
| 722 |
+
"eval_samples_per_second": 111.11,
|
| 723 |
+
"eval_steps_per_second": 1.444,
|
| 724 |
+
"step": 4886
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.10020056485612541,
|
| 728 |
+
"grad_norm": 620.0,
|
| 729 |
+
"learning_rate": 0.001,
|
| 730 |
+
"loss": 2210.3151,
|
| 731 |
+
"step": 4896
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.10118292333510703,
|
| 735 |
+
"grad_norm": 616.0,
|
| 736 |
+
"learning_rate": 0.001,
|
| 737 |
+
"loss": 2208.1779,
|
| 738 |
+
"step": 4944
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.10216528181408865,
|
| 742 |
+
"grad_norm": 592.0,
|
| 743 |
+
"learning_rate": 0.001,
|
| 744 |
+
"loss": 2166.7116,
|
| 745 |
+
"step": 4992
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.10314764029307028,
|
| 749 |
+
"grad_norm": 596.0,
|
| 750 |
+
"learning_rate": 0.001,
|
| 751 |
+
"loss": 2191.4295,
|
| 752 |
+
"step": 5040
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.1041299987720519,
|
| 756 |
+
"grad_norm": 684.0,
|
| 757 |
+
"learning_rate": 0.001,
|
| 758 |
+
"loss": 2155.1141,
|
| 759 |
+
"step": 5088
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.10511235725103352,
|
| 763 |
+
"grad_norm": 512.0,
|
| 764 |
+
"learning_rate": 0.001,
|
| 765 |
+
"loss": 2135.7635,
|
| 766 |
+
"step": 5136
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.10609471573001514,
|
| 770 |
+
"grad_norm": 506.0,
|
| 771 |
+
"learning_rate": 0.001,
|
| 772 |
+
"loss": 2155.5701,
|
| 773 |
+
"step": 5184
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.10707707420899677,
|
| 777 |
+
"grad_norm": 480.0,
|
| 778 |
+
"learning_rate": 0.001,
|
| 779 |
+
"loss": 2150.0086,
|
| 780 |
+
"step": 5232
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.1080594326879784,
|
| 784 |
+
"grad_norm": 540.0,
|
| 785 |
+
"learning_rate": 0.001,
|
| 786 |
+
"loss": 2142.4181,
|
| 787 |
+
"step": 5280
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.10904179116696001,
|
| 791 |
+
"grad_norm": 572.0,
|
| 792 |
+
"learning_rate": 0.001,
|
| 793 |
+
"loss": 2116.3011,
|
| 794 |
+
"step": 5328
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.11002414964594164,
|
| 798 |
+
"grad_norm": 548.0,
|
| 799 |
+
"learning_rate": 0.001,
|
| 800 |
+
"loss": 2141.0239,
|
| 801 |
+
"step": 5376
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.11100650812492326,
|
| 805 |
+
"grad_norm": 676.0,
|
| 806 |
+
"learning_rate": 0.001,
|
| 807 |
+
"loss": 2119.1307,
|
| 808 |
+
"step": 5424
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.11198886660390488,
|
| 812 |
+
"grad_norm": 656.0,
|
| 813 |
+
"learning_rate": 0.001,
|
| 814 |
+
"loss": 2137.8016,
|
| 815 |
+
"step": 5472
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.1129712250828865,
|
| 819 |
+
"grad_norm": 676.0,
|
| 820 |
+
"learning_rate": 0.001,
|
| 821 |
+
"loss": 2119.2923,
|
| 822 |
+
"step": 5520
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.11395358356186812,
|
| 826 |
+
"grad_norm": 588.0,
|
| 827 |
+
"learning_rate": 0.001,
|
| 828 |
+
"loss": 2120.9912,
|
| 829 |
+
"step": 5568
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.11493594204084974,
|
| 833 |
+
"grad_norm": 612.0,
|
| 834 |
+
"learning_rate": 0.001,
|
| 835 |
+
"loss": 2111.5037,
|
| 836 |
+
"step": 5616
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.11591830051983136,
|
| 840 |
+
"grad_norm": 588.0,
|
| 841 |
+
"learning_rate": 0.001,
|
| 842 |
+
"loss": 2119.6444,
|
| 843 |
+
"step": 5664
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.11690065899881298,
|
| 847 |
+
"grad_norm": 700.0,
|
| 848 |
+
"learning_rate": 0.001,
|
| 849 |
+
"loss": 2078.1807,
|
| 850 |
+
"step": 5712
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.1178830174777946,
|
| 854 |
+
"grad_norm": 564.0,
|
| 855 |
+
"learning_rate": 0.001,
|
| 856 |
+
"loss": 2095.8706,
|
| 857 |
+
"step": 5760
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.11886537595677622,
|
| 861 |
+
"grad_norm": 552.0,
|
| 862 |
+
"learning_rate": 0.001,
|
| 863 |
+
"loss": 2080.8527,
|
| 864 |
+
"step": 5808
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.11984773443575784,
|
| 868 |
+
"grad_norm": 488.0,
|
| 869 |
+
"learning_rate": 0.001,
|
| 870 |
+
"loss": 2062.9159,
|
| 871 |
+
"step": 5856
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.12083009291473946,
|
| 875 |
+
"grad_norm": 616.0,
|
| 876 |
+
"learning_rate": 0.001,
|
| 877 |
+
"loss": 2060.964,
|
| 878 |
+
"step": 5904
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.12181245139372109,
|
| 882 |
+
"grad_norm": 648.0,
|
| 883 |
+
"learning_rate": 0.001,
|
| 884 |
+
"loss": 2088.8507,
|
| 885 |
+
"step": 5952
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.12279480987270272,
|
| 889 |
+
"grad_norm": 604.0,
|
| 890 |
+
"learning_rate": 0.001,
|
| 891 |
+
"loss": 2052.1393,
|
| 892 |
+
"step": 6000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.12377716835168434,
|
| 896 |
+
"grad_norm": 720.0,
|
| 897 |
+
"learning_rate": 0.001,
|
| 898 |
+
"loss": 2043.2277,
|
| 899 |
+
"step": 6048
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.12475952683066596,
|
| 903 |
+
"grad_norm": 616.0,
|
| 904 |
+
"learning_rate": 0.001,
|
| 905 |
+
"loss": 2043.3983,
|
| 906 |
+
"step": 6096
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.12574188530964758,
|
| 910 |
+
"grad_norm": 668.0,
|
| 911 |
+
"learning_rate": 0.001,
|
| 912 |
+
"loss": 2080.6297,
|
| 913 |
+
"step": 6144
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.1267242437886292,
|
| 917 |
+
"grad_norm": 532.0,
|
| 918 |
+
"learning_rate": 0.001,
|
| 919 |
+
"loss": 2059.5207,
|
| 920 |
+
"step": 6192
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.12770660226761082,
|
| 924 |
+
"grad_norm": 568.0,
|
| 925 |
+
"learning_rate": 0.001,
|
| 926 |
+
"loss": 2030.5203,
|
| 927 |
+
"step": 6240
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.12868896074659245,
|
| 931 |
+
"grad_norm": 560.0,
|
| 932 |
+
"learning_rate": 0.001,
|
| 933 |
+
"loss": 2047.7404,
|
| 934 |
+
"step": 6288
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.12967131922557407,
|
| 938 |
+
"grad_norm": 624.0,
|
| 939 |
+
"learning_rate": 0.001,
|
| 940 |
+
"loss": 2043.3193,
|
| 941 |
+
"step": 6336
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.1306536777045557,
|
| 945 |
+
"grad_norm": 592.0,
|
| 946 |
+
"learning_rate": 0.001,
|
| 947 |
+
"loss": 2051.0589,
|
| 948 |
+
"step": 6384
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.1316360361835373,
|
| 952 |
+
"grad_norm": 876.0,
|
| 953 |
+
"learning_rate": 0.001,
|
| 954 |
+
"loss": 2054.3232,
|
| 955 |
+
"step": 6432
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.13261839466251893,
|
| 959 |
+
"grad_norm": 544.0,
|
| 960 |
+
"learning_rate": 0.001,
|
| 961 |
+
"loss": 2047.3159,
|
| 962 |
+
"step": 6480
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.13360075314150055,
|
| 966 |
+
"grad_norm": 648.0,
|
| 967 |
+
"learning_rate": 0.001,
|
| 968 |
+
"loss": 2029.021,
|
| 969 |
+
"step": 6528
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.13458311162048217,
|
| 973 |
+
"grad_norm": 556.0,
|
| 974 |
+
"learning_rate": 0.001,
|
| 975 |
+
"loss": 2027.506,
|
| 976 |
+
"step": 6576
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.1355654700994638,
|
| 980 |
+
"grad_norm": 672.0,
|
| 981 |
+
"learning_rate": 0.001,
|
| 982 |
+
"loss": 2034.3325,
|
| 983 |
+
"step": 6624
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.1365478285784454,
|
| 987 |
+
"grad_norm": 648.0,
|
| 988 |
+
"learning_rate": 0.001,
|
| 989 |
+
"loss": 1988.6841,
|
| 990 |
+
"step": 6672
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.13753018705742703,
|
| 994 |
+
"grad_norm": 592.0,
|
| 995 |
+
"learning_rate": 0.001,
|
| 996 |
+
"loss": 1998.0236,
|
| 997 |
+
"step": 6720
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.13851254553640865,
|
| 1001 |
+
"grad_norm": 552.0,
|
| 1002 |
+
"learning_rate": 0.001,
|
| 1003 |
+
"loss": 2008.8337,
|
| 1004 |
+
"step": 6768
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.13949490401539028,
|
| 1008 |
+
"grad_norm": 780.0,
|
| 1009 |
+
"learning_rate": 0.001,
|
| 1010 |
+
"loss": 2008.4787,
|
| 1011 |
+
"step": 6816
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.1404772624943719,
|
| 1015 |
+
"grad_norm": 716.0,
|
| 1016 |
+
"learning_rate": 0.001,
|
| 1017 |
+
"loss": 1995.237,
|
| 1018 |
+
"step": 6864
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.14145962097335352,
|
| 1022 |
+
"grad_norm": 804.0,
|
| 1023 |
+
"learning_rate": 0.001,
|
| 1024 |
+
"loss": 1996.2018,
|
| 1025 |
+
"step": 6912
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.14244197945233514,
|
| 1029 |
+
"grad_norm": 652.0,
|
| 1030 |
+
"learning_rate": 0.001,
|
| 1031 |
+
"loss": 1992.167,
|
| 1032 |
+
"step": 6960
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.14342433793131676,
|
| 1036 |
+
"grad_norm": 544.0,
|
| 1037 |
+
"learning_rate": 0.001,
|
| 1038 |
+
"loss": 1985.2515,
|
| 1039 |
+
"step": 7008
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.14440669641029838,
|
| 1043 |
+
"grad_norm": 600.0,
|
| 1044 |
+
"learning_rate": 0.001,
|
| 1045 |
+
"loss": 1989.0208,
|
| 1046 |
+
"step": 7056
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.14538905488928,
|
| 1050 |
+
"grad_norm": 712.0,
|
| 1051 |
+
"learning_rate": 0.001,
|
| 1052 |
+
"loss": 1993.743,
|
| 1053 |
+
"step": 7104
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.14637141336826162,
|
| 1057 |
+
"grad_norm": 580.0,
|
| 1058 |
+
"learning_rate": 0.001,
|
| 1059 |
+
"loss": 1986.2668,
|
| 1060 |
+
"step": 7152
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.14735377184724327,
|
| 1064 |
+
"grad_norm": 716.0,
|
| 1065 |
+
"learning_rate": 0.001,
|
| 1066 |
+
"loss": 1988.6514,
|
| 1067 |
+
"step": 7200
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.1483361303262249,
|
| 1071 |
+
"grad_norm": 452.0,
|
| 1072 |
+
"learning_rate": 0.001,
|
| 1073 |
+
"loss": 1971.7622,
|
| 1074 |
+
"step": 7248
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.1493184888052065,
|
| 1078 |
+
"grad_norm": 576.0,
|
| 1079 |
+
"learning_rate": 0.001,
|
| 1080 |
+
"loss": 1977.0863,
|
| 1081 |
+
"step": 7296
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.15030084728418813,
|
| 1085 |
+
"grad_norm": 708.0,
|
| 1086 |
+
"learning_rate": 0.001,
|
| 1087 |
+
"loss": 1968.3294,
|
| 1088 |
+
"step": 7344
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.15128320576316975,
|
| 1092 |
+
"grad_norm": 572.0,
|
| 1093 |
+
"learning_rate": 0.001,
|
| 1094 |
+
"loss": 1981.1888,
|
| 1095 |
+
"step": 7392
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.15226556424215137,
|
| 1099 |
+
"grad_norm": 748.0,
|
| 1100 |
+
"learning_rate": 0.001,
|
| 1101 |
+
"loss": 1937.5469,
|
| 1102 |
+
"step": 7440
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.153247922721133,
|
| 1106 |
+
"grad_norm": 672.0,
|
| 1107 |
+
"learning_rate": 0.001,
|
| 1108 |
+
"loss": 1944.2785,
|
| 1109 |
+
"step": 7488
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.15423028120011462,
|
| 1113 |
+
"grad_norm": 816.0,
|
| 1114 |
+
"learning_rate": 0.001,
|
| 1115 |
+
"loss": 1934.2336,
|
| 1116 |
+
"step": 7536
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.15521263967909624,
|
| 1120 |
+
"grad_norm": 740.0,
|
| 1121 |
+
"learning_rate": 0.001,
|
| 1122 |
+
"loss": 1953.3698,
|
| 1123 |
+
"step": 7584
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.15619499815807786,
|
| 1127 |
+
"grad_norm": 652.0,
|
| 1128 |
+
"learning_rate": 0.001,
|
| 1129 |
+
"loss": 1951.9084,
|
| 1130 |
+
"step": 7632
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.15717735663705948,
|
| 1134 |
+
"grad_norm": 652.0,
|
| 1135 |
+
"learning_rate": 0.001,
|
| 1136 |
+
"loss": 1934.8753,
|
| 1137 |
+
"step": 7680
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.1581597151160411,
|
| 1141 |
+
"grad_norm": 652.0,
|
| 1142 |
+
"learning_rate": 0.001,
|
| 1143 |
+
"loss": 1923.8843,
|
| 1144 |
+
"step": 7728
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.15914207359502272,
|
| 1148 |
+
"grad_norm": 612.0,
|
| 1149 |
+
"learning_rate": 0.001,
|
| 1150 |
+
"loss": 1935.5955,
|
| 1151 |
+
"step": 7776
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.16012443207400434,
|
| 1155 |
+
"grad_norm": 724.0,
|
| 1156 |
+
"learning_rate": 0.001,
|
| 1157 |
+
"loss": 1962.8574,
|
| 1158 |
+
"step": 7824
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.16110679055298596,
|
| 1162 |
+
"grad_norm": 540.0,
|
| 1163 |
+
"learning_rate": 0.001,
|
| 1164 |
+
"loss": 1955.3468,
|
| 1165 |
+
"step": 7872
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.16208914903196758,
|
| 1169 |
+
"grad_norm": 752.0,
|
| 1170 |
+
"learning_rate": 0.001,
|
| 1171 |
+
"loss": 1915.3901,
|
| 1172 |
+
"step": 7920
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.1630715075109492,
|
| 1176 |
+
"grad_norm": 572.0,
|
| 1177 |
+
"learning_rate": 0.001,
|
| 1178 |
+
"loss": 1944.2292,
|
| 1179 |
+
"step": 7968
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.16405386598993082,
|
| 1183 |
+
"grad_norm": 668.0,
|
| 1184 |
+
"learning_rate": 0.001,
|
| 1185 |
+
"loss": 1926.0425,
|
| 1186 |
+
"step": 8016
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.16503622446891245,
|
| 1190 |
+
"grad_norm": 556.0,
|
| 1191 |
+
"learning_rate": 0.001,
|
| 1192 |
+
"loss": 1938.1131,
|
| 1193 |
+
"step": 8064
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.16601858294789407,
|
| 1197 |
+
"grad_norm": 756.0,
|
| 1198 |
+
"learning_rate": 0.001,
|
| 1199 |
+
"loss": 1925.4678,
|
| 1200 |
+
"step": 8112
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.1670009414268757,
|
| 1204 |
+
"grad_norm": 848.0,
|
| 1205 |
+
"learning_rate": 0.001,
|
| 1206 |
+
"loss": 1921.8462,
|
| 1207 |
+
"step": 8160
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.1679832999058573,
|
| 1211 |
+
"grad_norm": 588.0,
|
| 1212 |
+
"learning_rate": 0.001,
|
| 1213 |
+
"loss": 1890.1263,
|
| 1214 |
+
"step": 8208
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.16896565838483893,
|
| 1218 |
+
"grad_norm": 580.0,
|
| 1219 |
+
"learning_rate": 0.001,
|
| 1220 |
+
"loss": 1923.7113,
|
| 1221 |
+
"step": 8256
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.16994801686382055,
|
| 1225 |
+
"grad_norm": 712.0,
|
| 1226 |
+
"learning_rate": 0.001,
|
| 1227 |
+
"loss": 1902.661,
|
| 1228 |
+
"step": 8304
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.17093037534280217,
|
| 1232 |
+
"grad_norm": 676.0,
|
| 1233 |
+
"learning_rate": 0.001,
|
| 1234 |
+
"loss": 1898.4054,
|
| 1235 |
+
"step": 8352
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.1719127338217838,
|
| 1239 |
+
"grad_norm": 604.0,
|
| 1240 |
+
"learning_rate": 0.001,
|
| 1241 |
+
"loss": 1899.0542,
|
| 1242 |
+
"step": 8400
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.1728950923007654,
|
| 1246 |
+
"grad_norm": 700.0,
|
| 1247 |
+
"learning_rate": 0.001,
|
| 1248 |
+
"loss": 1906.8057,
|
| 1249 |
+
"step": 8448
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.17387745077974703,
|
| 1253 |
+
"grad_norm": 716.0,
|
| 1254 |
+
"learning_rate": 0.001,
|
| 1255 |
+
"loss": 1908.1032,
|
| 1256 |
+
"step": 8496
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.17485980925872865,
|
| 1260 |
+
"grad_norm": 628.0,
|
| 1261 |
+
"learning_rate": 0.001,
|
| 1262 |
+
"loss": 1928.3221,
|
| 1263 |
+
"step": 8544
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.17584216773771028,
|
| 1267 |
+
"grad_norm": 664.0,
|
| 1268 |
+
"learning_rate": 0.001,
|
| 1269 |
+
"loss": 1890.7321,
|
| 1270 |
+
"step": 8592
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.1768245262166919,
|
| 1274 |
+
"grad_norm": 556.0,
|
| 1275 |
+
"learning_rate": 0.001,
|
| 1276 |
+
"loss": 1910.8001,
|
| 1277 |
+
"step": 8640
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.17780688469567352,
|
| 1281 |
+
"grad_norm": 648.0,
|
| 1282 |
+
"learning_rate": 0.001,
|
| 1283 |
+
"loss": 1908.4972,
|
| 1284 |
+
"step": 8688
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.17878924317465514,
|
| 1288 |
+
"grad_norm": 608.0,
|
| 1289 |
+
"learning_rate": 0.001,
|
| 1290 |
+
"loss": 1870.7344,
|
| 1291 |
+
"step": 8736
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.1797716016536368,
|
| 1295 |
+
"grad_norm": 644.0,
|
| 1296 |
+
"learning_rate": 0.001,
|
| 1297 |
+
"loss": 1901.4289,
|
| 1298 |
+
"step": 8784
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.1807539601326184,
|
| 1302 |
+
"grad_norm": 580.0,
|
| 1303 |
+
"learning_rate": 0.001,
|
| 1304 |
+
"loss": 1883.8433,
|
| 1305 |
+
"step": 8832
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.18173631861160003,
|
| 1309 |
+
"grad_norm": 828.0,
|
| 1310 |
+
"learning_rate": 0.001,
|
| 1311 |
+
"loss": 1869.978,
|
| 1312 |
+
"step": 8880
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.18271867709058165,
|
| 1316 |
+
"grad_norm": 652.0,
|
| 1317 |
+
"learning_rate": 0.001,
|
| 1318 |
+
"loss": 1895.2178,
|
| 1319 |
+
"step": 8928
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.18370103556956327,
|
| 1323 |
+
"grad_norm": 680.0,
|
| 1324 |
+
"learning_rate": 0.001,
|
| 1325 |
+
"loss": 1857.217,
|
| 1326 |
+
"step": 8976
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.1846833940485449,
|
| 1330 |
+
"grad_norm": 608.0,
|
| 1331 |
+
"learning_rate": 0.001,
|
| 1332 |
+
"loss": 1880.6992,
|
| 1333 |
+
"step": 9024
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.1856657525275265,
|
| 1337 |
+
"grad_norm": 664.0,
|
| 1338 |
+
"learning_rate": 0.001,
|
| 1339 |
+
"loss": 1869.5422,
|
| 1340 |
+
"step": 9072
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.18664811100650813,
|
| 1344 |
+
"grad_norm": 720.0,
|
| 1345 |
+
"learning_rate": 0.001,
|
| 1346 |
+
"loss": 1898.1034,
|
| 1347 |
+
"step": 9120
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.18763046948548975,
|
| 1351 |
+
"grad_norm": 604.0,
|
| 1352 |
+
"learning_rate": 0.001,
|
| 1353 |
+
"loss": 1887.1818,
|
| 1354 |
+
"step": 9168
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.18861282796447137,
|
| 1358 |
+
"grad_norm": 672.0,
|
| 1359 |
+
"learning_rate": 0.001,
|
| 1360 |
+
"loss": 1869.6294,
|
| 1361 |
+
"step": 9216
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.189595186443453,
|
| 1365 |
+
"grad_norm": 572.0,
|
| 1366 |
+
"learning_rate": 0.001,
|
| 1367 |
+
"loss": 1857.5962,
|
| 1368 |
+
"step": 9264
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.19057754492243462,
|
| 1372 |
+
"grad_norm": 732.0,
|
| 1373 |
+
"learning_rate": 0.001,
|
| 1374 |
+
"loss": 1869.6444,
|
| 1375 |
+
"step": 9312
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.19155990340141624,
|
| 1379 |
+
"grad_norm": 848.0,
|
| 1380 |
+
"learning_rate": 0.001,
|
| 1381 |
+
"loss": 1869.8807,
|
| 1382 |
+
"step": 9360
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.19254226188039786,
|
| 1386 |
+
"grad_norm": 740.0,
|
| 1387 |
+
"learning_rate": 0.001,
|
| 1388 |
+
"loss": 1857.5882,
|
| 1389 |
+
"step": 9408
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.19352462035937948,
|
| 1393 |
+
"grad_norm": 652.0,
|
| 1394 |
+
"learning_rate": 0.001,
|
| 1395 |
+
"loss": 1835.6294,
|
| 1396 |
+
"step": 9456
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.1945069788383611,
|
| 1400 |
+
"grad_norm": 608.0,
|
| 1401 |
+
"learning_rate": 0.001,
|
| 1402 |
+
"loss": 1853.5081,
|
| 1403 |
+
"step": 9504
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.19548933731734272,
|
| 1407 |
+
"grad_norm": 648.0,
|
| 1408 |
+
"learning_rate": 0.001,
|
| 1409 |
+
"loss": 1866.897,
|
| 1410 |
+
"step": 9552
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.19647169579632434,
|
| 1414 |
+
"grad_norm": 724.0,
|
| 1415 |
+
"learning_rate": 0.001,
|
| 1416 |
+
"loss": 1848.0703,
|
| 1417 |
+
"step": 9600
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.19745405427530596,
|
| 1421 |
+
"grad_norm": 628.0,
|
| 1422 |
+
"learning_rate": 0.001,
|
| 1423 |
+
"loss": 1867.1585,
|
| 1424 |
+
"step": 9648
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.19843641275428758,
|
| 1428 |
+
"grad_norm": 612.0,
|
| 1429 |
+
"learning_rate": 0.001,
|
| 1430 |
+
"loss": 1864.8203,
|
| 1431 |
+
"step": 9696
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.1994187712332692,
|
| 1435 |
+
"grad_norm": 572.0,
|
| 1436 |
+
"learning_rate": 0.001,
|
| 1437 |
+
"loss": 1827.0848,
|
| 1438 |
+
"step": 9744
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.19999181367934182,
|
| 1442 |
+
"eval_loss": 1771.5172119140625,
|
| 1443 |
+
"eval_runtime": 9.0052,
|
| 1444 |
+
"eval_samples_per_second": 111.047,
|
| 1445 |
+
"eval_steps_per_second": 1.444,
|
| 1446 |
+
"step": 9772
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 0.20040112971225083,
|
| 1450 |
+
"grad_norm": 784.0,
|
| 1451 |
+
"learning_rate": 0.001,
|
| 1452 |
+
"loss": 1850.5506,
|
| 1453 |
+
"step": 9792
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 0.20138348819123245,
|
| 1457 |
+
"grad_norm": 728.0,
|
| 1458 |
+
"learning_rate": 0.001,
|
| 1459 |
+
"loss": 1853.3254,
|
| 1460 |
+
"step": 9840
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 0.20236584667021407,
|
| 1464 |
+
"grad_norm": 744.0,
|
| 1465 |
+
"learning_rate": 0.001,
|
| 1466 |
+
"loss": 1884.8763,
|
| 1467 |
+
"step": 9888
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.2033482051491957,
|
| 1471 |
+
"grad_norm": 740.0,
|
| 1472 |
+
"learning_rate": 0.001,
|
| 1473 |
+
"loss": 1852.5361,
|
| 1474 |
+
"step": 9936
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 0.2043305636281773,
|
| 1478 |
+
"grad_norm": 780.0,
|
| 1479 |
+
"learning_rate": 0.001,
|
| 1480 |
+
"loss": 1840.8996,
|
| 1481 |
+
"step": 9984
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 0.20531292210715893,
|
| 1485 |
+
"grad_norm": 676.0,
|
| 1486 |
+
"learning_rate": 0.001,
|
| 1487 |
+
"loss": 1848.5868,
|
| 1488 |
+
"step": 10032
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 0.20629528058614055,
|
| 1492 |
+
"grad_norm": 764.0,
|
| 1493 |
+
"learning_rate": 0.001,
|
| 1494 |
+
"loss": 1848.7498,
|
| 1495 |
+
"step": 10080
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 0.20727763906512217,
|
| 1499 |
+
"grad_norm": 856.0,
|
| 1500 |
+
"learning_rate": 0.001,
|
| 1501 |
+
"loss": 1845.7381,
|
| 1502 |
+
"step": 10128
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 0.2082599975441038,
|
| 1506 |
+
"grad_norm": 740.0,
|
| 1507 |
+
"learning_rate": 0.001,
|
| 1508 |
+
"loss": 1851.979,
|
| 1509 |
+
"step": 10176
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.2092423560230854,
|
| 1513 |
+
"grad_norm": 644.0,
|
| 1514 |
+
"learning_rate": 0.001,
|
| 1515 |
+
"loss": 1850.7716,
|
| 1516 |
+
"step": 10224
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 0.21022471450206703,
|
| 1520 |
+
"grad_norm": 828.0,
|
| 1521 |
+
"learning_rate": 0.001,
|
| 1522 |
+
"loss": 1844.3057,
|
| 1523 |
+
"step": 10272
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 0.21120707298104865,
|
| 1527 |
+
"grad_norm": 688.0,
|
| 1528 |
+
"learning_rate": 0.001,
|
| 1529 |
+
"loss": 1820.6678,
|
| 1530 |
+
"step": 10320
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 0.21218943146003028,
|
| 1534 |
+
"grad_norm": 832.0,
|
| 1535 |
+
"learning_rate": 0.001,
|
| 1536 |
+
"loss": 1793.4041,
|
| 1537 |
+
"step": 10368
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 0.21317178993901192,
|
| 1541 |
+
"grad_norm": 648.0,
|
| 1542 |
+
"learning_rate": 0.001,
|
| 1543 |
+
"loss": 1853.5828,
|
| 1544 |
+
"step": 10416
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 0.21415414841799355,
|
| 1548 |
+
"grad_norm": 780.0,
|
| 1549 |
+
"learning_rate": 0.001,
|
| 1550 |
+
"loss": 1816.429,
|
| 1551 |
+
"step": 10464
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.21513650689697517,
|
| 1555 |
+
"grad_norm": 708.0,
|
| 1556 |
+
"learning_rate": 0.001,
|
| 1557 |
+
"loss": 1827.7533,
|
| 1558 |
+
"step": 10512
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 0.2161188653759568,
|
| 1562 |
+
"grad_norm": 812.0,
|
| 1563 |
+
"learning_rate": 0.001,
|
| 1564 |
+
"loss": 1807.555,
|
| 1565 |
+
"step": 10560
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 0.2171012238549384,
|
| 1569 |
+
"grad_norm": 728.0,
|
| 1570 |
+
"learning_rate": 0.001,
|
| 1571 |
+
"loss": 1824.4678,
|
| 1572 |
+
"step": 10608
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 0.21808358233392003,
|
| 1576 |
+
"grad_norm": 760.0,
|
| 1577 |
+
"learning_rate": 0.001,
|
| 1578 |
+
"loss": 1832.056,
|
| 1579 |
+
"step": 10656
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 0.21906594081290165,
|
| 1583 |
+
"grad_norm": 672.0,
|
| 1584 |
+
"learning_rate": 0.001,
|
| 1585 |
+
"loss": 1819.7812,
|
| 1586 |
+
"step": 10704
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 0.22004829929188327,
|
| 1590 |
+
"grad_norm": 808.0,
|
| 1591 |
+
"learning_rate": 0.001,
|
| 1592 |
+
"loss": 1837.8351,
|
| 1593 |
+
"step": 10752
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.2210306577708649,
|
| 1597 |
+
"grad_norm": 716.0,
|
| 1598 |
+
"learning_rate": 0.001,
|
| 1599 |
+
"loss": 1823.1432,
|
| 1600 |
+
"step": 10800
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.2220130162498465,
|
| 1604 |
+
"grad_norm": 768.0,
|
| 1605 |
+
"learning_rate": 0.001,
|
| 1606 |
+
"loss": 1810.9959,
|
| 1607 |
+
"step": 10848
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.22299537472882813,
|
| 1611 |
+
"grad_norm": 756.0,
|
| 1612 |
+
"learning_rate": 0.001,
|
| 1613 |
+
"loss": 1848.2907,
|
| 1614 |
+
"step": 10896
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.22397773320780975,
|
| 1618 |
+
"grad_norm": 744.0,
|
| 1619 |
+
"learning_rate": 0.001,
|
| 1620 |
+
"loss": 1786.6442,
|
| 1621 |
+
"step": 10944
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.22496009168679137,
|
| 1625 |
+
"grad_norm": 740.0,
|
| 1626 |
+
"learning_rate": 0.001,
|
| 1627 |
+
"loss": 1804.0133,
|
| 1628 |
+
"step": 10992
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.225942450165773,
|
| 1632 |
+
"grad_norm": 640.0,
|
| 1633 |
+
"learning_rate": 0.001,
|
| 1634 |
+
"loss": 1813.6567,
|
| 1635 |
+
"step": 11040
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.22692480864475462,
|
| 1639 |
+
"grad_norm": 696.0,
|
| 1640 |
+
"learning_rate": 0.001,
|
| 1641 |
+
"loss": 1812.9946,
|
| 1642 |
+
"step": 11088
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 0.22790716712373624,
|
| 1646 |
+
"grad_norm": 696.0,
|
| 1647 |
+
"learning_rate": 0.001,
|
| 1648 |
+
"loss": 1816.8553,
|
| 1649 |
+
"step": 11136
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 0.22888952560271786,
|
| 1653 |
+
"grad_norm": 640.0,
|
| 1654 |
+
"learning_rate": 0.001,
|
| 1655 |
+
"loss": 1801.8009,
|
| 1656 |
+
"step": 11184
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 0.22987188408169948,
|
| 1660 |
+
"grad_norm": 680.0,
|
| 1661 |
+
"learning_rate": 0.001,
|
| 1662 |
+
"loss": 1816.7332,
|
| 1663 |
+
"step": 11232
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 0.2308542425606811,
|
| 1667 |
+
"grad_norm": 692.0,
|
| 1668 |
+
"learning_rate": 0.001,
|
| 1669 |
+
"loss": 1799.8708,
|
| 1670 |
+
"step": 11280
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 0.23183660103966272,
|
| 1674 |
+
"grad_norm": 680.0,
|
| 1675 |
+
"learning_rate": 0.001,
|
| 1676 |
+
"loss": 1791.1471,
|
| 1677 |
+
"step": 11328
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.23281895951864434,
|
| 1681 |
+
"grad_norm": 700.0,
|
| 1682 |
+
"learning_rate": 0.001,
|
| 1683 |
+
"loss": 1812.3979,
|
| 1684 |
+
"step": 11376
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 0.23380131799762596,
|
| 1688 |
+
"grad_norm": 748.0,
|
| 1689 |
+
"learning_rate": 0.001,
|
| 1690 |
+
"loss": 1807.806,
|
| 1691 |
+
"step": 11424
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 0.23478367647660758,
|
| 1695 |
+
"grad_norm": 716.0,
|
| 1696 |
+
"learning_rate": 0.001,
|
| 1697 |
+
"loss": 1811.6502,
|
| 1698 |
+
"step": 11472
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 0.2357660349555892,
|
| 1702 |
+
"grad_norm": 736.0,
|
| 1703 |
+
"learning_rate": 0.001,
|
| 1704 |
+
"loss": 1821.8501,
|
| 1705 |
+
"step": 11520
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 0.23674839343457083,
|
| 1709 |
+
"grad_norm": 648.0,
|
| 1710 |
+
"learning_rate": 0.001,
|
| 1711 |
+
"loss": 1777.6597,
|
| 1712 |
+
"step": 11568
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 0.23773075191355245,
|
| 1716 |
+
"grad_norm": 768.0,
|
| 1717 |
+
"learning_rate": 0.001,
|
| 1718 |
+
"loss": 1804.2365,
|
| 1719 |
+
"step": 11616
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.23871311039253407,
|
| 1723 |
+
"grad_norm": 672.0,
|
| 1724 |
+
"learning_rate": 0.001,
|
| 1725 |
+
"loss": 1794.9201,
|
| 1726 |
+
"step": 11664
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 0.2396954688715157,
|
| 1730 |
+
"grad_norm": 696.0,
|
| 1731 |
+
"learning_rate": 0.001,
|
| 1732 |
+
"loss": 1775.2284,
|
| 1733 |
+
"step": 11712
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 0.2406778273504973,
|
| 1737 |
+
"grad_norm": 700.0,
|
| 1738 |
+
"learning_rate": 0.001,
|
| 1739 |
+
"loss": 1785.5417,
|
| 1740 |
+
"step": 11760
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 0.24166018582947893,
|
| 1744 |
+
"grad_norm": 840.0,
|
| 1745 |
+
"learning_rate": 0.001,
|
| 1746 |
+
"loss": 1792.2282,
|
| 1747 |
+
"step": 11808
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 0.24264254430846055,
|
| 1751 |
+
"grad_norm": 992.0,
|
| 1752 |
+
"learning_rate": 0.001,
|
| 1753 |
+
"loss": 1799.9831,
|
| 1754 |
+
"step": 11856
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 0.24362490278744217,
|
| 1758 |
+
"grad_norm": 872.0,
|
| 1759 |
+
"learning_rate": 0.001,
|
| 1760 |
+
"loss": 1804.1024,
|
| 1761 |
+
"step": 11904
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.2446072612664238,
|
| 1765 |
+
"grad_norm": 668.0,
|
| 1766 |
+
"learning_rate": 0.001,
|
| 1767 |
+
"loss": 1785.5889,
|
| 1768 |
+
"step": 11952
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 0.24558961974540544,
|
| 1772 |
+
"grad_norm": 872.0,
|
| 1773 |
+
"learning_rate": 0.001,
|
| 1774 |
+
"loss": 1785.6185,
|
| 1775 |
+
"step": 12000
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 0.24657197822438706,
|
| 1779 |
+
"grad_norm": 784.0,
|
| 1780 |
+
"learning_rate": 0.001,
|
| 1781 |
+
"loss": 1785.6107,
|
| 1782 |
+
"step": 12048
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 0.24755433670336868,
|
| 1786 |
+
"grad_norm": 644.0,
|
| 1787 |
+
"learning_rate": 0.001,
|
| 1788 |
+
"loss": 1789.2995,
|
| 1789 |
+
"step": 12096
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 0.2485366951823503,
|
| 1793 |
+
"grad_norm": 772.0,
|
| 1794 |
+
"learning_rate": 0.001,
|
| 1795 |
+
"loss": 1780.3151,
|
| 1796 |
+
"step": 12144
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 0.24951905366133192,
|
| 1800 |
+
"grad_norm": 728.0,
|
| 1801 |
+
"learning_rate": 0.001,
|
| 1802 |
+
"loss": 1769.0786,
|
| 1803 |
+
"step": 12192
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.2505014121403135,
|
| 1807 |
+
"grad_norm": 752.0,
|
| 1808 |
+
"learning_rate": 0.001,
|
| 1809 |
+
"loss": 1801.0431,
|
| 1810 |
+
"step": 12240
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 0.25148377061929517,
|
| 1814 |
+
"grad_norm": 844.0,
|
| 1815 |
+
"learning_rate": 0.001,
|
| 1816 |
+
"loss": 1796.9209,
|
| 1817 |
+
"step": 12288
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 0.25246612909827676,
|
| 1821 |
+
"grad_norm": 1088.0,
|
| 1822 |
+
"learning_rate": 0.001,
|
| 1823 |
+
"loss": 1795.411,
|
| 1824 |
+
"step": 12336
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 0.2534484875772584,
|
| 1828 |
+
"grad_norm": 1320.0,
|
| 1829 |
+
"learning_rate": 0.001,
|
| 1830 |
+
"loss": 1802.1553,
|
| 1831 |
+
"step": 12384
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 0.25443084605624,
|
| 1835 |
+
"grad_norm": 716.0,
|
| 1836 |
+
"learning_rate": 0.001,
|
| 1837 |
+
"loss": 1772.7713,
|
| 1838 |
+
"step": 12432
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 0.25541320453522165,
|
| 1842 |
+
"grad_norm": 744.0,
|
| 1843 |
+
"learning_rate": 0.001,
|
| 1844 |
+
"loss": 1787.7516,
|
| 1845 |
+
"step": 12480
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 0.25639556301420324,
|
| 1849 |
+
"grad_norm": 744.0,
|
| 1850 |
+
"learning_rate": 0.001,
|
| 1851 |
+
"loss": 1785.005,
|
| 1852 |
+
"step": 12528
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 0.2573779214931849,
|
| 1856 |
+
"grad_norm": 716.0,
|
| 1857 |
+
"learning_rate": 0.001,
|
| 1858 |
+
"loss": 1763.7612,
|
| 1859 |
+
"step": 12576
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 0.2583602799721665,
|
| 1863 |
+
"grad_norm": 752.0,
|
| 1864 |
+
"learning_rate": 0.001,
|
| 1865 |
+
"loss": 1777.0677,
|
| 1866 |
+
"step": 12624
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 0.25934263845114813,
|
| 1870 |
+
"grad_norm": 712.0,
|
| 1871 |
+
"learning_rate": 0.001,
|
| 1872 |
+
"loss": 1761.1235,
|
| 1873 |
+
"step": 12672
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 0.2603249969301297,
|
| 1877 |
+
"grad_norm": 696.0,
|
| 1878 |
+
"learning_rate": 0.001,
|
| 1879 |
+
"loss": 1795.2174,
|
| 1880 |
+
"step": 12720
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 0.2613073554091114,
|
| 1884 |
+
"grad_norm": 816.0,
|
| 1885 |
+
"learning_rate": 0.001,
|
| 1886 |
+
"loss": 1763.8905,
|
| 1887 |
+
"step": 12768
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 0.262289713888093,
|
| 1891 |
+
"grad_norm": 852.0,
|
| 1892 |
+
"learning_rate": 0.001,
|
| 1893 |
+
"loss": 1761.4404,
|
| 1894 |
+
"step": 12816
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 0.2632720723670746,
|
| 1898 |
+
"grad_norm": 608.0,
|
| 1899 |
+
"learning_rate": 0.001,
|
| 1900 |
+
"loss": 1762.6668,
|
| 1901 |
+
"step": 12864
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 0.26425443084605627,
|
| 1905 |
+
"grad_norm": 892.0,
|
| 1906 |
+
"learning_rate": 0.001,
|
| 1907 |
+
"loss": 1725.5638,
|
| 1908 |
+
"step": 12912
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 0.26523678932503786,
|
| 1912 |
+
"grad_norm": 724.0,
|
| 1913 |
+
"learning_rate": 0.001,
|
| 1914 |
+
"loss": 1762.1764,
|
| 1915 |
+
"step": 12960
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 0.2662191478040195,
|
| 1919 |
+
"grad_norm": 728.0,
|
| 1920 |
+
"learning_rate": 0.001,
|
| 1921 |
+
"loss": 1764.0163,
|
| 1922 |
+
"step": 13008
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.2672015062830011,
|
| 1926 |
+
"grad_norm": 664.0,
|
| 1927 |
+
"learning_rate": 0.001,
|
| 1928 |
+
"loss": 1754.1729,
|
| 1929 |
+
"step": 13056
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.26818386476198275,
|
| 1933 |
+
"grad_norm": 724.0,
|
| 1934 |
+
"learning_rate": 0.001,
|
| 1935 |
+
"loss": 1772.8592,
|
| 1936 |
+
"step": 13104
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.26916622324096434,
|
| 1940 |
+
"grad_norm": 704.0,
|
| 1941 |
+
"learning_rate": 0.001,
|
| 1942 |
+
"loss": 1780.2349,
|
| 1943 |
+
"step": 13152
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 0.270148581719946,
|
| 1947 |
+
"grad_norm": 720.0,
|
| 1948 |
+
"learning_rate": 0.001,
|
| 1949 |
+
"loss": 1764.6678,
|
| 1950 |
+
"step": 13200
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 0.2711309401989276,
|
| 1954 |
+
"grad_norm": 772.0,
|
| 1955 |
+
"learning_rate": 0.001,
|
| 1956 |
+
"loss": 1757.6209,
|
| 1957 |
+
"step": 13248
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 0.27211329867790923,
|
| 1961 |
+
"grad_norm": 748.0,
|
| 1962 |
+
"learning_rate": 0.001,
|
| 1963 |
+
"loss": 1749.5741,
|
| 1964 |
+
"step": 13296
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 0.2730956571568908,
|
| 1968 |
+
"grad_norm": 804.0,
|
| 1969 |
+
"learning_rate": 0.001,
|
| 1970 |
+
"loss": 1758.4183,
|
| 1971 |
+
"step": 13344
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 0.2740780156358725,
|
| 1975 |
+
"grad_norm": 712.0,
|
| 1976 |
+
"learning_rate": 0.001,
|
| 1977 |
+
"loss": 1770.6115,
|
| 1978 |
+
"step": 13392
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 0.27506037411485407,
|
| 1982 |
+
"grad_norm": 784.0,
|
| 1983 |
+
"learning_rate": 0.001,
|
| 1984 |
+
"loss": 1752.6141,
|
| 1985 |
+
"step": 13440
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 0.2760427325938357,
|
| 1989 |
+
"grad_norm": 700.0,
|
| 1990 |
+
"learning_rate": 0.001,
|
| 1991 |
+
"loss": 1732.4147,
|
| 1992 |
+
"step": 13488
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 0.2770250910728173,
|
| 1996 |
+
"grad_norm": 780.0,
|
| 1997 |
+
"learning_rate": 0.001,
|
| 1998 |
+
"loss": 1757.4318,
|
| 1999 |
+
"step": 13536
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 0.27800744955179896,
|
| 2003 |
+
"grad_norm": 764.0,
|
| 2004 |
+
"learning_rate": 0.001,
|
| 2005 |
+
"loss": 1746.452,
|
| 2006 |
+
"step": 13584
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 0.27898980803078055,
|
| 2010 |
+
"grad_norm": 696.0,
|
| 2011 |
+
"learning_rate": 0.001,
|
| 2012 |
+
"loss": 1733.8742,
|
| 2013 |
+
"step": 13632
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 0.2799721665097622,
|
| 2017 |
+
"grad_norm": 824.0,
|
| 2018 |
+
"learning_rate": 0.001,
|
| 2019 |
+
"loss": 1761.4808,
|
| 2020 |
+
"step": 13680
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 0.2809545249887438,
|
| 2024 |
+
"grad_norm": 664.0,
|
| 2025 |
+
"learning_rate": 0.001,
|
| 2026 |
+
"loss": 1749.8506,
|
| 2027 |
+
"step": 13728
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 0.28193688346772544,
|
| 2031 |
+
"grad_norm": 776.0,
|
| 2032 |
+
"learning_rate": 0.001,
|
| 2033 |
+
"loss": 1734.1479,
|
| 2034 |
+
"step": 13776
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 0.28291924194670703,
|
| 2038 |
+
"grad_norm": 708.0,
|
| 2039 |
+
"learning_rate": 0.001,
|
| 2040 |
+
"loss": 1721.951,
|
| 2041 |
+
"step": 13824
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 0.2839016004256887,
|
| 2045 |
+
"grad_norm": 748.0,
|
| 2046 |
+
"learning_rate": 0.001,
|
| 2047 |
+
"loss": 1741.5046,
|
| 2048 |
+
"step": 13872
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 0.2848839589046703,
|
| 2052 |
+
"grad_norm": 764.0,
|
| 2053 |
+
"learning_rate": 0.001,
|
| 2054 |
+
"loss": 1743.1763,
|
| 2055 |
+
"step": 13920
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 0.2858663173836519,
|
| 2059 |
+
"grad_norm": 808.0,
|
| 2060 |
+
"learning_rate": 0.001,
|
| 2061 |
+
"loss": 1767.7448,
|
| 2062 |
+
"step": 13968
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 0.2868486758626335,
|
| 2066 |
+
"grad_norm": 696.0,
|
| 2067 |
+
"learning_rate": 0.001,
|
| 2068 |
+
"loss": 1717.0291,
|
| 2069 |
+
"step": 14016
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 0.28783103434161517,
|
| 2073 |
+
"grad_norm": 804.0,
|
| 2074 |
+
"learning_rate": 0.001,
|
| 2075 |
+
"loss": 1731.1566,
|
| 2076 |
+
"step": 14064
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 0.28881339282059676,
|
| 2080 |
+
"grad_norm": 788.0,
|
| 2081 |
+
"learning_rate": 0.001,
|
| 2082 |
+
"loss": 1720.1551,
|
| 2083 |
+
"step": 14112
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 0.2897957512995784,
|
| 2087 |
+
"grad_norm": 732.0,
|
| 2088 |
+
"learning_rate": 0.001,
|
| 2089 |
+
"loss": 1743.5467,
|
| 2090 |
+
"step": 14160
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 0.29077810977856,
|
| 2094 |
+
"grad_norm": 680.0,
|
| 2095 |
+
"learning_rate": 0.001,
|
| 2096 |
+
"loss": 1736.5747,
|
| 2097 |
+
"step": 14208
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 0.29176046825754165,
|
| 2101 |
+
"grad_norm": 740.0,
|
| 2102 |
+
"learning_rate": 0.001,
|
| 2103 |
+
"loss": 1737.3779,
|
| 2104 |
+
"step": 14256
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 0.29274282673652324,
|
| 2108 |
+
"grad_norm": 760.0,
|
| 2109 |
+
"learning_rate": 0.001,
|
| 2110 |
+
"loss": 1718.3322,
|
| 2111 |
+
"step": 14304
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 0.2937251852155049,
|
| 2115 |
+
"grad_norm": 760.0,
|
| 2116 |
+
"learning_rate": 0.001,
|
| 2117 |
+
"loss": 1736.3989,
|
| 2118 |
+
"step": 14352
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 0.29470754369448654,
|
| 2122 |
+
"grad_norm": 832.0,
|
| 2123 |
+
"learning_rate": 0.001,
|
| 2124 |
+
"loss": 1738.8551,
|
| 2125 |
+
"step": 14400
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 0.29568990217346813,
|
| 2129 |
+
"grad_norm": 900.0,
|
| 2130 |
+
"learning_rate": 0.001,
|
| 2131 |
+
"loss": 1711.0072,
|
| 2132 |
+
"step": 14448
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 0.2966722606524498,
|
| 2136 |
+
"grad_norm": 748.0,
|
| 2137 |
+
"learning_rate": 0.001,
|
| 2138 |
+
"loss": 1709.6022,
|
| 2139 |
+
"step": 14496
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 0.2976546191314314,
|
| 2143 |
+
"grad_norm": 704.0,
|
| 2144 |
+
"learning_rate": 0.001,
|
| 2145 |
+
"loss": 1741.5581,
|
| 2146 |
+
"step": 14544
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 0.298636977610413,
|
| 2150 |
+
"grad_norm": 684.0,
|
| 2151 |
+
"learning_rate": 0.001,
|
| 2152 |
+
"loss": 1715.0571,
|
| 2153 |
+
"step": 14592
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 0.2996193360893946,
|
| 2157 |
+
"grad_norm": 728.0,
|
| 2158 |
+
"learning_rate": 0.001,
|
| 2159 |
+
"loss": 1733.5199,
|
| 2160 |
+
"step": 14640
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 0.29998772051901273,
|
| 2164 |
+
"eval_loss": 1650.6409912109375,
|
| 2165 |
+
"eval_runtime": 9.0148,
|
| 2166 |
+
"eval_samples_per_second": 110.929,
|
| 2167 |
+
"eval_steps_per_second": 1.442,
|
| 2168 |
+
"step": 14658
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 0.30060169456837627,
|
| 2172 |
+
"grad_norm": 708.0,
|
| 2173 |
+
"learning_rate": 0.001,
|
| 2174 |
+
"loss": 1719.6375,
|
| 2175 |
+
"step": 14688
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 0.30158405304735786,
|
| 2179 |
+
"grad_norm": 616.0,
|
| 2180 |
+
"learning_rate": 0.001,
|
| 2181 |
+
"loss": 1728.5174,
|
| 2182 |
+
"step": 14736
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 0.3025664115263395,
|
| 2186 |
+
"grad_norm": 624.0,
|
| 2187 |
+
"learning_rate": 0.001,
|
| 2188 |
+
"loss": 1724.9813,
|
| 2189 |
+
"step": 14784
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 0.3035487700053211,
|
| 2193 |
+
"grad_norm": 716.0,
|
| 2194 |
+
"learning_rate": 0.001,
|
| 2195 |
+
"loss": 1704.8024,
|
| 2196 |
+
"step": 14832
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 0.30453112848430275,
|
| 2200 |
+
"grad_norm": 748.0,
|
| 2201 |
+
"learning_rate": 0.001,
|
| 2202 |
+
"loss": 1714.6235,
|
| 2203 |
+
"step": 14880
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 0.30551348696328434,
|
| 2207 |
+
"grad_norm": 1048.0,
|
| 2208 |
+
"learning_rate": 0.001,
|
| 2209 |
+
"loss": 1734.4709,
|
| 2210 |
+
"step": 14928
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 0.306495845442266,
|
| 2214 |
+
"grad_norm": 688.0,
|
| 2215 |
+
"learning_rate": 0.001,
|
| 2216 |
+
"loss": 1721.2712,
|
| 2217 |
+
"step": 14976
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 0.3074782039212476,
|
| 2221 |
+
"grad_norm": 724.0,
|
| 2222 |
+
"learning_rate": 0.001,
|
| 2223 |
+
"loss": 1752.32,
|
| 2224 |
+
"step": 15024
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 0.30846056240022923,
|
| 2228 |
+
"grad_norm": 792.0,
|
| 2229 |
+
"learning_rate": 0.001,
|
| 2230 |
+
"loss": 1711.9393,
|
| 2231 |
+
"step": 15072
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 0.3094429208792108,
|
| 2235 |
+
"grad_norm": 904.0,
|
| 2236 |
+
"learning_rate": 0.001,
|
| 2237 |
+
"loss": 1722.3177,
|
| 2238 |
+
"step": 15120
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 0.3104252793581925,
|
| 2242 |
+
"grad_norm": 768.0,
|
| 2243 |
+
"learning_rate": 0.001,
|
| 2244 |
+
"loss": 1737.7088,
|
| 2245 |
+
"step": 15168
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 0.31140763783717407,
|
| 2249 |
+
"grad_norm": 768.0,
|
| 2250 |
+
"learning_rate": 0.001,
|
| 2251 |
+
"loss": 1728.0853,
|
| 2252 |
+
"step": 15216
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 0.3123899963161557,
|
| 2256 |
+
"grad_norm": 776.0,
|
| 2257 |
+
"learning_rate": 0.001,
|
| 2258 |
+
"loss": 1711.749,
|
| 2259 |
+
"step": 15264
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 0.3133723547951373,
|
| 2263 |
+
"grad_norm": 840.0,
|
| 2264 |
+
"learning_rate": 0.001,
|
| 2265 |
+
"loss": 1717.5446,
|
| 2266 |
+
"step": 15312
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 0.31435471327411896,
|
| 2270 |
+
"grad_norm": 696.0,
|
| 2271 |
+
"learning_rate": 0.001,
|
| 2272 |
+
"loss": 1718.4888,
|
| 2273 |
+
"step": 15360
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 0.31533707175310055,
|
| 2277 |
+
"grad_norm": 692.0,
|
| 2278 |
+
"learning_rate": 0.001,
|
| 2279 |
+
"loss": 1722.6672,
|
| 2280 |
+
"step": 15408
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 0.3163194302320822,
|
| 2284 |
+
"grad_norm": 864.0,
|
| 2285 |
+
"learning_rate": 0.001,
|
| 2286 |
+
"loss": 1715.826,
|
| 2287 |
+
"step": 15456
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 0.3173017887110638,
|
| 2291 |
+
"grad_norm": 712.0,
|
| 2292 |
+
"learning_rate": 0.001,
|
| 2293 |
+
"loss": 1714.7765,
|
| 2294 |
+
"step": 15504
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 0.31828414719004544,
|
| 2298 |
+
"grad_norm": 712.0,
|
| 2299 |
+
"learning_rate": 0.001,
|
| 2300 |
+
"loss": 1718.0269,
|
| 2301 |
+
"step": 15552
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 0.31926650566902703,
|
| 2305 |
+
"grad_norm": 748.0,
|
| 2306 |
+
"learning_rate": 0.001,
|
| 2307 |
+
"loss": 1691.7855,
|
| 2308 |
+
"step": 15600
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 0.3202488641480087,
|
| 2312 |
+
"grad_norm": 888.0,
|
| 2313 |
+
"learning_rate": 0.001,
|
| 2314 |
+
"loss": 1717.6808,
|
| 2315 |
+
"step": 15648
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 0.3212312226269903,
|
| 2319 |
+
"grad_norm": 680.0,
|
| 2320 |
+
"learning_rate": 0.001,
|
| 2321 |
+
"loss": 1719.3472,
|
| 2322 |
+
"step": 15696
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 0.3222135811059719,
|
| 2326 |
+
"grad_norm": 868.0,
|
| 2327 |
+
"learning_rate": 0.001,
|
| 2328 |
+
"loss": 1691.0158,
|
| 2329 |
+
"step": 15744
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 0.3231959395849535,
|
| 2333 |
+
"grad_norm": 756.0,
|
| 2334 |
+
"learning_rate": 0.001,
|
| 2335 |
+
"loss": 1704.2186,
|
| 2336 |
+
"step": 15792
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 0.32417829806393517,
|
| 2340 |
+
"grad_norm": 888.0,
|
| 2341 |
+
"learning_rate": 0.001,
|
| 2342 |
+
"loss": 1723.0382,
|
| 2343 |
+
"step": 15840
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 0.32516065654291676,
|
| 2347 |
+
"grad_norm": 912.0,
|
| 2348 |
+
"learning_rate": 0.001,
|
| 2349 |
+
"loss": 1702.2889,
|
| 2350 |
+
"step": 15888
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 0.3261430150218984,
|
| 2354 |
+
"grad_norm": 820.0,
|
| 2355 |
+
"learning_rate": 0.001,
|
| 2356 |
+
"loss": 1728.0734,
|
| 2357 |
+
"step": 15936
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 0.32712537350088006,
|
| 2361 |
+
"grad_norm": 788.0,
|
| 2362 |
+
"learning_rate": 0.001,
|
| 2363 |
+
"loss": 1720.2152,
|
| 2364 |
+
"step": 15984
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 0.32810773197986165,
|
| 2368 |
+
"grad_norm": 808.0,
|
| 2369 |
+
"learning_rate": 0.001,
|
| 2370 |
+
"loss": 1702.1133,
|
| 2371 |
+
"step": 16032
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 0.3290900904588433,
|
| 2375 |
+
"grad_norm": 836.0,
|
| 2376 |
+
"learning_rate": 0.001,
|
| 2377 |
+
"loss": 1720.4746,
|
| 2378 |
+
"step": 16080
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 0.3300724489378249,
|
| 2382 |
+
"grad_norm": 836.0,
|
| 2383 |
+
"learning_rate": 0.001,
|
| 2384 |
+
"loss": 1689.6606,
|
| 2385 |
+
"step": 16128
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 0.33105480741680654,
|
| 2389 |
+
"grad_norm": 728.0,
|
| 2390 |
+
"learning_rate": 0.001,
|
| 2391 |
+
"loss": 1689.0417,
|
| 2392 |
+
"step": 16176
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 0.33203716589578813,
|
| 2396 |
+
"grad_norm": 848.0,
|
| 2397 |
+
"learning_rate": 0.001,
|
| 2398 |
+
"loss": 1703.012,
|
| 2399 |
+
"step": 16224
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 0.3330195243747698,
|
| 2403 |
+
"grad_norm": 756.0,
|
| 2404 |
+
"learning_rate": 0.001,
|
| 2405 |
+
"loss": 1700.2785,
|
| 2406 |
+
"step": 16272
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 0.3340018828537514,
|
| 2410 |
+
"grad_norm": 756.0,
|
| 2411 |
+
"learning_rate": 0.001,
|
| 2412 |
+
"loss": 1709.3231,
|
| 2413 |
+
"step": 16320
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 0.334984241332733,
|
| 2417 |
+
"grad_norm": 960.0,
|
| 2418 |
+
"learning_rate": 0.001,
|
| 2419 |
+
"loss": 1715.8831,
|
| 2420 |
+
"step": 16368
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 0.3359665998117146,
|
| 2424 |
+
"grad_norm": 692.0,
|
| 2425 |
+
"learning_rate": 0.001,
|
| 2426 |
+
"loss": 1695.813,
|
| 2427 |
+
"step": 16416
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 0.33694895829069627,
|
| 2431 |
+
"grad_norm": 688.0,
|
| 2432 |
+
"learning_rate": 0.001,
|
| 2433 |
+
"loss": 1685.9803,
|
| 2434 |
+
"step": 16464
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 0.33793131676967786,
|
| 2438 |
+
"grad_norm": 876.0,
|
| 2439 |
+
"learning_rate": 0.001,
|
| 2440 |
+
"loss": 1704.5868,
|
| 2441 |
+
"step": 16512
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 0.3389136752486595,
|
| 2445 |
+
"grad_norm": 732.0,
|
| 2446 |
+
"learning_rate": 0.001,
|
| 2447 |
+
"loss": 1681.2751,
|
| 2448 |
+
"step": 16560
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 0.3398960337276411,
|
| 2452 |
+
"grad_norm": 748.0,
|
| 2453 |
+
"learning_rate": 0.001,
|
| 2454 |
+
"loss": 1690.0252,
|
| 2455 |
+
"step": 16608
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 0.34087839220662275,
|
| 2459 |
+
"grad_norm": 780.0,
|
| 2460 |
+
"learning_rate": 0.001,
|
| 2461 |
+
"loss": 1698.1932,
|
| 2462 |
+
"step": 16656
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 0.34186075068560434,
|
| 2466 |
+
"grad_norm": 856.0,
|
| 2467 |
+
"learning_rate": 0.001,
|
| 2468 |
+
"loss": 1692.6128,
|
| 2469 |
+
"step": 16704
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 0.342843109164586,
|
| 2473 |
+
"grad_norm": 880.0,
|
| 2474 |
+
"learning_rate": 0.001,
|
| 2475 |
+
"loss": 1696.6901,
|
| 2476 |
+
"step": 16752
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 0.3438254676435676,
|
| 2480 |
+
"grad_norm": 688.0,
|
| 2481 |
+
"learning_rate": 0.001,
|
| 2482 |
+
"loss": 1693.9344,
|
| 2483 |
+
"step": 16800
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 0.34480782612254923,
|
| 2487 |
+
"grad_norm": 688.0,
|
| 2488 |
+
"learning_rate": 0.001,
|
| 2489 |
+
"loss": 1704.4855,
|
| 2490 |
+
"step": 16848
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 0.3457901846015308,
|
| 2494 |
+
"grad_norm": 692.0,
|
| 2495 |
+
"learning_rate": 0.001,
|
| 2496 |
+
"loss": 1705.7817,
|
| 2497 |
+
"step": 16896
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 0.3467725430805125,
|
| 2501 |
+
"grad_norm": 760.0,
|
| 2502 |
+
"learning_rate": 0.001,
|
| 2503 |
+
"loss": 1690.8944,
|
| 2504 |
+
"step": 16944
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 0.34775490155949407,
|
| 2508 |
+
"grad_norm": 868.0,
|
| 2509 |
+
"learning_rate": 0.001,
|
| 2510 |
+
"loss": 1685.9479,
|
| 2511 |
+
"step": 16992
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 0.3487372600384757,
|
| 2515 |
+
"grad_norm": 744.0,
|
| 2516 |
+
"learning_rate": 0.001,
|
| 2517 |
+
"loss": 1698.2961,
|
| 2518 |
+
"step": 17040
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 0.3497196185174573,
|
| 2522 |
+
"grad_norm": 688.0,
|
| 2523 |
+
"learning_rate": 0.001,
|
| 2524 |
+
"loss": 1693.7596,
|
| 2525 |
+
"step": 17088
|
| 2526 |
+
},
|
| 2527 |
+
{
|
| 2528 |
+
"epoch": 0.35070197699643896,
|
| 2529 |
+
"grad_norm": 760.0,
|
| 2530 |
+
"learning_rate": 0.001,
|
| 2531 |
+
"loss": 1702.9092,
|
| 2532 |
+
"step": 17136
|
| 2533 |
+
},
|
| 2534 |
+
{
|
| 2535 |
+
"epoch": 0.35168433547542055,
|
| 2536 |
+
"grad_norm": 788.0,
|
| 2537 |
+
"learning_rate": 0.001,
|
| 2538 |
+
"loss": 1672.0039,
|
| 2539 |
+
"step": 17184
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 0.3526666939544022,
|
| 2543 |
+
"grad_norm": 772.0,
|
| 2544 |
+
"learning_rate": 0.001,
|
| 2545 |
+
"loss": 1673.5811,
|
| 2546 |
+
"step": 17232
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 0.3536490524333838,
|
| 2550 |
+
"grad_norm": 976.0,
|
| 2551 |
+
"learning_rate": 0.001,
|
| 2552 |
+
"loss": 1697.0251,
|
| 2553 |
+
"step": 17280
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 0.35463141091236544,
|
| 2557 |
+
"grad_norm": 740.0,
|
| 2558 |
+
"learning_rate": 0.001,
|
| 2559 |
+
"loss": 1699.7508,
|
| 2560 |
+
"step": 17328
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 0.35561376939134703,
|
| 2564 |
+
"grad_norm": 704.0,
|
| 2565 |
+
"learning_rate": 0.001,
|
| 2566 |
+
"loss": 1708.7798,
|
| 2567 |
+
"step": 17376
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 0.3565961278703287,
|
| 2571 |
+
"grad_norm": 716.0,
|
| 2572 |
+
"learning_rate": 0.001,
|
| 2573 |
+
"loss": 1693.451,
|
| 2574 |
+
"step": 17424
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 0.3575784863493103,
|
| 2578 |
+
"grad_norm": 904.0,
|
| 2579 |
+
"learning_rate": 0.001,
|
| 2580 |
+
"loss": 1676.6382,
|
| 2581 |
+
"step": 17472
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 0.3585608448282919,
|
| 2585 |
+
"grad_norm": 700.0,
|
| 2586 |
+
"learning_rate": 0.001,
|
| 2587 |
+
"loss": 1691.7266,
|
| 2588 |
+
"step": 17520
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 0.3595432033072736,
|
| 2592 |
+
"grad_norm": 1012.0,
|
| 2593 |
+
"learning_rate": 0.001,
|
| 2594 |
+
"loss": 1666.9458,
|
| 2595 |
+
"step": 17568
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 0.36052556178625517,
|
| 2599 |
+
"grad_norm": 804.0,
|
| 2600 |
+
"learning_rate": 0.001,
|
| 2601 |
+
"loss": 1675.5584,
|
| 2602 |
+
"step": 17616
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 0.3615079202652368,
|
| 2606 |
+
"grad_norm": 856.0,
|
| 2607 |
+
"learning_rate": 0.001,
|
| 2608 |
+
"loss": 1685.9595,
|
| 2609 |
+
"step": 17664
|
| 2610 |
+
},
|
| 2611 |
+
{
|
| 2612 |
+
"epoch": 0.3624902787442184,
|
| 2613 |
+
"grad_norm": 836.0,
|
| 2614 |
+
"learning_rate": 0.001,
|
| 2615 |
+
"loss": 1695.4741,
|
| 2616 |
+
"step": 17712
|
| 2617 |
+
},
|
| 2618 |
+
{
|
| 2619 |
+
"epoch": 0.36347263722320006,
|
| 2620 |
+
"grad_norm": 696.0,
|
| 2621 |
+
"learning_rate": 0.001,
|
| 2622 |
+
"loss": 1689.256,
|
| 2623 |
+
"step": 17760
|
| 2624 |
+
},
|
| 2625 |
+
{
|
| 2626 |
+
"epoch": 0.36445499570218165,
|
| 2627 |
+
"grad_norm": 732.0,
|
| 2628 |
+
"learning_rate": 0.001,
|
| 2629 |
+
"loss": 1689.8599,
|
| 2630 |
+
"step": 17808
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 0.3654373541811633,
|
| 2634 |
+
"grad_norm": 876.0,
|
| 2635 |
+
"learning_rate": 0.001,
|
| 2636 |
+
"loss": 1668.894,
|
| 2637 |
+
"step": 17856
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 0.3664197126601449,
|
| 2641 |
+
"grad_norm": 780.0,
|
| 2642 |
+
"learning_rate": 0.001,
|
| 2643 |
+
"loss": 1684.5539,
|
| 2644 |
+
"step": 17904
|
| 2645 |
+
},
|
| 2646 |
+
{
|
| 2647 |
+
"epoch": 0.36740207113912654,
|
| 2648 |
+
"grad_norm": 952.0,
|
| 2649 |
+
"learning_rate": 0.001,
|
| 2650 |
+
"loss": 1683.5539,
|
| 2651 |
+
"step": 17952
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 0.36838442961810813,
|
| 2655 |
+
"grad_norm": 860.0,
|
| 2656 |
+
"learning_rate": 0.001,
|
| 2657 |
+
"loss": 1695.5282,
|
| 2658 |
+
"step": 18000
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 0.3693667880970898,
|
| 2662 |
+
"grad_norm": 844.0,
|
| 2663 |
+
"learning_rate": 0.001,
|
| 2664 |
+
"loss": 1667.8563,
|
| 2665 |
+
"step": 18048
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 0.3703491465760714,
|
| 2669 |
+
"grad_norm": 800.0,
|
| 2670 |
+
"learning_rate": 0.001,
|
| 2671 |
+
"loss": 1671.2471,
|
| 2672 |
+
"step": 18096
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 0.371331505055053,
|
| 2676 |
+
"grad_norm": 760.0,
|
| 2677 |
+
"learning_rate": 0.001,
|
| 2678 |
+
"loss": 1664.4082,
|
| 2679 |
+
"step": 18144
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 0.3723138635340346,
|
| 2683 |
+
"grad_norm": 1120.0,
|
| 2684 |
+
"learning_rate": 0.001,
|
| 2685 |
+
"loss": 1666.0448,
|
| 2686 |
+
"step": 18192
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 0.37329622201301627,
|
| 2690 |
+
"grad_norm": 824.0,
|
| 2691 |
+
"learning_rate": 0.001,
|
| 2692 |
+
"loss": 1665.9009,
|
| 2693 |
+
"step": 18240
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 0.37427858049199786,
|
| 2697 |
+
"grad_norm": 872.0,
|
| 2698 |
+
"learning_rate": 0.001,
|
| 2699 |
+
"loss": 1663.6131,
|
| 2700 |
+
"step": 18288
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 0.3752609389709795,
|
| 2704 |
+
"grad_norm": 804.0,
|
| 2705 |
+
"learning_rate": 0.001,
|
| 2706 |
+
"loss": 1665.7214,
|
| 2707 |
+
"step": 18336
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 0.3762432974499611,
|
| 2711 |
+
"grad_norm": 768.0,
|
| 2712 |
+
"learning_rate": 0.001,
|
| 2713 |
+
"loss": 1663.0591,
|
| 2714 |
+
"step": 18384
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 0.37722565592894275,
|
| 2718 |
+
"grad_norm": 988.0,
|
| 2719 |
+
"learning_rate": 0.001,
|
| 2720 |
+
"loss": 1683.5985,
|
| 2721 |
+
"step": 18432
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 0.37820801440792434,
|
| 2725 |
+
"grad_norm": 804.0,
|
| 2726 |
+
"learning_rate": 0.001,
|
| 2727 |
+
"loss": 1661.8081,
|
| 2728 |
+
"step": 18480
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 0.379190372886906,
|
| 2732 |
+
"grad_norm": 776.0,
|
| 2733 |
+
"learning_rate": 0.001,
|
| 2734 |
+
"loss": 1685.9769,
|
| 2735 |
+
"step": 18528
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 0.3801727313658876,
|
| 2739 |
+
"grad_norm": 920.0,
|
| 2740 |
+
"learning_rate": 0.001,
|
| 2741 |
+
"loss": 1676.7816,
|
| 2742 |
+
"step": 18576
|
| 2743 |
+
},
|
| 2744 |
+
{
|
| 2745 |
+
"epoch": 0.38115508984486923,
|
| 2746 |
+
"grad_norm": 800.0,
|
| 2747 |
+
"learning_rate": 0.001,
|
| 2748 |
+
"loss": 1669.9821,
|
| 2749 |
+
"step": 18624
|
| 2750 |
+
},
|
| 2751 |
+
{
|
| 2752 |
+
"epoch": 0.3821374483238508,
|
| 2753 |
+
"grad_norm": 828.0,
|
| 2754 |
+
"learning_rate": 0.001,
|
| 2755 |
+
"loss": 1654.353,
|
| 2756 |
+
"step": 18672
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 0.3831198068028325,
|
| 2760 |
+
"grad_norm": 756.0,
|
| 2761 |
+
"learning_rate": 0.001,
|
| 2762 |
+
"loss": 1641.133,
|
| 2763 |
+
"step": 18720
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 0.38410216528181407,
|
| 2767 |
+
"grad_norm": 772.0,
|
| 2768 |
+
"learning_rate": 0.001,
|
| 2769 |
+
"loss": 1654.8257,
|
| 2770 |
+
"step": 18768
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 0.3850845237607957,
|
| 2774 |
+
"grad_norm": 856.0,
|
| 2775 |
+
"learning_rate": 0.001,
|
| 2776 |
+
"loss": 1674.0685,
|
| 2777 |
+
"step": 18816
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 0.3860668822397773,
|
| 2781 |
+
"grad_norm": 980.0,
|
| 2782 |
+
"learning_rate": 0.001,
|
| 2783 |
+
"loss": 1663.0804,
|
| 2784 |
+
"step": 18864
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 0.38704924071875896,
|
| 2788 |
+
"grad_norm": 852.0,
|
| 2789 |
+
"learning_rate": 0.001,
|
| 2790 |
+
"loss": 1676.6375,
|
| 2791 |
+
"step": 18912
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 0.38803159919774055,
|
| 2795 |
+
"grad_norm": 788.0,
|
| 2796 |
+
"learning_rate": 0.001,
|
| 2797 |
+
"loss": 1681.3968,
|
| 2798 |
+
"step": 18960
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 0.3890139576767222,
|
| 2802 |
+
"grad_norm": 740.0,
|
| 2803 |
+
"learning_rate": 0.001,
|
| 2804 |
+
"loss": 1658.5428,
|
| 2805 |
+
"step": 19008
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 0.3899963161557038,
|
| 2809 |
+
"grad_norm": 772.0,
|
| 2810 |
+
"learning_rate": 0.001,
|
| 2811 |
+
"loss": 1693.6683,
|
| 2812 |
+
"step": 19056
|
| 2813 |
+
},
|
| 2814 |
+
{
|
| 2815 |
+
"epoch": 0.39097867463468544,
|
| 2816 |
+
"grad_norm": 1224.0,
|
| 2817 |
+
"learning_rate": 0.001,
|
| 2818 |
+
"loss": 1637.9217,
|
| 2819 |
+
"step": 19104
|
| 2820 |
+
},
|
| 2821 |
+
{
|
| 2822 |
+
"epoch": 0.3919610331136671,
|
| 2823 |
+
"grad_norm": 896.0,
|
| 2824 |
+
"learning_rate": 0.001,
|
| 2825 |
+
"loss": 1680.59,
|
| 2826 |
+
"step": 19152
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 0.3929433915926487,
|
| 2830 |
+
"grad_norm": 716.0,
|
| 2831 |
+
"learning_rate": 0.001,
|
| 2832 |
+
"loss": 1663.9777,
|
| 2833 |
+
"step": 19200
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 0.39392575007163033,
|
| 2837 |
+
"grad_norm": 940.0,
|
| 2838 |
+
"learning_rate": 0.001,
|
| 2839 |
+
"loss": 1672.4491,
|
| 2840 |
+
"step": 19248
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 0.3949081085506119,
|
| 2844 |
+
"grad_norm": 696.0,
|
| 2845 |
+
"learning_rate": 0.001,
|
| 2846 |
+
"loss": 1668.8294,
|
| 2847 |
+
"step": 19296
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 0.3958904670295936,
|
| 2851 |
+
"grad_norm": 740.0,
|
| 2852 |
+
"learning_rate": 0.001,
|
| 2853 |
+
"loss": 1652.0028,
|
| 2854 |
+
"step": 19344
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 0.39687282550857517,
|
| 2858 |
+
"grad_norm": 900.0,
|
| 2859 |
+
"learning_rate": 0.001,
|
| 2860 |
+
"loss": 1670.4543,
|
| 2861 |
+
"step": 19392
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 0.3978551839875568,
|
| 2865 |
+
"grad_norm": 832.0,
|
| 2866 |
+
"learning_rate": 0.001,
|
| 2867 |
+
"loss": 1674.2799,
|
| 2868 |
+
"step": 19440
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 0.3988375424665384,
|
| 2872 |
+
"grad_norm": 896.0,
|
| 2873 |
+
"learning_rate": 0.001,
|
| 2874 |
+
"loss": 1637.7557,
|
| 2875 |
+
"step": 19488
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 0.39981990094552006,
|
| 2879 |
+
"grad_norm": 772.0,
|
| 2880 |
+
"learning_rate": 0.001,
|
| 2881 |
+
"loss": 1659.3999,
|
| 2882 |
+
"step": 19536
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 0.39998362735868365,
|
| 2886 |
+
"eval_loss": 1588.186767578125,
|
| 2887 |
+
"eval_runtime": 9.0185,
|
| 2888 |
+
"eval_samples_per_second": 110.884,
|
| 2889 |
+
"eval_steps_per_second": 1.441,
|
| 2890 |
+
"step": 19544
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 0.40080225942450165,
|
| 2894 |
+
"grad_norm": 812.0,
|
| 2895 |
+
"learning_rate": 0.001,
|
| 2896 |
+
"loss": 1663.3135,
|
| 2897 |
+
"step": 19584
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 0.4017846179034833,
|
| 2901 |
+
"grad_norm": 820.0,
|
| 2902 |
+
"learning_rate": 0.001,
|
| 2903 |
+
"loss": 1648.4126,
|
| 2904 |
+
"step": 19632
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 0.4027669763824649,
|
| 2908 |
+
"grad_norm": 828.0,
|
| 2909 |
+
"learning_rate": 0.001,
|
| 2910 |
+
"loss": 1629.137,
|
| 2911 |
+
"step": 19680
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 0.40374933486144654,
|
| 2915 |
+
"grad_norm": 840.0,
|
| 2916 |
+
"learning_rate": 0.001,
|
| 2917 |
+
"loss": 1675.1574,
|
| 2918 |
+
"step": 19728
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 0.40473169334042813,
|
| 2922 |
+
"grad_norm": 892.0,
|
| 2923 |
+
"learning_rate": 0.001,
|
| 2924 |
+
"loss": 1651.4735,
|
| 2925 |
+
"step": 19776
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 0.4057140518194098,
|
| 2929 |
+
"grad_norm": 732.0,
|
| 2930 |
+
"learning_rate": 0.001,
|
| 2931 |
+
"loss": 1659.3854,
|
| 2932 |
+
"step": 19824
|
| 2933 |
+
},
|
| 2934 |
+
{
|
| 2935 |
+
"epoch": 0.4066964102983914,
|
| 2936 |
+
"grad_norm": 808.0,
|
| 2937 |
+
"learning_rate": 0.001,
|
| 2938 |
+
"loss": 1676.7249,
|
| 2939 |
+
"step": 19872
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 0.407678768777373,
|
| 2943 |
+
"grad_norm": 1088.0,
|
| 2944 |
+
"learning_rate": 0.001,
|
| 2945 |
+
"loss": 1658.8581,
|
| 2946 |
+
"step": 19920
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 0.4086611272563546,
|
| 2950 |
+
"grad_norm": 772.0,
|
| 2951 |
+
"learning_rate": 0.001,
|
| 2952 |
+
"loss": 1663.8711,
|
| 2953 |
+
"step": 19968
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 0.40964348573533627,
|
| 2957 |
+
"grad_norm": 724.0,
|
| 2958 |
+
"learning_rate": 0.001,
|
| 2959 |
+
"loss": 1657.056,
|
| 2960 |
+
"step": 20016
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 0.41062584421431786,
|
| 2964 |
+
"grad_norm": 920.0,
|
| 2965 |
+
"learning_rate": 0.001,
|
| 2966 |
+
"loss": 1637.993,
|
| 2967 |
+
"step": 20064
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 0.4116082026932995,
|
| 2971 |
+
"grad_norm": 636.0,
|
| 2972 |
+
"learning_rate": 0.001,
|
| 2973 |
+
"loss": 1644.8833,
|
| 2974 |
+
"step": 20112
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 0.4125905611722811,
|
| 2978 |
+
"grad_norm": 956.0,
|
| 2979 |
+
"learning_rate": 0.001,
|
| 2980 |
+
"loss": 1656.4339,
|
| 2981 |
+
"step": 20160
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 0.41357291965126275,
|
| 2985 |
+
"grad_norm": 792.0,
|
| 2986 |
+
"learning_rate": 0.001,
|
| 2987 |
+
"loss": 1652.4888,
|
| 2988 |
+
"step": 20208
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 0.41455527813024434,
|
| 2992 |
+
"grad_norm": 832.0,
|
| 2993 |
+
"learning_rate": 0.001,
|
| 2994 |
+
"loss": 1642.5142,
|
| 2995 |
+
"step": 20256
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 0.415537636609226,
|
| 2999 |
+
"grad_norm": 724.0,
|
| 3000 |
+
"learning_rate": 0.001,
|
| 3001 |
+
"loss": 1668.1183,
|
| 3002 |
+
"step": 20304
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 0.4165199950882076,
|
| 3006 |
+
"grad_norm": 796.0,
|
| 3007 |
+
"learning_rate": 0.001,
|
| 3008 |
+
"loss": 1660.486,
|
| 3009 |
+
"step": 20352
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 0.41750235356718923,
|
| 3013 |
+
"grad_norm": 788.0,
|
| 3014 |
+
"learning_rate": 0.001,
|
| 3015 |
+
"loss": 1655.4614,
|
| 3016 |
+
"step": 20400
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 0.4184847120461708,
|
| 3020 |
+
"grad_norm": 844.0,
|
| 3021 |
+
"learning_rate": 0.001,
|
| 3022 |
+
"loss": 1650.6449,
|
| 3023 |
+
"step": 20448
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 0.4194670705251525,
|
| 3027 |
+
"grad_norm": 1080.0,
|
| 3028 |
+
"learning_rate": 0.001,
|
| 3029 |
+
"loss": 1639.0168,
|
| 3030 |
+
"step": 20496
|
| 3031 |
+
},
|
| 3032 |
+
{
|
| 3033 |
+
"epoch": 0.42044942900413407,
|
| 3034 |
+
"grad_norm": 944.0,
|
| 3035 |
+
"learning_rate": 0.001,
|
| 3036 |
+
"loss": 1655.6951,
|
| 3037 |
+
"step": 20544
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 0.4214317874831157,
|
| 3041 |
+
"grad_norm": 716.0,
|
| 3042 |
+
"learning_rate": 0.001,
|
| 3043 |
+
"loss": 1644.007,
|
| 3044 |
+
"step": 20592
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 0.4224141459620973,
|
| 3048 |
+
"grad_norm": 896.0,
|
| 3049 |
+
"learning_rate": 0.001,
|
| 3050 |
+
"loss": 1614.1253,
|
| 3051 |
+
"step": 20640
|
| 3052 |
+
},
|
| 3053 |
+
{
|
| 3054 |
+
"epoch": 0.42339650444107896,
|
| 3055 |
+
"grad_norm": 736.0,
|
| 3056 |
+
"learning_rate": 0.001,
|
| 3057 |
+
"loss": 1637.6761,
|
| 3058 |
+
"step": 20688
|
| 3059 |
+
},
|
| 3060 |
+
{
|
| 3061 |
+
"epoch": 0.42437886292006055,
|
| 3062 |
+
"grad_norm": 752.0,
|
| 3063 |
+
"learning_rate": 0.001,
|
| 3064 |
+
"loss": 1635.8405,
|
| 3065 |
+
"step": 20736
|
| 3066 |
+
},
|
| 3067 |
+
{
|
| 3068 |
+
"epoch": 0.4253612213990422,
|
| 3069 |
+
"grad_norm": 768.0,
|
| 3070 |
+
"learning_rate": 0.001,
|
| 3071 |
+
"loss": 1653.1647,
|
| 3072 |
+
"step": 20784
|
| 3073 |
+
},
|
| 3074 |
+
{
|
| 3075 |
+
"epoch": 0.42634357987802385,
|
| 3076 |
+
"grad_norm": 832.0,
|
| 3077 |
+
"learning_rate": 0.001,
|
| 3078 |
+
"loss": 1657.5373,
|
| 3079 |
+
"step": 20832
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 0.42732593835700544,
|
| 3083 |
+
"grad_norm": 832.0,
|
| 3084 |
+
"learning_rate": 0.001,
|
| 3085 |
+
"loss": 1649.7998,
|
| 3086 |
+
"step": 20880
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 0.4283082968359871,
|
| 3090 |
+
"grad_norm": 848.0,
|
| 3091 |
+
"learning_rate": 0.001,
|
| 3092 |
+
"loss": 1639.043,
|
| 3093 |
+
"step": 20928
|
| 3094 |
+
},
|
| 3095 |
+
{
|
| 3096 |
+
"epoch": 0.4292906553149687,
|
| 3097 |
+
"grad_norm": 716.0,
|
| 3098 |
+
"learning_rate": 0.001,
|
| 3099 |
+
"loss": 1656.0706,
|
| 3100 |
+
"step": 20976
|
| 3101 |
+
},
|
| 3102 |
+
{
|
| 3103 |
+
"epoch": 0.43027301379395033,
|
| 3104 |
+
"grad_norm": 924.0,
|
| 3105 |
+
"learning_rate": 0.001,
|
| 3106 |
+
"loss": 1640.4744,
|
| 3107 |
+
"step": 21024
|
| 3108 |
+
},
|
| 3109 |
+
{
|
| 3110 |
+
"epoch": 0.4312553722729319,
|
| 3111 |
+
"grad_norm": 832.0,
|
| 3112 |
+
"learning_rate": 0.001,
|
| 3113 |
+
"loss": 1640.8403,
|
| 3114 |
+
"step": 21072
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"epoch": 0.4322377307519136,
|
| 3118 |
+
"grad_norm": 828.0,
|
| 3119 |
+
"learning_rate": 0.001,
|
| 3120 |
+
"loss": 1638.4172,
|
| 3121 |
+
"step": 21120
|
| 3122 |
+
},
|
| 3123 |
+
{
|
| 3124 |
+
"epoch": 0.43322008923089517,
|
| 3125 |
+
"grad_norm": 732.0,
|
| 3126 |
+
"learning_rate": 0.001,
|
| 3127 |
+
"loss": 1662.0506,
|
| 3128 |
+
"step": 21168
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 0.4342024477098768,
|
| 3132 |
+
"grad_norm": 752.0,
|
| 3133 |
+
"learning_rate": 0.001,
|
| 3134 |
+
"loss": 1634.0928,
|
| 3135 |
+
"step": 21216
|
| 3136 |
+
},
|
| 3137 |
+
{
|
| 3138 |
+
"epoch": 0.4351848061888584,
|
| 3139 |
+
"grad_norm": 976.0,
|
| 3140 |
+
"learning_rate": 0.001,
|
| 3141 |
+
"loss": 1650.1844,
|
| 3142 |
+
"step": 21264
|
| 3143 |
+
},
|
| 3144 |
+
{
|
| 3145 |
+
"epoch": 0.43616716466784006,
|
| 3146 |
+
"grad_norm": 864.0,
|
| 3147 |
+
"learning_rate": 0.001,
|
| 3148 |
+
"loss": 1637.9504,
|
| 3149 |
+
"step": 21312
|
| 3150 |
+
},
|
| 3151 |
+
{
|
| 3152 |
+
"epoch": 0.43714952314682165,
|
| 3153 |
+
"grad_norm": 660.0,
|
| 3154 |
+
"learning_rate": 0.001,
|
| 3155 |
+
"loss": 1651.0807,
|
| 3156 |
+
"step": 21360
|
| 3157 |
+
},
|
| 3158 |
+
{
|
| 3159 |
+
"epoch": 0.4381318816258033,
|
| 3160 |
+
"grad_norm": 884.0,
|
| 3161 |
+
"learning_rate": 0.001,
|
| 3162 |
+
"loss": 1639.6099,
|
| 3163 |
+
"step": 21408
|
| 3164 |
+
},
|
| 3165 |
+
{
|
| 3166 |
+
"epoch": 0.4391142401047849,
|
| 3167 |
+
"grad_norm": 752.0,
|
| 3168 |
+
"learning_rate": 0.001,
|
| 3169 |
+
"loss": 1636.7961,
|
| 3170 |
+
"step": 21456
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"epoch": 0.44009659858376654,
|
| 3174 |
+
"grad_norm": 704.0,
|
| 3175 |
+
"learning_rate": 0.001,
|
| 3176 |
+
"loss": 1630.2891,
|
| 3177 |
+
"step": 21504
|
| 3178 |
+
},
|
| 3179 |
+
{
|
| 3180 |
+
"epoch": 0.44107895706274813,
|
| 3181 |
+
"grad_norm": 868.0,
|
| 3182 |
+
"learning_rate": 0.001,
|
| 3183 |
+
"loss": 1651.1029,
|
| 3184 |
+
"step": 21552
|
| 3185 |
+
},
|
| 3186 |
+
{
|
| 3187 |
+
"epoch": 0.4420613155417298,
|
| 3188 |
+
"grad_norm": 1200.0,
|
| 3189 |
+
"learning_rate": 0.001,
|
| 3190 |
+
"loss": 1658.1079,
|
| 3191 |
+
"step": 21600
|
| 3192 |
+
},
|
| 3193 |
+
{
|
| 3194 |
+
"epoch": 0.4430436740207114,
|
| 3195 |
+
"grad_norm": 820.0,
|
| 3196 |
+
"learning_rate": 0.001,
|
| 3197 |
+
"loss": 1650.035,
|
| 3198 |
+
"step": 21648
|
| 3199 |
+
},
|
| 3200 |
+
{
|
| 3201 |
+
"epoch": 0.444026032499693,
|
| 3202 |
+
"grad_norm": 628.0,
|
| 3203 |
+
"learning_rate": 0.001,
|
| 3204 |
+
"loss": 1651.446,
|
| 3205 |
+
"step": 21696
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 0.4450083909786746,
|
| 3209 |
+
"grad_norm": 936.0,
|
| 3210 |
+
"learning_rate": 0.001,
|
| 3211 |
+
"loss": 1651.8545,
|
| 3212 |
+
"step": 21744
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 0.44599074945765627,
|
| 3216 |
+
"grad_norm": 724.0,
|
| 3217 |
+
"learning_rate": 0.001,
|
| 3218 |
+
"loss": 1633.7931,
|
| 3219 |
+
"step": 21792
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 0.44697310793663786,
|
| 3223 |
+
"grad_norm": 868.0,
|
| 3224 |
+
"learning_rate": 0.001,
|
| 3225 |
+
"loss": 1643.6271,
|
| 3226 |
+
"step": 21840
|
| 3227 |
+
},
|
| 3228 |
+
{
|
| 3229 |
+
"epoch": 0.4479554664156195,
|
| 3230 |
+
"grad_norm": 884.0,
|
| 3231 |
+
"learning_rate": 0.001,
|
| 3232 |
+
"loss": 1628.9087,
|
| 3233 |
+
"step": 21888
|
| 3234 |
+
},
|
| 3235 |
+
{
|
| 3236 |
+
"epoch": 0.4489378248946011,
|
| 3237 |
+
"grad_norm": 808.0,
|
| 3238 |
+
"learning_rate": 0.001,
|
| 3239 |
+
"loss": 1633.3311,
|
| 3240 |
+
"step": 21936
|
| 3241 |
+
},
|
| 3242 |
+
{
|
| 3243 |
+
"epoch": 0.44992018337358275,
|
| 3244 |
+
"grad_norm": 776.0,
|
| 3245 |
+
"learning_rate": 0.001,
|
| 3246 |
+
"loss": 1636.3483,
|
| 3247 |
+
"step": 21984
|
| 3248 |
+
},
|
| 3249 |
+
{
|
| 3250 |
+
"epoch": 0.45090254185256434,
|
| 3251 |
+
"grad_norm": 740.0,
|
| 3252 |
+
"learning_rate": 0.001,
|
| 3253 |
+
"loss": 1627.1842,
|
| 3254 |
+
"step": 22032
|
| 3255 |
+
},
|
| 3256 |
+
{
|
| 3257 |
+
"epoch": 0.451884900331546,
|
| 3258 |
+
"grad_norm": 832.0,
|
| 3259 |
+
"learning_rate": 0.001,
|
| 3260 |
+
"loss": 1632.6536,
|
| 3261 |
+
"step": 22080
|
| 3262 |
+
},
|
| 3263 |
+
{
|
| 3264 |
+
"epoch": 0.4528672588105276,
|
| 3265 |
+
"grad_norm": 920.0,
|
| 3266 |
+
"learning_rate": 0.001,
|
| 3267 |
+
"loss": 1663.3418,
|
| 3268 |
+
"step": 22128
|
| 3269 |
+
},
|
| 3270 |
+
{
|
| 3271 |
+
"epoch": 0.45384961728950923,
|
| 3272 |
+
"grad_norm": 752.0,
|
| 3273 |
+
"learning_rate": 0.001,
|
| 3274 |
+
"loss": 1635.7738,
|
| 3275 |
+
"step": 22176
|
| 3276 |
+
},
|
| 3277 |
+
{
|
| 3278 |
+
"epoch": 0.4548319757684908,
|
| 3279 |
+
"grad_norm": 752.0,
|
| 3280 |
+
"learning_rate": 0.001,
|
| 3281 |
+
"loss": 1636.0459,
|
| 3282 |
+
"step": 22224
|
| 3283 |
+
},
|
| 3284 |
+
{
|
| 3285 |
+
"epoch": 0.4558143342474725,
|
| 3286 |
+
"grad_norm": 892.0,
|
| 3287 |
+
"learning_rate": 0.001,
|
| 3288 |
+
"loss": 1627.4956,
|
| 3289 |
+
"step": 22272
|
| 3290 |
+
},
|
| 3291 |
+
{
|
| 3292 |
+
"epoch": 0.45679669272645407,
|
| 3293 |
+
"grad_norm": 860.0,
|
| 3294 |
+
"learning_rate": 0.001,
|
| 3295 |
+
"loss": 1628.1626,
|
| 3296 |
+
"step": 22320
|
| 3297 |
+
},
|
| 3298 |
+
{
|
| 3299 |
+
"epoch": 0.4577790512054357,
|
| 3300 |
+
"grad_norm": 776.0,
|
| 3301 |
+
"learning_rate": 0.001,
|
| 3302 |
+
"loss": 1628.0701,
|
| 3303 |
+
"step": 22368
|
| 3304 |
+
},
|
| 3305 |
+
{
|
| 3306 |
+
"epoch": 0.45876140968441737,
|
| 3307 |
+
"grad_norm": 792.0,
|
| 3308 |
+
"learning_rate": 0.001,
|
| 3309 |
+
"loss": 1644.1922,
|
| 3310 |
+
"step": 22416
|
| 3311 |
+
},
|
| 3312 |
+
{
|
| 3313 |
+
"epoch": 0.45974376816339896,
|
| 3314 |
+
"grad_norm": 776.0,
|
| 3315 |
+
"learning_rate": 0.001,
|
| 3316 |
+
"loss": 1608.5988,
|
| 3317 |
+
"step": 22464
|
| 3318 |
+
},
|
| 3319 |
+
{
|
| 3320 |
+
"epoch": 0.4607261266423806,
|
| 3321 |
+
"grad_norm": 860.0,
|
| 3322 |
+
"learning_rate": 0.001,
|
| 3323 |
+
"loss": 1637.166,
|
| 3324 |
+
"step": 22512
|
| 3325 |
+
},
|
| 3326 |
+
{
|
| 3327 |
+
"epoch": 0.4617084851213622,
|
| 3328 |
+
"grad_norm": 924.0,
|
| 3329 |
+
"learning_rate": 0.001,
|
| 3330 |
+
"loss": 1626.6854,
|
| 3331 |
+
"step": 22560
|
| 3332 |
+
},
|
| 3333 |
+
{
|
| 3334 |
+
"epoch": 0.46269084360034385,
|
| 3335 |
+
"grad_norm": 876.0,
|
| 3336 |
+
"learning_rate": 0.001,
|
| 3337 |
+
"loss": 1639.1245,
|
| 3338 |
+
"step": 22608
|
| 3339 |
+
},
|
| 3340 |
+
{
|
| 3341 |
+
"epoch": 0.46367320207932544,
|
| 3342 |
+
"grad_norm": 936.0,
|
| 3343 |
+
"learning_rate": 0.001,
|
| 3344 |
+
"loss": 1634.3815,
|
| 3345 |
+
"step": 22656
|
| 3346 |
+
},
|
| 3347 |
+
{
|
| 3348 |
+
"epoch": 0.4646555605583071,
|
| 3349 |
+
"grad_norm": 912.0,
|
| 3350 |
+
"learning_rate": 0.001,
|
| 3351 |
+
"loss": 1606.1912,
|
| 3352 |
+
"step": 22704
|
| 3353 |
+
},
|
| 3354 |
+
{
|
| 3355 |
+
"epoch": 0.4656379190372887,
|
| 3356 |
+
"grad_norm": 952.0,
|
| 3357 |
+
"learning_rate": 0.001,
|
| 3358 |
+
"loss": 1620.5391,
|
| 3359 |
+
"step": 22752
|
| 3360 |
+
},
|
| 3361 |
+
{
|
| 3362 |
+
"epoch": 0.46662027751627033,
|
| 3363 |
+
"grad_norm": 960.0,
|
| 3364 |
+
"learning_rate": 0.001,
|
| 3365 |
+
"loss": 1612.0667,
|
| 3366 |
+
"step": 22800
|
| 3367 |
+
},
|
| 3368 |
+
{
|
| 3369 |
+
"epoch": 0.4676026359952519,
|
| 3370 |
+
"grad_norm": 832.0,
|
| 3371 |
+
"learning_rate": 0.001,
|
| 3372 |
+
"loss": 1651.9868,
|
| 3373 |
+
"step": 22848
|
| 3374 |
+
},
|
| 3375 |
+
{
|
| 3376 |
+
"epoch": 0.4685849944742336,
|
| 3377 |
+
"grad_norm": 712.0,
|
| 3378 |
+
"learning_rate": 0.001,
|
| 3379 |
+
"loss": 1629.237,
|
| 3380 |
+
"step": 22896
|
| 3381 |
+
},
|
| 3382 |
+
{
|
| 3383 |
+
"epoch": 0.46956735295321517,
|
| 3384 |
+
"grad_norm": 864.0,
|
| 3385 |
+
"learning_rate": 0.001,
|
| 3386 |
+
"loss": 1618.2004,
|
| 3387 |
+
"step": 22944
|
| 3388 |
+
},
|
| 3389 |
+
{
|
| 3390 |
+
"epoch": 0.4705497114321968,
|
| 3391 |
+
"grad_norm": 728.0,
|
| 3392 |
+
"learning_rate": 0.001,
|
| 3393 |
+
"loss": 1625.5379,
|
| 3394 |
+
"step": 22992
|
| 3395 |
+
},
|
| 3396 |
+
{
|
| 3397 |
+
"epoch": 0.4715320699111784,
|
| 3398 |
+
"grad_norm": 836.0,
|
| 3399 |
+
"learning_rate": 0.001,
|
| 3400 |
+
"loss": 1622.8146,
|
| 3401 |
+
"step": 23040
|
| 3402 |
+
},
|
| 3403 |
+
{
|
| 3404 |
+
"epoch": 0.47251442839016006,
|
| 3405 |
+
"grad_norm": 1064.0,
|
| 3406 |
+
"learning_rate": 0.001,
|
| 3407 |
+
"loss": 1623.9705,
|
| 3408 |
+
"step": 23088
|
| 3409 |
+
},
|
| 3410 |
+
{
|
| 3411 |
+
"epoch": 0.47349678686914165,
|
| 3412 |
+
"grad_norm": 860.0,
|
| 3413 |
+
"learning_rate": 0.001,
|
| 3414 |
+
"loss": 1626.2383,
|
| 3415 |
+
"step": 23136
|
| 3416 |
+
},
|
| 3417 |
+
{
|
| 3418 |
+
"epoch": 0.4744791453481233,
|
| 3419 |
+
"grad_norm": 1120.0,
|
| 3420 |
+
"learning_rate": 0.001,
|
| 3421 |
+
"loss": 1634.2668,
|
| 3422 |
+
"step": 23184
|
| 3423 |
+
},
|
| 3424 |
+
{
|
| 3425 |
+
"epoch": 0.4754615038271049,
|
| 3426 |
+
"grad_norm": 796.0,
|
| 3427 |
+
"learning_rate": 0.001,
|
| 3428 |
+
"loss": 1642.5649,
|
| 3429 |
+
"step": 23232
|
| 3430 |
+
},
|
| 3431 |
+
{
|
| 3432 |
+
"epoch": 0.47644386230608654,
|
| 3433 |
+
"grad_norm": 1072.0,
|
| 3434 |
+
"learning_rate": 0.001,
|
| 3435 |
+
"loss": 1633.4873,
|
| 3436 |
+
"step": 23280
|
| 3437 |
+
},
|
| 3438 |
+
{
|
| 3439 |
+
"epoch": 0.47742622078506813,
|
| 3440 |
+
"grad_norm": 904.0,
|
| 3441 |
+
"learning_rate": 0.001,
|
| 3442 |
+
"loss": 1604.186,
|
| 3443 |
+
"step": 23328
|
| 3444 |
+
},
|
| 3445 |
+
{
|
| 3446 |
+
"epoch": 0.4784085792640498,
|
| 3447 |
+
"grad_norm": 852.0,
|
| 3448 |
+
"learning_rate": 0.001,
|
| 3449 |
+
"loss": 1608.5158,
|
| 3450 |
+
"step": 23376
|
| 3451 |
+
},
|
| 3452 |
+
{
|
| 3453 |
+
"epoch": 0.4793909377430314,
|
| 3454 |
+
"grad_norm": 860.0,
|
| 3455 |
+
"learning_rate": 0.001,
|
| 3456 |
+
"loss": 1624.3991,
|
| 3457 |
+
"step": 23424
|
| 3458 |
+
},
|
| 3459 |
+
{
|
| 3460 |
+
"epoch": 0.480373296222013,
|
| 3461 |
+
"grad_norm": 820.0,
|
| 3462 |
+
"learning_rate": 0.001,
|
| 3463 |
+
"loss": 1640.4948,
|
| 3464 |
+
"step": 23472
|
| 3465 |
+
},
|
| 3466 |
+
{
|
| 3467 |
+
"epoch": 0.4813556547009946,
|
| 3468 |
+
"grad_norm": 700.0,
|
| 3469 |
+
"learning_rate": 0.001,
|
| 3470 |
+
"loss": 1593.3931,
|
| 3471 |
+
"step": 23520
|
| 3472 |
+
},
|
| 3473 |
+
{
|
| 3474 |
+
"epoch": 0.48233801317997627,
|
| 3475 |
+
"grad_norm": 824.0,
|
| 3476 |
+
"learning_rate": 0.001,
|
| 3477 |
+
"loss": 1622.2378,
|
| 3478 |
+
"step": 23568
|
| 3479 |
+
},
|
| 3480 |
+
{
|
| 3481 |
+
"epoch": 0.48332037165895786,
|
| 3482 |
+
"grad_norm": 936.0,
|
| 3483 |
+
"learning_rate": 0.001,
|
| 3484 |
+
"loss": 1612.6034,
|
| 3485 |
+
"step": 23616
|
| 3486 |
+
},
|
| 3487 |
+
{
|
| 3488 |
+
"epoch": 0.4843027301379395,
|
| 3489 |
+
"grad_norm": 732.0,
|
| 3490 |
+
"learning_rate": 0.001,
|
| 3491 |
+
"loss": 1624.4165,
|
| 3492 |
+
"step": 23664
|
| 3493 |
+
},
|
| 3494 |
+
{
|
| 3495 |
+
"epoch": 0.4852850886169211,
|
| 3496 |
+
"grad_norm": 820.0,
|
| 3497 |
+
"learning_rate": 0.001,
|
| 3498 |
+
"loss": 1634.2424,
|
| 3499 |
+
"step": 23712
|
| 3500 |
+
},
|
| 3501 |
+
{
|
| 3502 |
+
"epoch": 0.48626744709590275,
|
| 3503 |
+
"grad_norm": 896.0,
|
| 3504 |
+
"learning_rate": 0.001,
|
| 3505 |
+
"loss": 1616.617,
|
| 3506 |
+
"step": 23760
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 0.48724980557488434,
|
| 3510 |
+
"grad_norm": 732.0,
|
| 3511 |
+
"learning_rate": 0.001,
|
| 3512 |
+
"loss": 1629.8065,
|
| 3513 |
+
"step": 23808
|
| 3514 |
+
},
|
| 3515 |
+
{
|
| 3516 |
+
"epoch": 0.488232164053866,
|
| 3517 |
+
"grad_norm": 876.0,
|
| 3518 |
+
"learning_rate": 0.001,
|
| 3519 |
+
"loss": 1611.0832,
|
| 3520 |
+
"step": 23856
|
| 3521 |
+
},
|
| 3522 |
+
{
|
| 3523 |
+
"epoch": 0.4892145225328476,
|
| 3524 |
+
"grad_norm": 1004.0,
|
| 3525 |
+
"learning_rate": 0.001,
|
| 3526 |
+
"loss": 1596.9705,
|
| 3527 |
+
"step": 23904
|
| 3528 |
+
},
|
| 3529 |
+
{
|
| 3530 |
+
"epoch": 0.49019688101182923,
|
| 3531 |
+
"grad_norm": 812.0,
|
| 3532 |
+
"learning_rate": 0.001,
|
| 3533 |
+
"loss": 1612.6437,
|
| 3534 |
+
"step": 23952
|
| 3535 |
+
},
|
| 3536 |
+
{
|
| 3537 |
+
"epoch": 0.4911792394908109,
|
| 3538 |
+
"grad_norm": 764.0,
|
| 3539 |
+
"learning_rate": 0.001,
|
| 3540 |
+
"loss": 1612.0643,
|
| 3541 |
+
"step": 24000
|
| 3542 |
+
},
|
| 3543 |
+
{
|
| 3544 |
+
"epoch": 0.4921615979697925,
|
| 3545 |
+
"grad_norm": 944.0,
|
| 3546 |
+
"learning_rate": 0.001,
|
| 3547 |
+
"loss": 1620.1268,
|
| 3548 |
+
"step": 24048
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 0.4931439564487741,
|
| 3552 |
+
"grad_norm": 920.0,
|
| 3553 |
+
"learning_rate": 0.001,
|
| 3554 |
+
"loss": 1619.8875,
|
| 3555 |
+
"step": 24096
|
| 3556 |
+
},
|
| 3557 |
+
{
|
| 3558 |
+
"epoch": 0.4941263149277557,
|
| 3559 |
+
"grad_norm": 808.0,
|
| 3560 |
+
"learning_rate": 0.001,
|
| 3561 |
+
"loss": 1608.6463,
|
| 3562 |
+
"step": 24144
|
| 3563 |
+
},
|
| 3564 |
+
{
|
| 3565 |
+
"epoch": 0.49510867340673737,
|
| 3566 |
+
"grad_norm": 784.0,
|
| 3567 |
+
"learning_rate": 0.001,
|
| 3568 |
+
"loss": 1609.1462,
|
| 3569 |
+
"step": 24192
|
| 3570 |
+
},
|
| 3571 |
+
{
|
| 3572 |
+
"epoch": 0.49609103188571896,
|
| 3573 |
+
"grad_norm": 796.0,
|
| 3574 |
+
"learning_rate": 0.001,
|
| 3575 |
+
"loss": 1610.4935,
|
| 3576 |
+
"step": 24240
|
| 3577 |
+
},
|
| 3578 |
+
{
|
| 3579 |
+
"epoch": 0.4970733903647006,
|
| 3580 |
+
"grad_norm": 896.0,
|
| 3581 |
+
"learning_rate": 0.001,
|
| 3582 |
+
"loss": 1622.8371,
|
| 3583 |
+
"step": 24288
|
| 3584 |
+
},
|
| 3585 |
+
{
|
| 3586 |
+
"epoch": 0.4980557488436822,
|
| 3587 |
+
"grad_norm": 768.0,
|
| 3588 |
+
"learning_rate": 0.001,
|
| 3589 |
+
"loss": 1617.0732,
|
| 3590 |
+
"step": 24336
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 0.49903810732266385,
|
| 3594 |
+
"grad_norm": 920.0,
|
| 3595 |
+
"learning_rate": 0.001,
|
| 3596 |
+
"loss": 1615.2142,
|
| 3597 |
+
"step": 24384
|
| 3598 |
+
},
|
| 3599 |
+
{
|
| 3600 |
+
"epoch": 0.49997953419835456,
|
| 3601 |
+
"eval_loss": 1546.7662353515625,
|
| 3602 |
+
"eval_runtime": 9.0072,
|
| 3603 |
+
"eval_samples_per_second": 111.022,
|
| 3604 |
+
"eval_steps_per_second": 1.443,
|
| 3605 |
+
"step": 24430
|
| 3606 |
+
}
|
| 3607 |
+
],
|
| 3608 |
+
"logging_steps": 48,
|
| 3609 |
+
"max_steps": 48862,
|
| 3610 |
+
"num_input_tokens_seen": 0,
|
| 3611 |
+
"num_train_epochs": 9223372036854775807,
|
| 3612 |
+
"save_steps": 4886,
|
| 3613 |
+
"stateful_callbacks": {
|
| 3614 |
+
"TrainerControl": {
|
| 3615 |
+
"args": {
|
| 3616 |
+
"should_epoch_stop": false,
|
| 3617 |
+
"should_evaluate": false,
|
| 3618 |
+
"should_log": false,
|
| 3619 |
+
"should_save": true,
|
| 3620 |
+
"should_training_stop": false
|
| 3621 |
+
},
|
| 3622 |
+
"attributes": {}
|
| 3623 |
+
}
|
| 3624 |
+
},
|
| 3625 |
+
"total_flos": 1.7859053283033743e+18,
|
| 3626 |
+
"train_batch_size": 8,
|
| 3627 |
+
"trial_name": null,
|
| 3628 |
+
"trial_params": null
|
| 3629 |
+
}
|
checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cae776ea460dabd2fb943e5a559b6cb0a1095afad448097111225a1183e87c64
|
| 3 |
+
size 5496
|
checkpoint/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|