hiiamsid commited on
Commit
09d48b4
1 Parent(s): 1a37e26

Model save

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: mistral_8k_epoch_4_classification
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # mistral_8k_epoch_4_classification
15
+
16
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0705
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-07
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 1
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - num_devices: 3
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 12
45
+ - total_eval_batch_size: 3
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 4
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:---------------:|
55
+ | 0.0427 | 1.0 | 594 | 0.0546 |
56
+ | 0.0473 | 2.0 | 1188 | 0.0474 |
57
+ | 0.0211 | 3.0 | 1782 | 0.0500 |
58
+ | 0.0072 | 4.0 | 2376 | 0.0705 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.36.0
64
+ - Pytorch 2.0.1+cu118
65
+ - Datasets 2.16.1
66
+ - Tokenizers 0.15.1
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_loss": 0.07049984484910965,
4
+ "eval_runtime": 53.5339,
5
+ "eval_samples": 376,
6
+ "eval_samples_per_second": 7.024,
7
+ "eval_steps_per_second": 2.354,
8
+ "train_loss": 0.10876847104865568,
9
+ "train_runtime": 16521.7456,
10
+ "train_samples": 7130,
11
+ "train_samples_per_second": 1.726,
12
+ "train_steps_per_second": 0.144
13
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.36.0",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_loss": 0.07049984484910965,
4
+ "eval_runtime": 53.5339,
5
+ "eval_samples": 376,
6
+ "eval_samples_per_second": 7.024,
7
+ "eval_steps_per_second": 2.354
8
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.0"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a6f32d9c09df470b0447e3cb8ecc0484ea911485121c776f0c02c6c059b143c
3
+ size 4943162336
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c32ea1488de14f676e23ea9b97dd552f69607af3c8daf47a9fa2ebfc6c2bae02
3
+ size 4999819336
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c41ecff5f6716eee428ffb55316db07926ed09c2f3553bd1878ed5d831bca5ba
3
+ size 4540516344
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### Input:\n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ '### Instruction:' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '\n###Response :\n' + message['content'] }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '###Response :\n' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 8192,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.10876847104865568,
4
+ "train_runtime": 16521.7456,
5
+ "train_samples": 7130,
6
+ "train_samples_per_second": 1.726,
7
+ "train_steps_per_second": 0.144
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1010 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.9983172065628945,
5
+ "eval_steps": 500,
6
+ "global_step": 2376,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 3.151260504201681e-08,
14
+ "loss": 4.7778,
15
+ "step": 15
16
+ },
17
+ {
18
+ "epoch": 0.05,
19
+ "learning_rate": 6.302521008403361e-08,
20
+ "loss": 4.1934,
21
+ "step": 30
22
+ },
23
+ {
24
+ "epoch": 0.08,
25
+ "learning_rate": 9.453781512605041e-08,
26
+ "loss": 2.2385,
27
+ "step": 45
28
+ },
29
+ {
30
+ "epoch": 0.1,
31
+ "learning_rate": 1.2605042016806723e-07,
32
+ "loss": 0.6474,
33
+ "step": 60
34
+ },
35
+ {
36
+ "epoch": 0.13,
37
+ "learning_rate": 1.5756302521008403e-07,
38
+ "loss": 0.2815,
39
+ "step": 75
40
+ },
41
+ {
42
+ "epoch": 0.15,
43
+ "learning_rate": 1.8907563025210083e-07,
44
+ "loss": 0.1927,
45
+ "step": 90
46
+ },
47
+ {
48
+ "epoch": 0.18,
49
+ "learning_rate": 2.2058823529411763e-07,
50
+ "loss": 0.1627,
51
+ "step": 105
52
+ },
53
+ {
54
+ "epoch": 0.2,
55
+ "learning_rate": 2.5210084033613445e-07,
56
+ "loss": 0.1106,
57
+ "step": 120
58
+ },
59
+ {
60
+ "epoch": 0.23,
61
+ "learning_rate": 2.8361344537815123e-07,
62
+ "loss": 0.0844,
63
+ "step": 135
64
+ },
65
+ {
66
+ "epoch": 0.25,
67
+ "learning_rate": 3.1512605042016805e-07,
68
+ "loss": 0.075,
69
+ "step": 150
70
+ },
71
+ {
72
+ "epoch": 0.28,
73
+ "learning_rate": 3.4663865546218483e-07,
74
+ "loss": 0.07,
75
+ "step": 165
76
+ },
77
+ {
78
+ "epoch": 0.3,
79
+ "learning_rate": 3.7815126050420166e-07,
80
+ "loss": 0.0633,
81
+ "step": 180
82
+ },
83
+ {
84
+ "epoch": 0.33,
85
+ "learning_rate": 4.096638655462185e-07,
86
+ "loss": 0.0693,
87
+ "step": 195
88
+ },
89
+ {
90
+ "epoch": 0.35,
91
+ "learning_rate": 4.4117647058823526e-07,
92
+ "loss": 0.0682,
93
+ "step": 210
94
+ },
95
+ {
96
+ "epoch": 0.38,
97
+ "learning_rate": 4.726890756302521e-07,
98
+ "loss": 0.0639,
99
+ "step": 225
100
+ },
101
+ {
102
+ "epoch": 0.4,
103
+ "learning_rate": 4.99998920421976e-07,
104
+ "loss": 0.0626,
105
+ "step": 240
106
+ },
107
+ {
108
+ "epoch": 0.43,
109
+ "learning_rate": 4.999220044875031e-07,
110
+ "loss": 0.0599,
111
+ "step": 255
112
+ },
113
+ {
114
+ "epoch": 0.45,
115
+ "learning_rate": 4.997236787442598e-07,
116
+ "loss": 0.0616,
117
+ "step": 270
118
+ },
119
+ {
120
+ "epoch": 0.48,
121
+ "learning_rate": 4.99404039537066e-07,
122
+ "loss": 0.0562,
123
+ "step": 285
124
+ },
125
+ {
126
+ "epoch": 0.5,
127
+ "learning_rate": 4.989632421437059e-07,
128
+ "loss": 0.0554,
129
+ "step": 300
130
+ },
131
+ {
132
+ "epoch": 0.53,
133
+ "learning_rate": 4.984015006994947e-07,
134
+ "loss": 0.0514,
135
+ "step": 315
136
+ },
137
+ {
138
+ "epoch": 0.56,
139
+ "learning_rate": 4.977190880932541e-07,
140
+ "loss": 0.0561,
141
+ "step": 330
142
+ },
143
+ {
144
+ "epoch": 0.58,
145
+ "learning_rate": 4.969163358347454e-07,
146
+ "loss": 0.0552,
147
+ "step": 345
148
+ },
149
+ {
150
+ "epoch": 0.61,
151
+ "learning_rate": 4.959936338936248e-07,
152
+ "loss": 0.0522,
153
+ "step": 360
154
+ },
155
+ {
156
+ "epoch": 0.63,
157
+ "learning_rate": 4.949514305100001e-07,
158
+ "loss": 0.0486,
159
+ "step": 375
160
+ },
161
+ {
162
+ "epoch": 0.66,
163
+ "learning_rate": 4.937902319766796e-07,
164
+ "loss": 0.06,
165
+ "step": 390
166
+ },
167
+ {
168
+ "epoch": 0.68,
169
+ "learning_rate": 4.925106023932197e-07,
170
+ "loss": 0.055,
171
+ "step": 405
172
+ },
173
+ {
174
+ "epoch": 0.71,
175
+ "learning_rate": 4.911131633918905e-07,
176
+ "loss": 0.0469,
177
+ "step": 420
178
+ },
179
+ {
180
+ "epoch": 0.73,
181
+ "learning_rate": 4.895985938356931e-07,
182
+ "loss": 0.0522,
183
+ "step": 435
184
+ },
185
+ {
186
+ "epoch": 0.76,
187
+ "learning_rate": 4.879676294885731e-07,
188
+ "loss": 0.0521,
189
+ "step": 450
190
+ },
191
+ {
192
+ "epoch": 0.78,
193
+ "learning_rate": 4.862210626579943e-07,
194
+ "loss": 0.0452,
195
+ "step": 465
196
+ },
197
+ {
198
+ "epoch": 0.81,
199
+ "learning_rate": 4.843597418100424e-07,
200
+ "loss": 0.0458,
201
+ "step": 480
202
+ },
203
+ {
204
+ "epoch": 0.83,
205
+ "learning_rate": 4.823845711572484e-07,
206
+ "loss": 0.05,
207
+ "step": 495
208
+ },
209
+ {
210
+ "epoch": 0.86,
211
+ "learning_rate": 4.802965102193303e-07,
212
+ "loss": 0.0437,
213
+ "step": 510
214
+ },
215
+ {
216
+ "epoch": 0.88,
217
+ "learning_rate": 4.78096573357067e-07,
218
+ "loss": 0.0509,
219
+ "step": 525
220
+ },
221
+ {
222
+ "epoch": 0.91,
223
+ "learning_rate": 4.757858292795316e-07,
224
+ "loss": 0.041,
225
+ "step": 540
226
+ },
227
+ {
228
+ "epoch": 0.93,
229
+ "learning_rate": 4.7336540052492215e-07,
230
+ "loss": 0.0416,
231
+ "step": 555
232
+ },
233
+ {
234
+ "epoch": 0.96,
235
+ "learning_rate": 4.7083646291524306e-07,
236
+ "loss": 0.0381,
237
+ "step": 570
238
+ },
239
+ {
240
+ "epoch": 0.98,
241
+ "learning_rate": 4.6820024498510123e-07,
242
+ "loss": 0.0427,
243
+ "step": 585
244
+ },
245
+ {
246
+ "epoch": 1.0,
247
+ "eval_loss": 0.05463867634534836,
248
+ "eval_runtime": 53.6645,
249
+ "eval_samples_per_second": 7.007,
250
+ "eval_steps_per_second": 2.348,
251
+ "step": 594
252
+ },
253
+ {
254
+ "epoch": 1.01,
255
+ "learning_rate": 4.6545802738489593e-07,
256
+ "loss": 0.0407,
257
+ "step": 600
258
+ },
259
+ {
260
+ "epoch": 1.03,
261
+ "learning_rate": 4.6261114225868974e-07,
262
+ "loss": 0.0275,
263
+ "step": 615
264
+ },
265
+ {
266
+ "epoch": 1.06,
267
+ "learning_rate": 4.5966097259706617e-07,
268
+ "loss": 0.0489,
269
+ "step": 630
270
+ },
271
+ {
272
+ "epoch": 1.09,
273
+ "learning_rate": 4.5660895156528477e-07,
274
+ "loss": 0.0511,
275
+ "step": 645
276
+ },
277
+ {
278
+ "epoch": 1.11,
279
+ "learning_rate": 4.5345656180706316e-07,
280
+ "loss": 0.0453,
281
+ "step": 660
282
+ },
283
+ {
284
+ "epoch": 1.14,
285
+ "learning_rate": 4.50205334724322e-07,
286
+ "loss": 0.0421,
287
+ "step": 675
288
+ },
289
+ {
290
+ "epoch": 1.16,
291
+ "learning_rate": 4.4685684973324447e-07,
292
+ "loss": 0.0396,
293
+ "step": 690
294
+ },
295
+ {
296
+ "epoch": 1.19,
297
+ "learning_rate": 4.434127334970099e-07,
298
+ "loss": 0.0386,
299
+ "step": 705
300
+ },
301
+ {
302
+ "epoch": 1.21,
303
+ "learning_rate": 4.398746591355763e-07,
304
+ "loss": 0.0487,
305
+ "step": 720
306
+ },
307
+ {
308
+ "epoch": 1.24,
309
+ "learning_rate": 4.3624434541289365e-07,
310
+ "loss": 0.0394,
311
+ "step": 735
312
+ },
313
+ {
314
+ "epoch": 1.26,
315
+ "learning_rate": 4.3252355590194444e-07,
316
+ "loss": 0.041,
317
+ "step": 750
318
+ },
319
+ {
320
+ "epoch": 1.29,
321
+ "learning_rate": 4.287140981280162e-07,
322
+ "loss": 0.0414,
323
+ "step": 765
324
+ },
325
+ {
326
+ "epoch": 1.31,
327
+ "learning_rate": 4.248178226906221e-07,
328
+ "loss": 0.0398,
329
+ "step": 780
330
+ },
331
+ {
332
+ "epoch": 1.34,
333
+ "learning_rate": 4.2083662236449694e-07,
334
+ "loss": 0.0391,
335
+ "step": 795
336
+ },
337
+ {
338
+ "epoch": 1.36,
339
+ "learning_rate": 4.167724311801047e-07,
340
+ "loss": 0.034,
341
+ "step": 810
342
+ },
343
+ {
344
+ "epoch": 1.39,
345
+ "learning_rate": 4.12627223484104e-07,
346
+ "loss": 0.0466,
347
+ "step": 825
348
+ },
349
+ {
350
+ "epoch": 1.41,
351
+ "learning_rate": 4.0840301298022904e-07,
352
+ "loss": 0.0405,
353
+ "step": 840
354
+ },
355
+ {
356
+ "epoch": 1.44,
357
+ "learning_rate": 4.0410185175105074e-07,
358
+ "loss": 0.0408,
359
+ "step": 855
360
+ },
361
+ {
362
+ "epoch": 1.46,
363
+ "learning_rate": 3.9972582926109373e-07,
364
+ "loss": 0.0473,
365
+ "step": 870
366
+ },
367
+ {
368
+ "epoch": 1.49,
369
+ "learning_rate": 3.95277071341794e-07,
370
+ "loss": 0.0414,
371
+ "step": 885
372
+ },
373
+ {
374
+ "epoch": 1.51,
375
+ "learning_rate": 3.907577391587894e-07,
376
+ "loss": 0.0417,
377
+ "step": 900
378
+ },
379
+ {
380
+ "epoch": 1.54,
381
+ "learning_rate": 3.861700281620455e-07,
382
+ "loss": 0.0478,
383
+ "step": 915
384
+ },
385
+ {
386
+ "epoch": 1.56,
387
+ "learning_rate": 3.8151616701932575e-07,
388
+ "loss": 0.0356,
389
+ "step": 930
390
+ },
391
+ {
392
+ "epoch": 1.59,
393
+ "learning_rate": 3.7679841653352563e-07,
394
+ "loss": 0.0346,
395
+ "step": 945
396
+ },
397
+ {
398
+ "epoch": 1.62,
399
+ "learning_rate": 3.7201906854439514e-07,
400
+ "loss": 0.0434,
401
+ "step": 960
402
+ },
403
+ {
404
+ "epoch": 1.64,
405
+ "learning_rate": 3.671804448151845e-07,
406
+ "loss": 0.0511,
407
+ "step": 975
408
+ },
409
+ {
410
+ "epoch": 1.67,
411
+ "learning_rate": 3.622848959047525e-07,
412
+ "loss": 0.0413,
413
+ "step": 990
414
+ },
415
+ {
416
+ "epoch": 1.69,
417
+ "learning_rate": 3.57334800025687e-07,
418
+ "loss": 0.0355,
419
+ "step": 1005
420
+ },
421
+ {
422
+ "epoch": 1.72,
423
+ "learning_rate": 3.523325618889909e-07,
424
+ "loss": 0.033,
425
+ "step": 1020
426
+ },
427
+ {
428
+ "epoch": 1.74,
429
+ "learning_rate": 3.4728061153589595e-07,
430
+ "loss": 0.0316,
431
+ "step": 1035
432
+ },
433
+ {
434
+ "epoch": 1.77,
435
+ "learning_rate": 3.4218140315737075e-07,
436
+ "loss": 0.0415,
437
+ "step": 1050
438
+ },
439
+ {
440
+ "epoch": 1.79,
441
+ "learning_rate": 3.3703741390189765e-07,
442
+ "loss": 0.0401,
443
+ "step": 1065
444
+ },
445
+ {
446
+ "epoch": 1.82,
447
+ "learning_rate": 3.318511426720967e-07,
448
+ "loss": 0.0333,
449
+ "step": 1080
450
+ },
451
+ {
452
+ "epoch": 1.84,
453
+ "learning_rate": 3.2662510891078175e-07,
454
+ "loss": 0.0347,
455
+ "step": 1095
456
+ },
457
+ {
458
+ "epoch": 1.87,
459
+ "learning_rate": 3.2136185137703856e-07,
460
+ "loss": 0.0389,
461
+ "step": 1110
462
+ },
463
+ {
464
+ "epoch": 1.89,
465
+ "learning_rate": 3.160639269129186e-07,
466
+ "loss": 0.0406,
467
+ "step": 1125
468
+ },
469
+ {
470
+ "epoch": 1.92,
471
+ "learning_rate": 3.10733909201349e-07,
472
+ "loss": 0.0354,
473
+ "step": 1140
474
+ },
475
+ {
476
+ "epoch": 1.94,
477
+ "learning_rate": 3.053743875158611e-07,
478
+ "loss": 0.0334,
479
+ "step": 1155
480
+ },
481
+ {
482
+ "epoch": 1.97,
483
+ "learning_rate": 2.9998796546274496e-07,
484
+ "loss": 0.0337,
485
+ "step": 1170
486
+ },
487
+ {
488
+ "epoch": 1.99,
489
+ "learning_rate": 2.9457725971624173e-07,
490
+ "loss": 0.0473,
491
+ "step": 1185
492
+ },
493
+ {
494
+ "epoch": 2.0,
495
+ "eval_loss": 0.0474083386361599,
496
+ "eval_runtime": 53.4669,
497
+ "eval_samples_per_second": 7.032,
498
+ "eval_steps_per_second": 2.357,
499
+ "step": 1188
500
+ },
501
+ {
502
+ "epoch": 2.02,
503
+ "learning_rate": 2.891448987473873e-07,
504
+ "loss": 0.0316,
505
+ "step": 1200
506
+ },
507
+ {
508
+ "epoch": 2.04,
509
+ "learning_rate": 2.8369352154712493e-07,
510
+ "loss": 0.0316,
511
+ "step": 1215
512
+ },
513
+ {
514
+ "epoch": 2.07,
515
+ "learning_rate": 2.782257763443082e-07,
516
+ "loss": 0.0194,
517
+ "step": 1230
518
+ },
519
+ {
520
+ "epoch": 2.1,
521
+ "learning_rate": 2.7274431931921563e-07,
522
+ "loss": 0.0172,
523
+ "step": 1245
524
+ },
525
+ {
526
+ "epoch": 2.12,
527
+ "learning_rate": 2.6725181331320274e-07,
528
+ "loss": 0.0236,
529
+ "step": 1260
530
+ },
531
+ {
532
+ "epoch": 2.15,
533
+ "learning_rate": 2.617509265351181e-07,
534
+ "loss": 0.0281,
535
+ "step": 1275
536
+ },
537
+ {
538
+ "epoch": 2.17,
539
+ "learning_rate": 2.5624433126511254e-07,
540
+ "loss": 0.0228,
541
+ "step": 1290
542
+ },
543
+ {
544
+ "epoch": 2.2,
545
+ "learning_rate": 2.507347025564693e-07,
546
+ "loss": 0.0296,
547
+ "step": 1305
548
+ },
549
+ {
550
+ "epoch": 2.22,
551
+ "learning_rate": 2.452247169360885e-07,
552
+ "loss": 0.0332,
553
+ "step": 1320
554
+ },
555
+ {
556
+ "epoch": 2.25,
557
+ "learning_rate": 2.3971705110425454e-07,
558
+ "loss": 0.0218,
559
+ "step": 1335
560
+ },
561
+ {
562
+ "epoch": 2.27,
563
+ "learning_rate": 2.3421438063431996e-07,
564
+ "loss": 0.0255,
565
+ "step": 1350
566
+ },
567
+ {
568
+ "epoch": 2.3,
569
+ "learning_rate": 2.2871937867293638e-07,
570
+ "loss": 0.0272,
571
+ "step": 1365
572
+ },
573
+ {
574
+ "epoch": 2.32,
575
+ "learning_rate": 2.2323471464146477e-07,
576
+ "loss": 0.0253,
577
+ "step": 1380
578
+ },
579
+ {
580
+ "epoch": 2.35,
581
+ "learning_rate": 2.1776305293919473e-07,
582
+ "loss": 0.0319,
583
+ "step": 1395
584
+ },
585
+ {
586
+ "epoch": 2.37,
587
+ "learning_rate": 2.1230705164900408e-07,
588
+ "loss": 0.0279,
589
+ "step": 1410
590
+ },
591
+ {
592
+ "epoch": 2.4,
593
+ "learning_rate": 2.0686936124608682e-07,
594
+ "loss": 0.0243,
595
+ "step": 1425
596
+ },
597
+ {
598
+ "epoch": 2.42,
599
+ "learning_rate": 2.0145262331037628e-07,
600
+ "loss": 0.0266,
601
+ "step": 1440
602
+ },
603
+ {
604
+ "epoch": 2.45,
605
+ "learning_rate": 1.960594692432901e-07,
606
+ "loss": 0.0277,
607
+ "step": 1455
608
+ },
609
+ {
610
+ "epoch": 2.47,
611
+ "learning_rate": 1.9069251898941995e-07,
612
+ "loss": 0.0265,
613
+ "step": 1470
614
+ },
615
+ {
616
+ "epoch": 2.5,
617
+ "learning_rate": 1.8535437976378608e-07,
618
+ "loss": 0.0239,
619
+ "step": 1485
620
+ },
621
+ {
622
+ "epoch": 2.52,
623
+ "learning_rate": 1.8004764478527641e-07,
624
+ "loss": 0.0182,
625
+ "step": 1500
626
+ },
627
+ {
628
+ "epoch": 2.55,
629
+ "learning_rate": 1.7477489201688505e-07,
630
+ "loss": 0.0235,
631
+ "step": 1515
632
+ },
633
+ {
634
+ "epoch": 2.57,
635
+ "learning_rate": 1.6953868291336103e-07,
636
+ "loss": 0.0241,
637
+ "step": 1530
638
+ },
639
+ {
640
+ "epoch": 2.6,
641
+ "learning_rate": 1.6434156117687747e-07,
642
+ "loss": 0.0248,
643
+ "step": 1545
644
+ },
645
+ {
646
+ "epoch": 2.63,
647
+ "learning_rate": 1.591860515213247e-07,
648
+ "loss": 0.0257,
649
+ "step": 1560
650
+ },
651
+ {
652
+ "epoch": 2.65,
653
+ "learning_rate": 1.540746584458269e-07,
654
+ "loss": 0.0296,
655
+ "step": 1575
656
+ },
657
+ {
658
+ "epoch": 2.68,
659
+ "learning_rate": 1.4900986501808e-07,
660
+ "loss": 0.024,
661
+ "step": 1590
662
+ },
663
+ {
664
+ "epoch": 2.7,
665
+ "learning_rate": 1.4399413166810027e-07,
666
+ "loss": 0.0289,
667
+ "step": 1605
668
+ },
669
+ {
670
+ "epoch": 2.73,
671
+ "learning_rate": 1.3902989499296953e-07,
672
+ "loss": 0.0245,
673
+ "step": 1620
674
+ },
675
+ {
676
+ "epoch": 2.75,
677
+ "learning_rate": 1.3411956657315935e-07,
678
+ "loss": 0.0219,
679
+ "step": 1635
680
+ },
681
+ {
682
+ "epoch": 2.78,
683
+ "learning_rate": 1.2926553180100714e-07,
684
+ "loss": 0.0213,
685
+ "step": 1650
686
+ },
687
+ {
688
+ "epoch": 2.8,
689
+ "learning_rate": 1.244701487219146e-07,
690
+ "loss": 0.0179,
691
+ "step": 1665
692
+ },
693
+ {
694
+ "epoch": 2.83,
695
+ "learning_rate": 1.1973574688883075e-07,
696
+ "loss": 0.0239,
697
+ "step": 1680
698
+ },
699
+ {
700
+ "epoch": 2.85,
701
+ "learning_rate": 1.1506462623057698e-07,
702
+ "loss": 0.0227,
703
+ "step": 1695
704
+ },
705
+ {
706
+ "epoch": 2.88,
707
+ "learning_rate": 1.1045905593456254e-07,
708
+ "loss": 0.0228,
709
+ "step": 1710
710
+ },
711
+ {
712
+ "epoch": 2.9,
713
+ "learning_rate": 1.0592127334443398e-07,
714
+ "loss": 0.0212,
715
+ "step": 1725
716
+ },
717
+ {
718
+ "epoch": 2.93,
719
+ "learning_rate": 1.0145348287319471e-07,
720
+ "loss": 0.019,
721
+ "step": 1740
722
+ },
723
+ {
724
+ "epoch": 2.95,
725
+ "learning_rate": 9.705785493232125e-08,
726
+ "loss": 0.0243,
727
+ "step": 1755
728
+ },
729
+ {
730
+ "epoch": 2.98,
731
+ "learning_rate": 9.27365248773969e-08,
732
+ "loss": 0.0211,
733
+ "step": 1770
734
+ },
735
+ {
736
+ "epoch": 3.0,
737
+ "eval_loss": 0.05001327767968178,
738
+ "eval_runtime": 53.5686,
739
+ "eval_samples_per_second": 7.019,
740
+ "eval_steps_per_second": 2.352,
741
+ "step": 1782
742
+ },
743
+ {
744
+ "epoch": 3.0,
745
+ "learning_rate": 8.849159197077633e-08,
746
+ "loss": 0.0222,
747
+ "step": 1785
748
+ },
749
+ {
750
+ "epoch": 3.03,
751
+ "learning_rate": 8.432511836178294e-08,
752
+ "loss": 0.0098,
753
+ "step": 1800
754
+ },
755
+ {
756
+ "epoch": 3.05,
757
+ "learning_rate": 8.02391280849355e-08,
758
+ "loss": 0.0086,
759
+ "step": 1815
760
+ },
761
+ {
762
+ "epoch": 3.08,
763
+ "learning_rate": 7.623560607669117e-08,
764
+ "loss": 0.0112,
765
+ "step": 1830
766
+ },
767
+ {
768
+ "epoch": 3.1,
769
+ "learning_rate": 7.231649721118163e-08,
770
+ "loss": 0.0106,
771
+ "step": 1845
772
+ },
773
+ {
774
+ "epoch": 3.13,
775
+ "learning_rate": 6.848370535541068e-08,
776
+ "loss": 0.0125,
777
+ "step": 1860
778
+ },
779
+ {
780
+ "epoch": 3.16,
781
+ "learning_rate": 6.473909244437376e-08,
782
+ "loss": 0.008,
783
+ "step": 1875
784
+ },
785
+ {
786
+ "epoch": 3.18,
787
+ "learning_rate": 6.108447757654678e-08,
788
+ "loss": 0.0102,
789
+ "step": 1890
790
+ },
791
+ {
792
+ "epoch": 3.21,
793
+ "learning_rate": 5.752163613018471e-08,
794
+ "loss": 0.0074,
795
+ "step": 1905
796
+ },
797
+ {
798
+ "epoch": 3.23,
799
+ "learning_rate": 5.405229890085949e-08,
800
+ "loss": 0.006,
801
+ "step": 1920
802
+ },
803
+ {
804
+ "epoch": 3.26,
805
+ "learning_rate": 5.0678151260655335e-08,
806
+ "loss": 0.0084,
807
+ "step": 1935
808
+ },
809
+ {
810
+ "epoch": 3.28,
811
+ "learning_rate": 4.740083233943021e-08,
812
+ "loss": 0.0099,
813
+ "step": 1950
814
+ },
815
+ {
816
+ "epoch": 3.31,
817
+ "learning_rate": 4.4221934228542144e-08,
818
+ "loss": 0.0051,
819
+ "step": 1965
820
+ },
821
+ {
822
+ "epoch": 3.33,
823
+ "learning_rate": 4.114300120742564e-08,
824
+ "loss": 0.0124,
825
+ "step": 1980
826
+ },
827
+ {
828
+ "epoch": 3.36,
829
+ "learning_rate": 3.8165528993394756e-08,
830
+ "loss": 0.0032,
831
+ "step": 1995
832
+ },
833
+ {
834
+ "epoch": 3.38,
835
+ "learning_rate": 3.5290964015037836e-08,
836
+ "loss": 0.0091,
837
+ "step": 2010
838
+ },
839
+ {
840
+ "epoch": 3.41,
841
+ "learning_rate": 3.2520702709555564e-08,
842
+ "loss": 0.0044,
843
+ "step": 2025
844
+ },
845
+ {
846
+ "epoch": 3.43,
847
+ "learning_rate": 2.985609084438442e-08,
848
+ "loss": 0.0152,
849
+ "step": 2040
850
+ },
851
+ {
852
+ "epoch": 3.46,
853
+ "learning_rate": 2.729842286343581e-08,
854
+ "loss": 0.0053,
855
+ "step": 2055
856
+ },
857
+ {
858
+ "epoch": 3.48,
859
+ "learning_rate": 2.4848941258266643e-08,
860
+ "loss": 0.0053,
861
+ "step": 2070
862
+ },
863
+ {
864
+ "epoch": 3.51,
865
+ "learning_rate": 2.2508835964488465e-08,
866
+ "loss": 0.0059,
867
+ "step": 2085
868
+ },
869
+ {
870
+ "epoch": 3.53,
871
+ "learning_rate": 2.0279243783707904e-08,
872
+ "loss": 0.0046,
873
+ "step": 2100
874
+ },
875
+ {
876
+ "epoch": 3.56,
877
+ "learning_rate": 1.8161247831278785e-08,
878
+ "loss": 0.0063,
879
+ "step": 2115
880
+ },
881
+ {
882
+ "epoch": 3.58,
883
+ "learning_rate": 1.6155877010134488e-08,
884
+ "loss": 0.0067,
885
+ "step": 2130
886
+ },
887
+ {
888
+ "epoch": 3.61,
889
+ "learning_rate": 1.426410551095672e-08,
890
+ "loss": 0.003,
891
+ "step": 2145
892
+ },
893
+ {
894
+ "epoch": 3.63,
895
+ "learning_rate": 1.2486852338922438e-08,
896
+ "loss": 0.011,
897
+ "step": 2160
898
+ },
899
+ {
900
+ "epoch": 3.66,
901
+ "learning_rate": 1.0824980867259526e-08,
902
+ "loss": 0.0068,
903
+ "step": 2175
904
+ },
905
+ {
906
+ "epoch": 3.69,
907
+ "learning_rate": 9.279298417828263e-09,
908
+ "loss": 0.0113,
909
+ "step": 2190
910
+ },
911
+ {
912
+ "epoch": 3.71,
913
+ "learning_rate": 7.85055586893163e-09,
914
+ "loss": 0.0069,
915
+ "step": 2205
916
+ },
917
+ {
918
+ "epoch": 3.74,
919
+ "learning_rate": 6.539447290545563e-09,
920
+ "loss": 0.0105,
921
+ "step": 2220
922
+ },
923
+ {
924
+ "epoch": 3.76,
925
+ "learning_rate": 5.346609607146141e-09,
926
+ "loss": 0.0093,
927
+ "step": 2235
928
+ },
929
+ {
930
+ "epoch": 3.79,
931
+ "learning_rate": 4.272622288297695e-09,
932
+ "loss": 0.004,
933
+ "step": 2250
934
+ },
935
+ {
936
+ "epoch": 3.81,
937
+ "learning_rate": 3.3180070671515736e-09,
938
+ "loss": 0.0082,
939
+ "step": 2265
940
+ },
941
+ {
942
+ "epoch": 3.84,
943
+ "learning_rate": 2.4832276869931056e-09,
944
+ "loss": 0.0065,
945
+ "step": 2280
946
+ },
947
+ {
948
+ "epoch": 3.86,
949
+ "learning_rate": 1.7686896759595282e-09,
950
+ "loss": 0.0063,
951
+ "step": 2295
952
+ },
953
+ {
954
+ "epoch": 3.89,
955
+ "learning_rate": 1.174740150037823e-09,
956
+ "loss": 0.0123,
957
+ "step": 2310
958
+ },
959
+ {
960
+ "epoch": 3.91,
961
+ "learning_rate": 7.016676444392966e-10,
962
+ "loss": 0.0083,
963
+ "step": 2325
964
+ },
965
+ {
966
+ "epoch": 3.94,
967
+ "learning_rate": 3.497019734316209e-10,
968
+ "loss": 0.005,
969
+ "step": 2340
970
+ },
971
+ {
972
+ "epoch": 3.96,
973
+ "learning_rate": 1.1901411869724708e-10,
974
+ "loss": 0.0076,
975
+ "step": 2355
976
+ },
977
+ {
978
+ "epoch": 3.99,
979
+ "learning_rate": 9.716146272098492e-12,
980
+ "loss": 0.0072,
981
+ "step": 2370
982
+ },
983
+ {
984
+ "epoch": 4.0,
985
+ "eval_loss": 0.07049984484910965,
986
+ "eval_runtime": 53.5111,
987
+ "eval_samples_per_second": 7.027,
988
+ "eval_steps_per_second": 2.355,
989
+ "step": 2376
990
+ },
991
+ {
992
+ "epoch": 4.0,
993
+ "step": 2376,
994
+ "total_flos": 134540166758400.0,
995
+ "train_loss": 0.10876847104865568,
996
+ "train_runtime": 16521.7456,
997
+ "train_samples_per_second": 1.726,
998
+ "train_steps_per_second": 0.144
999
+ }
1000
+ ],
1001
+ "logging_steps": 15,
1002
+ "max_steps": 2376,
1003
+ "num_input_tokens_seen": 0,
1004
+ "num_train_epochs": 4,
1005
+ "save_steps": 500,
1006
+ "total_flos": 134540166758400.0,
1007
+ "train_batch_size": 1,
1008
+ "trial_name": null,
1009
+ "trial_params": null
1010
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83b106b40138d14a2163f404fe0cadc17bdf4a9fbcdee78be75da1abe7f2313f
3
+ size 5371