Training in progress, step 150, checkpoint
Browse files- last-checkpoint/README.md +1 -1
- last-checkpoint/adapter_config.json +140 -9
- last-checkpoint/adapter_model.safetensors +2 -2
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +2 -2
- last-checkpoint/special_tokens_map.json +1 -1
- last-checkpoint/tokenizer.json +2 -2
- last-checkpoint/tokenizer.model +3 -0
- last-checkpoint/tokenizer_config.json +9 -13
- last-checkpoint/trainer_state.json +54 -732
- last-checkpoint/training_args.bin +2 -2
last-checkpoint/README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/mistral-7b-v0.2-bnb-4bit
|
| 3 |
library_name: peft
|
| 4 |
---
|
| 5 |
|
last-checkpoint/adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
@@ -14,20 +14,151 @@
|
|
| 14 |
"lora_dropout": 0.3,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
-
"modules_to_save":
|
|
|
|
|
|
|
| 18 |
"peft_type": "LORA",
|
| 19 |
"r": 4,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM",
|
| 31 |
"use_dora": false,
|
| 32 |
-
"use_rslora":
|
| 33 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/mistral-7b-v0.2-bnb-4bit",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 14 |
"lora_dropout": 0.3,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": [
|
| 18 |
+
"lm_head"
|
| 19 |
+
],
|
| 20 |
"peft_type": "LORA",
|
| 21 |
"r": 4,
|
| 22 |
"rank_pattern": {},
|
| 23 |
"revision": null,
|
| 24 |
"target_modules": [
|
| 25 |
+
"model.layers.27.self_attn.v_proj",
|
| 26 |
+
"model.layers.28.mlp.down_proj",
|
| 27 |
+
"model.layers.12.self_attn.q_proj",
|
| 28 |
+
"model.layers.28.self_attn.o_proj",
|
| 29 |
+
"model.layers.9.self_attn.v_proj",
|
| 30 |
+
"model.layers.14.self_attn.q_proj",
|
| 31 |
+
"model.layers.19.self_attn.q_proj",
|
| 32 |
+
"model.layers.27.mlp.gate_proj",
|
| 33 |
+
"model.layers.17.self_attn.o_proj",
|
| 34 |
+
"model.layers.23.self_attn.o_proj",
|
| 35 |
+
"model.layers.22.self_attn.v_proj",
|
| 36 |
+
"model.layers.25.self_attn.o_proj",
|
| 37 |
+
"model.layers.0.mlp.down_proj",
|
| 38 |
+
"model.layers.20.mlp.gate_proj",
|
| 39 |
+
"model.layers.9.mlp.gate_proj",
|
| 40 |
+
"model.layers.18.self_attn.k_proj",
|
| 41 |
+
"model.layers.21.self_attn.k_proj",
|
| 42 |
+
"model.layers.17.self_attn.k_proj",
|
| 43 |
+
"model.layers.3.self_attn.q_proj",
|
| 44 |
+
"model.layers.24.self_attn.q_proj",
|
| 45 |
+
"model.layers.26.mlp.up_proj",
|
| 46 |
+
"model.layers.31.mlp.up_proj",
|
| 47 |
+
"model.layers.1.mlp.down_proj",
|
| 48 |
+
"model.layers.13.mlp.up_proj",
|
| 49 |
+
"model.layers.5.mlp.down_proj",
|
| 50 |
+
"model.layers.3.self_attn.o_proj",
|
| 51 |
+
"model.layers.29.self_attn.k_proj",
|
| 52 |
+
"model.layers.3.mlp.down_proj",
|
| 53 |
+
"model.layers.20.mlp.down_proj",
|
| 54 |
+
"model.layers.2.mlp.gate_proj",
|
| 55 |
+
"model.layers.16.self_attn.q_proj",
|
| 56 |
+
"model.layers.14.mlp.down_proj",
|
| 57 |
+
"model.layers.6.self_attn.o_proj",
|
| 58 |
+
"model.layers.26.self_attn.o_proj",
|
| 59 |
+
"model.layers.6.self_attn.k_proj",
|
| 60 |
+
"model.layers.21.mlp.down_proj",
|
| 61 |
+
"model.layers.9.mlp.down_proj",
|
| 62 |
+
"model.layers.31.self_attn.o_proj",
|
| 63 |
+
"model.layers.7.self_attn.k_proj",
|
| 64 |
+
"model.layers.12.self_attn.o_proj",
|
| 65 |
+
"model.layers.14.mlp.gate_proj",
|
| 66 |
+
"model.layers.8.mlp.down_proj",
|
| 67 |
+
"model.layers.16.self_attn.o_proj",
|
| 68 |
+
"model.layers.15.self_attn.k_proj",
|
| 69 |
+
"model.layers.21.self_attn.o_proj",
|
| 70 |
+
"model.layers.13.self_attn.v_proj",
|
| 71 |
+
"model.layers.7.mlp.down_proj",
|
| 72 |
+
"model.layers.21.self_attn.v_proj",
|
| 73 |
+
"model.layers.27.self_attn.k_proj",
|
| 74 |
+
"model.layers.18.self_attn.v_proj",
|
| 75 |
+
"model.layers.15.self_attn.q_proj",
|
| 76 |
+
"model.layers.1.self_attn.k_proj",
|
| 77 |
+
"model.layers.5.mlp.gate_proj",
|
| 78 |
+
"model.layers.2.self_attn.q_proj",
|
| 79 |
+
"model.layers.28.mlp.up_proj",
|
| 80 |
+
"model.layers.10.mlp.gate_proj",
|
| 81 |
+
"model.layers.29.mlp.up_proj",
|
| 82 |
+
"model.layers.7.self_attn.q_proj",
|
| 83 |
+
"model.layers.12.mlp.gate_proj",
|
| 84 |
+
"model.layers.20.mlp.up_proj",
|
| 85 |
+
"model.layers.4.mlp.up_proj",
|
| 86 |
+
"model.layers.23.self_attn.q_proj",
|
| 87 |
+
"model.layers.23.self_attn.v_proj",
|
| 88 |
+
"model.layers.1.self_attn.q_proj",
|
| 89 |
+
"model.layers.27.mlp.down_proj",
|
| 90 |
+
"model.layers.30.mlp.down_proj",
|
| 91 |
+
"model.layers.17.mlp.down_proj",
|
| 92 |
+
"model.layers.25.mlp.up_proj",
|
| 93 |
+
"model.layers.4.self_attn.k_proj",
|
| 94 |
+
"model.layers.2.mlp.up_proj",
|
| 95 |
+
"model.layers.6.mlp.gate_proj",
|
| 96 |
+
"model.layers.31.self_attn.v_proj",
|
| 97 |
+
"model.layers.30.self_attn.k_proj",
|
| 98 |
+
"model.layers.30.self_attn.q_proj",
|
| 99 |
+
"model.layers.30.mlp.gate_proj",
|
| 100 |
+
"model.layers.8.mlp.gate_proj",
|
| 101 |
+
"model.layers.13.mlp.down_proj",
|
| 102 |
+
"model.layers.10.self_attn.q_proj",
|
| 103 |
+
"model.layers.22.self_attn.q_proj",
|
| 104 |
+
"model.layers.15.self_attn.v_proj",
|
| 105 |
+
"model.layers.25.mlp.gate_proj",
|
| 106 |
+
"model.layers.4.self_attn.q_proj",
|
| 107 |
+
"model.embed_tokens",
|
| 108 |
+
"model.layers.14.self_attn.k_proj",
|
| 109 |
+
"model.layers.31.mlp.down_proj",
|
| 110 |
+
"model.layers.31.self_attn.q_proj",
|
| 111 |
+
"model.layers.1.mlp.up_proj",
|
| 112 |
+
"model.layers.2.mlp.down_proj",
|
| 113 |
+
"model.layers.12.mlp.up_proj",
|
| 114 |
+
"model.layers.19.mlp.up_proj",
|
| 115 |
+
"model.layers.0.self_attn.v_proj",
|
| 116 |
+
"model.layers.8.self_attn.v_proj",
|
| 117 |
+
"model.layers.5.self_attn.o_proj",
|
| 118 |
+
"model.layers.11.mlp.gate_proj",
|
| 119 |
+
"model.layers.18.mlp.up_proj",
|
| 120 |
+
"model.layers.10.self_attn.v_proj",
|
| 121 |
+
"model.layers.23.mlp.down_proj",
|
| 122 |
+
"model.layers.0.mlp.up_proj",
|
| 123 |
+
"model.layers.8.self_attn.k_proj",
|
| 124 |
+
"model.layers.13.mlp.gate_proj",
|
| 125 |
+
"model.layers.24.self_attn.k_proj",
|
| 126 |
+
"model.layers.24.mlp.down_proj",
|
| 127 |
+
"model.layers.15.mlp.up_proj",
|
| 128 |
+
"model.layers.25.self_attn.k_proj",
|
| 129 |
+
"model.layers.6.self_attn.v_proj",
|
| 130 |
+
"model.layers.29.self_attn.o_proj",
|
| 131 |
+
"model.layers.10.self_attn.o_proj",
|
| 132 |
+
"model.layers.31.mlp.gate_proj",
|
| 133 |
+
"model.layers.30.mlp.up_proj",
|
| 134 |
+
"model.layers.16.mlp.down_proj",
|
| 135 |
+
"model.layers.30.self_attn.o_proj",
|
| 136 |
+
"model.layers.7.self_attn.o_proj",
|
| 137 |
+
"model.layers.5.self_attn.k_proj",
|
| 138 |
+
"model.layers.0.self_attn.q_proj",
|
| 139 |
+
"model.layers.16.self_attn.k_proj",
|
| 140 |
+
"model.layers.19.mlp.down_proj",
|
| 141 |
+
"model.layers.17.self_attn.v_proj",
|
| 142 |
+
"model.layers.29.self_attn.v_proj",
|
| 143 |
+
"model.layers.9.self_attn.q_proj",
|
| 144 |
+
"model.layers.26.self_attn.k_proj",
|
| 145 |
+
"model.layers.11.self_attn.q_proj",
|
| 146 |
+
"model.layers.24.self_attn.v_proj",
|
| 147 |
+
"model.layers.18.mlp.down_proj",
|
| 148 |
+
"model.layers.11.self_attn.v_proj",
|
| 149 |
+
"model.layers.19.self_attn.k_proj",
|
| 150 |
+
"model.layers.26.self_attn.v_proj",
|
| 151 |
+
"model.layers.28.mlp.gate_proj",
|
| 152 |
+
"model.layers.22.self_attn.k_proj",
|
| 153 |
+
"model.layers.31.self_attn.k_proj",
|
| 154 |
+
"model.layers.3.mlp.gate_proj",
|
| 155 |
+
"model.layers.22.mlp.up_proj",
|
| 156 |
+
"model.layers.30.self_attn.v_proj",
|
| 157 |
+
"model.layers.4.mlp.down_proj",
|
| 158 |
+
"model.layers.20.self_attn.k_proj",
|
| 159 |
+
"model.layers.11.self_attn.o_proj"
|
| 160 |
],
|
| 161 |
"task_type": "CAUSAL_LM",
|
| 162 |
"use_dora": false,
|
| 163 |
+
"use_rslora": true
|
| 164 |
}
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18a0ef7164d47257fa5e03e94a378e8b160912c89dea19a8e1f7af4d4f485094
|
| 3 |
+
size 287644488
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83bab8051a975e48fe6b37fa4732978d04aa6b82c8f1f55d13ddf5d2c07b7d75
|
| 3 |
+
size 574288634
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42f2102978cbe9c56d5a8a027ea80c143b48f9e1e590c1c68cf2a3125de2e811
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fac40e05bb032b9491fbd1b7ca84c8c3e5be3358f97f841daf2ab09e4beb7c6b
|
| 3 |
+
size 1256
|
last-checkpoint/special_tokens_map.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "<
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
last-checkpoint/tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2699839c243202a04a90537576fc719283f638e90fe80feb469888275289575
|
| 3 |
+
size 3505751
|
last-checkpoint/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
last-checkpoint/tokenizer_config.json
CHANGED
|
@@ -1,5 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "<unk>",
|
|
@@ -24,25 +26,19 @@
|
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
| 27 |
-
},
|
| 28 |
-
"3": {
|
| 29 |
-
"content": "<pad>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"bos_token": "<s>",
|
| 38 |
"clean_up_tokenization_spaces": false,
|
| 39 |
"eos_token": "</s>",
|
| 40 |
"extra_special_tokens": {},
|
| 41 |
-
"
|
| 42 |
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
-
"pad_token": "<
|
| 44 |
"padding_side": "left",
|
| 45 |
-
"
|
|
|
|
|
|
|
| 46 |
"unk_token": "<unk>",
|
| 47 |
-
"
|
| 48 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
|
|
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
}
|
| 30 |
},
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"clean_up_tokenization_spaces": false,
|
| 33 |
"eos_token": "</s>",
|
| 34 |
"extra_special_tokens": {},
|
| 35 |
+
"legacy": true,
|
| 36 |
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "<unk>",
|
| 38 |
"padding_side": "left",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false
|
| 44 |
}
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,803 +1,125 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "./output/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 150,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.2777777777777778,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.5555555555555556,
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.8333333333333334,
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss":
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 1.1111111111111112,
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 1.3888888888888888,
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 1.6666666666666665,
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss":
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 1.9444444444444444,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss":
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 2.2222222222222223,
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss":
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 2.5,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss":
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 2.7777777777777777,
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss":
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 3.0555555555555554,
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss":
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 3.3333333333333335,
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss":
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 3.611111111111111,
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss":
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 3.888888888888889,
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss":
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 4.166666666666667,
|
| 111 |
-
"grad_norm":
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss":
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 4.166666666666667,
|
| 118 |
-
"eval_loss":
|
| 119 |
-
"eval_runtime": 0.
|
| 120 |
-
"eval_samples_per_second":
|
| 121 |
-
"eval_steps_per_second":
|
| 122 |
"step": 150
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 4.444444444444445,
|
| 126 |
-
"grad_norm": 101.75000762939453,
|
| 127 |
-
"learning_rate": 4.99815044801767e-06,
|
| 128 |
-
"loss": 3.9084,
|
| 129 |
-
"step": 160
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 4.722222222222222,
|
| 133 |
-
"grad_norm": 68.58529663085938,
|
| 134 |
-
"learning_rate": 4.997482666353287e-06,
|
| 135 |
-
"loss": 3.6879,
|
| 136 |
-
"step": 170
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 5.0,
|
| 140 |
-
"grad_norm": 75.727294921875,
|
| 141 |
-
"learning_rate": 4.9967122229584614e-06,
|
| 142 |
-
"loss": 3.6844,
|
| 143 |
-
"step": 180
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 5.277777777777778,
|
| 147 |
-
"grad_norm": 191.76918029785156,
|
| 148 |
-
"learning_rate": 4.995839149503103e-06,
|
| 149 |
-
"loss": 3.9383,
|
| 150 |
-
"step": 190
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 5.555555555555555,
|
| 154 |
-
"grad_norm": 72.1632080078125,
|
| 155 |
-
"learning_rate": 4.994863481875842e-06,
|
| 156 |
-
"loss": 3.5542,
|
| 157 |
-
"step": 200
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 5.833333333333333,
|
| 161 |
-
"grad_norm": 158.5887908935547,
|
| 162 |
-
"learning_rate": 4.993785260182552e-06,
|
| 163 |
-
"loss": 3.4056,
|
| 164 |
-
"step": 210
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 6.111111111111111,
|
| 168 |
-
"grad_norm": 89.98544311523438,
|
| 169 |
-
"learning_rate": 4.992604528744705e-06,
|
| 170 |
-
"loss": 3.5972,
|
| 171 |
-
"step": 220
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 6.388888888888889,
|
| 175 |
-
"grad_norm": 124.9444351196289,
|
| 176 |
-
"learning_rate": 4.991321336097546e-06,
|
| 177 |
-
"loss": 3.819,
|
| 178 |
-
"step": 230
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 6.666666666666667,
|
| 182 |
-
"grad_norm": 97.10274505615234,
|
| 183 |
-
"learning_rate": 4.989935734988098e-06,
|
| 184 |
-
"loss": 3.2709,
|
| 185 |
-
"step": 240
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 6.944444444444445,
|
| 189 |
-
"grad_norm": 107.55123138427734,
|
| 190 |
-
"learning_rate": 4.988447782372996e-06,
|
| 191 |
-
"loss": 3.0078,
|
| 192 |
-
"step": 250
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 7.222222222222222,
|
| 196 |
-
"grad_norm": 102.92362213134766,
|
| 197 |
-
"learning_rate": 4.986857539416144e-06,
|
| 198 |
-
"loss": 3.3251,
|
| 199 |
-
"step": 260
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 7.5,
|
| 203 |
-
"grad_norm": 83.20296478271484,
|
| 204 |
-
"learning_rate": 4.985165071486201e-06,
|
| 205 |
-
"loss": 3.669,
|
| 206 |
-
"step": 270
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 7.777777777777778,
|
| 210 |
-
"grad_norm": 78.28851318359375,
|
| 211 |
-
"learning_rate": 4.983370448153896e-06,
|
| 212 |
-
"loss": 3.1768,
|
| 213 |
-
"step": 280
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 8.055555555555555,
|
| 217 |
-
"grad_norm": 64.56950378417969,
|
| 218 |
-
"learning_rate": 4.981473743189163e-06,
|
| 219 |
-
"loss": 3.2936,
|
| 220 |
-
"step": 290
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 8.333333333333334,
|
| 224 |
-
"grad_norm": 71.38610076904297,
|
| 225 |
-
"learning_rate": 4.979475034558115e-06,
|
| 226 |
-
"loss": 2.9679,
|
| 227 |
-
"step": 300
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 8.333333333333334,
|
| 231 |
-
"eval_loss": 2.776277542114258,
|
| 232 |
-
"eval_runtime": 0.3519,
|
| 233 |
-
"eval_samples_per_second": 25.575,
|
| 234 |
-
"eval_steps_per_second": 25.575,
|
| 235 |
-
"step": 300
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 8.61111111111111,
|
| 239 |
-
"grad_norm": 70.84721374511719,
|
| 240 |
-
"learning_rate": 4.977374404419838e-06,
|
| 241 |
-
"loss": 3.8222,
|
| 242 |
-
"step": 310
|
| 243 |
-
},
|
| 244 |
-
{
|
| 245 |
-
"epoch": 8.88888888888889,
|
| 246 |
-
"grad_norm": 57.08628845214844,
|
| 247 |
-
"learning_rate": 4.9751719391230055e-06,
|
| 248 |
-
"loss": 3.139,
|
| 249 |
-
"step": 320
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 9.166666666666666,
|
| 253 |
-
"grad_norm": 114.66728973388672,
|
| 254 |
-
"learning_rate": 4.9728677292023405e-06,
|
| 255 |
-
"loss": 2.7926,
|
| 256 |
-
"step": 330
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 9.444444444444445,
|
| 260 |
-
"grad_norm": 107.12257385253906,
|
| 261 |
-
"learning_rate": 4.97046186937489e-06,
|
| 262 |
-
"loss": 3.6297,
|
| 263 |
-
"step": 340
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 9.722222222222221,
|
| 267 |
-
"grad_norm": 123.43621063232422,
|
| 268 |
-
"learning_rate": 4.967954458536126e-06,
|
| 269 |
-
"loss": 2.9921,
|
| 270 |
-
"step": 350
|
| 271 |
-
},
|
| 272 |
-
{
|
| 273 |
-
"epoch": 10.0,
|
| 274 |
-
"grad_norm": 90.94454956054688,
|
| 275 |
-
"learning_rate": 4.965345599755888e-06,
|
| 276 |
-
"loss": 2.9652,
|
| 277 |
-
"step": 360
|
| 278 |
-
},
|
| 279 |
-
{
|
| 280 |
-
"epoch": 10.277777777777779,
|
| 281 |
-
"grad_norm": 95.23873901367188,
|
| 282 |
-
"learning_rate": 4.9626354002741424e-06,
|
| 283 |
-
"loss": 3.0514,
|
| 284 |
-
"step": 370
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 10.555555555555555,
|
| 288 |
-
"grad_norm": 59.19866943359375,
|
| 289 |
-
"learning_rate": 4.959823971496575e-06,
|
| 290 |
-
"loss": 2.7505,
|
| 291 |
-
"step": 380
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 10.833333333333334,
|
| 295 |
-
"grad_norm": 86.36837768554688,
|
| 296 |
-
"learning_rate": 4.95691142899001e-06,
|
| 297 |
-
"loss": 2.9705,
|
| 298 |
-
"step": 390
|
| 299 |
-
},
|
| 300 |
-
{
|
| 301 |
-
"epoch": 11.11111111111111,
|
| 302 |
-
"grad_norm": 78.96321868896484,
|
| 303 |
-
"learning_rate": 4.953897892477664e-06,
|
| 304 |
-
"loss": 3.1144,
|
| 305 |
-
"step": 400
|
| 306 |
-
},
|
| 307 |
-
{
|
| 308 |
-
"epoch": 11.38888888888889,
|
| 309 |
-
"grad_norm": 53.98061752319336,
|
| 310 |
-
"learning_rate": 4.950783485834218e-06,
|
| 311 |
-
"loss": 2.5288,
|
| 312 |
-
"step": 410
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"epoch": 11.666666666666666,
|
| 316 |
-
"grad_norm": 113.72119140625,
|
| 317 |
-
"learning_rate": 4.947568337080733e-06,
|
| 318 |
-
"loss": 2.8438,
|
| 319 |
-
"step": 420
|
| 320 |
-
},
|
| 321 |
-
{
|
| 322 |
-
"epoch": 11.944444444444445,
|
| 323 |
-
"grad_norm": 81.29522705078125,
|
| 324 |
-
"learning_rate": 4.944252578379379e-06,
|
| 325 |
-
"loss": 2.7956,
|
| 326 |
-
"step": 430
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 12.222222222222221,
|
| 330 |
-
"grad_norm": 58.65493392944336,
|
| 331 |
-
"learning_rate": 4.940836346028011e-06,
|
| 332 |
-
"loss": 2.8808,
|
| 333 |
-
"step": 440
|
| 334 |
-
},
|
| 335 |
-
{
|
| 336 |
-
"epoch": 12.5,
|
| 337 |
-
"grad_norm": 88.85804748535156,
|
| 338 |
-
"learning_rate": 4.937319780454559e-06,
|
| 339 |
-
"loss": 2.9837,
|
| 340 |
-
"step": 450
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"epoch": 12.5,
|
| 344 |
-
"eval_loss": 2.297574281692505,
|
| 345 |
-
"eval_runtime": 0.3379,
|
| 346 |
-
"eval_samples_per_second": 26.638,
|
| 347 |
-
"eval_steps_per_second": 26.638,
|
| 348 |
-
"step": 450
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 12.777777777777779,
|
| 352 |
-
"grad_norm": 154.9428253173828,
|
| 353 |
-
"learning_rate": 4.933703026211262e-06,
|
| 354 |
-
"loss": 2.4245,
|
| 355 |
-
"step": 460
|
| 356 |
-
},
|
| 357 |
-
{
|
| 358 |
-
"epoch": 13.055555555555555,
|
| 359 |
-
"grad_norm": 60.50612258911133,
|
| 360 |
-
"learning_rate": 4.92998623196872e-06,
|
| 361 |
-
"loss": 2.5858,
|
| 362 |
-
"step": 470
|
| 363 |
-
},
|
| 364 |
-
{
|
| 365 |
-
"epoch": 13.333333333333334,
|
| 366 |
-
"grad_norm": 65.40650177001953,
|
| 367 |
-
"learning_rate": 4.926169550509787e-06,
|
| 368 |
-
"loss": 2.865,
|
| 369 |
-
"step": 480
|
| 370 |
-
},
|
| 371 |
-
{
|
| 372 |
-
"epoch": 13.61111111111111,
|
| 373 |
-
"grad_norm": 61.311580657958984,
|
| 374 |
-
"learning_rate": 4.9222531387232885e-06,
|
| 375 |
-
"loss": 2.3105,
|
| 376 |
-
"step": 490
|
| 377 |
-
},
|
| 378 |
-
{
|
| 379 |
-
"epoch": 13.88888888888889,
|
| 380 |
-
"grad_norm": 132.292236328125,
|
| 381 |
-
"learning_rate": 4.918237157597574e-06,
|
| 382 |
-
"loss": 2.6459,
|
| 383 |
-
"step": 500
|
| 384 |
-
},
|
| 385 |
-
{
|
| 386 |
-
"epoch": 14.166666666666666,
|
| 387 |
-
"grad_norm": 64.7785873413086,
|
| 388 |
-
"learning_rate": 4.914121772213898e-06,
|
| 389 |
-
"loss": 2.1178,
|
| 390 |
-
"step": 510
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 14.444444444444445,
|
| 394 |
-
"grad_norm": 63.461647033691406,
|
| 395 |
-
"learning_rate": 4.909907151739634e-06,
|
| 396 |
-
"loss": 2.6851,
|
| 397 |
-
"step": 520
|
| 398 |
-
},
|
| 399 |
-
{
|
| 400 |
-
"epoch": 14.722222222222221,
|
| 401 |
-
"grad_norm": 81.0846939086914,
|
| 402 |
-
"learning_rate": 4.905593469421323e-06,
|
| 403 |
-
"loss": 2.3994,
|
| 404 |
-
"step": 530
|
| 405 |
-
},
|
| 406 |
-
{
|
| 407 |
-
"epoch": 15.0,
|
| 408 |
-
"grad_norm": 126.24242401123047,
|
| 409 |
-
"learning_rate": 4.901180902577549e-06,
|
| 410 |
-
"loss": 2.4261,
|
| 411 |
-
"step": 540
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 15.277777777777779,
|
| 415 |
-
"grad_norm": 85.41973876953125,
|
| 416 |
-
"learning_rate": 4.896669632591652e-06,
|
| 417 |
-
"loss": 2.343,
|
| 418 |
-
"step": 550
|
| 419 |
-
},
|
| 420 |
-
{
|
| 421 |
-
"epoch": 15.555555555555555,
|
| 422 |
-
"grad_norm": 109.64722442626953,
|
| 423 |
-
"learning_rate": 4.892059844904273e-06,
|
| 424 |
-
"loss": 2.3353,
|
| 425 |
-
"step": 560
|
| 426 |
-
},
|
| 427 |
-
{
|
| 428 |
-
"epoch": 15.833333333333334,
|
| 429 |
-
"grad_norm": 78.56090545654297,
|
| 430 |
-
"learning_rate": 4.8873517290057265e-06,
|
| 431 |
-
"loss": 2.3844,
|
| 432 |
-
"step": 570
|
| 433 |
-
},
|
| 434 |
-
{
|
| 435 |
-
"epoch": 16.11111111111111,
|
| 436 |
-
"grad_norm": 49.437007904052734,
|
| 437 |
-
"learning_rate": 4.882545478428219e-06,
|
| 438 |
-
"loss": 2.2314,
|
| 439 |
-
"step": 580
|
| 440 |
-
},
|
| 441 |
-
{
|
| 442 |
-
"epoch": 16.38888888888889,
|
| 443 |
-
"grad_norm": 54.6522331237793,
|
| 444 |
-
"learning_rate": 4.8776412907378845e-06,
|
| 445 |
-
"loss": 2.3513,
|
| 446 |
-
"step": 590
|
| 447 |
-
},
|
| 448 |
-
{
|
| 449 |
-
"epoch": 16.666666666666668,
|
| 450 |
-
"grad_norm": 67.71409606933594,
|
| 451 |
-
"learning_rate": 4.872639367526672e-06,
|
| 452 |
-
"loss": 2.6987,
|
| 453 |
-
"step": 600
|
| 454 |
-
},
|
| 455 |
-
{
|
| 456 |
-
"epoch": 16.666666666666668,
|
| 457 |
-
"eval_loss": 1.923978567123413,
|
| 458 |
-
"eval_runtime": 0.3404,
|
| 459 |
-
"eval_samples_per_second": 26.437,
|
| 460 |
-
"eval_steps_per_second": 26.437,
|
| 461 |
-
"step": 600
|
| 462 |
-
},
|
| 463 |
-
{
|
| 464 |
-
"epoch": 16.944444444444443,
|
| 465 |
-
"grad_norm": 129.5966339111328,
|
| 466 |
-
"learning_rate": 4.8675399144040535e-06,
|
| 467 |
-
"loss": 1.8938,
|
| 468 |
-
"step": 610
|
| 469 |
-
},
|
| 470 |
-
{
|
| 471 |
-
"epoch": 17.22222222222222,
|
| 472 |
-
"grad_norm": 131.9312744140625,
|
| 473 |
-
"learning_rate": 4.862343140988573e-06,
|
| 474 |
-
"loss": 2.3376,
|
| 475 |
-
"step": 620
|
| 476 |
-
},
|
| 477 |
-
{
|
| 478 |
-
"epoch": 17.5,
|
| 479 |
-
"grad_norm": 74.60222625732422,
|
| 480 |
-
"learning_rate": 4.857049260899233e-06,
|
| 481 |
-
"loss": 1.6671,
|
| 482 |
-
"step": 630
|
| 483 |
-
},
|
| 484 |
-
{
|
| 485 |
-
"epoch": 17.77777777777778,
|
| 486 |
-
"grad_norm": 71.88908386230469,
|
| 487 |
-
"learning_rate": 4.851658491746707e-06,
|
| 488 |
-
"loss": 2.4909,
|
| 489 |
-
"step": 640
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 18.055555555555557,
|
| 493 |
-
"grad_norm": 61.891929626464844,
|
| 494 |
-
"learning_rate": 4.846171055124401e-06,
|
| 495 |
-
"loss": 2.1035,
|
| 496 |
-
"step": 650
|
| 497 |
-
},
|
| 498 |
-
{
|
| 499 |
-
"epoch": 18.333333333333332,
|
| 500 |
-
"grad_norm": 92.33902740478516,
|
| 501 |
-
"learning_rate": 4.8405871765993435e-06,
|
| 502 |
-
"loss": 2.3135,
|
| 503 |
-
"step": 660
|
| 504 |
-
},
|
| 505 |
-
{
|
| 506 |
-
"epoch": 18.61111111111111,
|
| 507 |
-
"grad_norm": 119.72765350341797,
|
| 508 |
-
"learning_rate": 4.834907085702909e-06,
|
| 509 |
-
"loss": 2.0914,
|
| 510 |
-
"step": 670
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"epoch": 18.88888888888889,
|
| 514 |
-
"grad_norm": 85.96342468261719,
|
| 515 |
-
"learning_rate": 4.829131015921386e-06,
|
| 516 |
-
"loss": 2.081,
|
| 517 |
-
"step": 680
|
| 518 |
-
},
|
| 519 |
-
{
|
| 520 |
-
"epoch": 19.166666666666668,
|
| 521 |
-
"grad_norm": 43.483604431152344,
|
| 522 |
-
"learning_rate": 4.82325920468638e-06,
|
| 523 |
-
"loss": 2.0018,
|
| 524 |
-
"step": 690
|
| 525 |
-
},
|
| 526 |
-
{
|
| 527 |
-
"epoch": 19.444444444444443,
|
| 528 |
-
"grad_norm": 58.90408706665039,
|
| 529 |
-
"learning_rate": 4.817291893365055e-06,
|
| 530 |
-
"loss": 2.0761,
|
| 531 |
-
"step": 700
|
| 532 |
-
},
|
| 533 |
-
{
|
| 534 |
-
"epoch": 19.72222222222222,
|
| 535 |
-
"grad_norm": 36.50251007080078,
|
| 536 |
-
"learning_rate": 4.811229327250204e-06,
|
| 537 |
-
"loss": 1.8106,
|
| 538 |
-
"step": 710
|
| 539 |
-
},
|
| 540 |
-
{
|
| 541 |
-
"epoch": 20.0,
|
| 542 |
-
"grad_norm": 165.16329956054688,
|
| 543 |
-
"learning_rate": 4.805071755550177e-06,
|
| 544 |
-
"loss": 2.0202,
|
| 545 |
-
"step": 720
|
| 546 |
-
},
|
| 547 |
-
{
|
| 548 |
-
"epoch": 20.27777777777778,
|
| 549 |
-
"grad_norm": 59.47331619262695,
|
| 550 |
-
"learning_rate": 4.7988194313786275e-06,
|
| 551 |
-
"loss": 2.0095,
|
| 552 |
-
"step": 730
|
| 553 |
-
},
|
| 554 |
-
{
|
| 555 |
-
"epoch": 20.555555555555557,
|
| 556 |
-
"grad_norm": 85.59427642822266,
|
| 557 |
-
"learning_rate": 4.7924726117441135e-06,
|
| 558 |
-
"loss": 1.9848,
|
| 559 |
-
"step": 740
|
| 560 |
-
},
|
| 561 |
-
{
|
| 562 |
-
"epoch": 20.833333333333332,
|
| 563 |
-
"grad_norm": 135.71310424804688,
|
| 564 |
-
"learning_rate": 4.786031557539532e-06,
|
| 565 |
-
"loss": 1.8273,
|
| 566 |
-
"step": 750
|
| 567 |
-
},
|
| 568 |
-
{
|
| 569 |
-
"epoch": 20.833333333333332,
|
| 570 |
-
"eval_loss": 1.7372846603393555,
|
| 571 |
-
"eval_runtime": 0.3551,
|
| 572 |
-
"eval_samples_per_second": 25.346,
|
| 573 |
-
"eval_steps_per_second": 25.346,
|
| 574 |
-
"step": 750
|
| 575 |
-
},
|
| 576 |
-
{
|
| 577 |
-
"epoch": 21.11111111111111,
|
| 578 |
-
"grad_norm": 54.28533935546875,
|
| 579 |
-
"learning_rate": 4.779496533531393e-06,
|
| 580 |
-
"loss": 1.9957,
|
| 581 |
-
"step": 760
|
| 582 |
-
},
|
| 583 |
-
{
|
| 584 |
-
"epoch": 21.38888888888889,
|
| 585 |
-
"grad_norm": 61.805938720703125,
|
| 586 |
-
"learning_rate": 4.7728678083489375e-06,
|
| 587 |
-
"loss": 1.8208,
|
| 588 |
-
"step": 770
|
| 589 |
-
},
|
| 590 |
-
{
|
| 591 |
-
"epoch": 21.666666666666668,
|
| 592 |
-
"grad_norm": 74.6706314086914,
|
| 593 |
-
"learning_rate": 4.766145654473096e-06,
|
| 594 |
-
"loss": 1.8079,
|
| 595 |
-
"step": 780
|
| 596 |
-
},
|
| 597 |
-
{
|
| 598 |
-
"epoch": 21.944444444444443,
|
| 599 |
-
"grad_norm": 94.1037368774414,
|
| 600 |
-
"learning_rate": 4.7593303482252835e-06,
|
| 601 |
-
"loss": 1.9016,
|
| 602 |
-
"step": 790
|
| 603 |
-
},
|
| 604 |
-
{
|
| 605 |
-
"epoch": 22.22222222222222,
|
| 606 |
-
"grad_norm": 52.785804748535156,
|
| 607 |
-
"learning_rate": 4.752422169756048e-06,
|
| 608 |
-
"loss": 1.4806,
|
| 609 |
-
"step": 800
|
| 610 |
-
},
|
| 611 |
-
{
|
| 612 |
-
"epoch": 22.5,
|
| 613 |
-
"grad_norm": 137.42938232421875,
|
| 614 |
-
"learning_rate": 4.745421403033548e-06,
|
| 615 |
-
"loss": 2.0772,
|
| 616 |
-
"step": 810
|
| 617 |
-
},
|
| 618 |
-
{
|
| 619 |
-
"epoch": 22.77777777777778,
|
| 620 |
-
"grad_norm": 49.996612548828125,
|
| 621 |
-
"learning_rate": 4.738328335831883e-06,
|
| 622 |
-
"loss": 1.9437,
|
| 623 |
-
"step": 820
|
| 624 |
-
},
|
| 625 |
-
{
|
| 626 |
-
"epoch": 23.055555555555557,
|
| 627 |
-
"grad_norm": 237.96719360351562,
|
| 628 |
-
"learning_rate": 4.7311432597192655e-06,
|
| 629 |
-
"loss": 1.9811,
|
| 630 |
-
"step": 830
|
| 631 |
-
},
|
| 632 |
-
{
|
| 633 |
-
"epoch": 23.333333333333332,
|
| 634 |
-
"grad_norm": 83.38140106201172,
|
| 635 |
-
"learning_rate": 4.72386647004603e-06,
|
| 636 |
-
"loss": 2.0359,
|
| 637 |
-
"step": 840
|
| 638 |
-
},
|
| 639 |
-
{
|
| 640 |
-
"epoch": 23.61111111111111,
|
| 641 |
-
"grad_norm": 101.59205627441406,
|
| 642 |
-
"learning_rate": 4.716498265932501e-06,
|
| 643 |
-
"loss": 1.4225,
|
| 644 |
-
"step": 850
|
| 645 |
-
},
|
| 646 |
-
{
|
| 647 |
-
"epoch": 23.88888888888889,
|
| 648 |
-
"grad_norm": 53.51150131225586,
|
| 649 |
-
"learning_rate": 4.7090389502566884e-06,
|
| 650 |
-
"loss": 1.6665,
|
| 651 |
-
"step": 860
|
| 652 |
-
},
|
| 653 |
-
{
|
| 654 |
-
"epoch": 24.166666666666668,
|
| 655 |
-
"grad_norm": 61.94685363769531,
|
| 656 |
-
"learning_rate": 4.701488829641845e-06,
|
| 657 |
-
"loss": 1.7755,
|
| 658 |
-
"step": 870
|
| 659 |
-
},
|
| 660 |
-
{
|
| 661 |
-
"epoch": 24.444444444444443,
|
| 662 |
-
"grad_norm": 144.9290008544922,
|
| 663 |
-
"learning_rate": 4.693848214443858e-06,
|
| 664 |
-
"loss": 1.8703,
|
| 665 |
-
"step": 880
|
| 666 |
-
},
|
| 667 |
-
{
|
| 668 |
-
"epoch": 24.72222222222222,
|
| 669 |
-
"grad_norm": 66.09136962890625,
|
| 670 |
-
"learning_rate": 4.686117418738489e-06,
|
| 671 |
-
"loss": 1.8144,
|
| 672 |
-
"step": 890
|
| 673 |
-
},
|
| 674 |
-
{
|
| 675 |
-
"epoch": 25.0,
|
| 676 |
-
"grad_norm": 42.97128677368164,
|
| 677 |
-
"learning_rate": 4.678296760308474e-06,
|
| 678 |
-
"loss": 1.4169,
|
| 679 |
-
"step": 900
|
| 680 |
-
},
|
| 681 |
-
{
|
| 682 |
-
"epoch": 25.0,
|
| 683 |
-
"eval_loss": 1.650766372680664,
|
| 684 |
-
"eval_runtime": 0.3362,
|
| 685 |
-
"eval_samples_per_second": 26.77,
|
| 686 |
-
"eval_steps_per_second": 26.77,
|
| 687 |
-
"step": 900
|
| 688 |
-
},
|
| 689 |
-
{
|
| 690 |
-
"epoch": 25.27777777777778,
|
| 691 |
-
"grad_norm": 79.94445037841797,
|
| 692 |
-
"learning_rate": 4.670386560630446e-06,
|
| 693 |
-
"loss": 1.7837,
|
| 694 |
-
"step": 910
|
| 695 |
-
},
|
| 696 |
-
{
|
| 697 |
-
"epoch": 25.555555555555557,
|
| 698 |
-
"grad_norm": 51.69401168823242,
|
| 699 |
-
"learning_rate": 4.6623871448617345e-06,
|
| 700 |
-
"loss": 1.6088,
|
| 701 |
-
"step": 920
|
| 702 |
-
},
|
| 703 |
-
{
|
| 704 |
-
"epoch": 25.833333333333332,
|
| 705 |
-
"grad_norm": 57.889190673828125,
|
| 706 |
-
"learning_rate": 4.654298841826988e-06,
|
| 707 |
-
"loss": 1.6924,
|
| 708 |
-
"step": 930
|
| 709 |
-
},
|
| 710 |
-
{
|
| 711 |
-
"epoch": 26.11111111111111,
|
| 712 |
-
"grad_norm": 105.6498794555664,
|
| 713 |
-
"learning_rate": 4.646121984004666e-06,
|
| 714 |
-
"loss": 1.5328,
|
| 715 |
-
"step": 940
|
| 716 |
-
},
|
| 717 |
-
{
|
| 718 |
-
"epoch": 26.38888888888889,
|
| 719 |
-
"grad_norm": 40.925804138183594,
|
| 720 |
-
"learning_rate": 4.637856907513366e-06,
|
| 721 |
-
"loss": 1.4407,
|
| 722 |
-
"step": 950
|
| 723 |
-
},
|
| 724 |
-
{
|
| 725 |
-
"epoch": 26.666666666666668,
|
| 726 |
-
"grad_norm": 95.5039291381836,
|
| 727 |
-
"learning_rate": 4.629503952098011e-06,
|
| 728 |
-
"loss": 1.7479,
|
| 729 |
-
"step": 960
|
| 730 |
-
},
|
| 731 |
-
{
|
| 732 |
-
"epoch": 26.944444444444443,
|
| 733 |
-
"grad_norm": 82.50537872314453,
|
| 734 |
-
"learning_rate": 4.621063461115882e-06,
|
| 735 |
-
"loss": 1.4828,
|
| 736 |
-
"step": 970
|
| 737 |
-
},
|
| 738 |
-
{
|
| 739 |
-
"epoch": 27.22222222222222,
|
| 740 |
-
"grad_norm": 58.20735168457031,
|
| 741 |
-
"learning_rate": 4.612535781522504e-06,
|
| 742 |
-
"loss": 1.3901,
|
| 743 |
-
"step": 980
|
| 744 |
-
},
|
| 745 |
-
{
|
| 746 |
-
"epoch": 27.5,
|
| 747 |
-
"grad_norm": 103.87213897705078,
|
| 748 |
-
"learning_rate": 4.6039212638573835e-06,
|
| 749 |
-
"loss": 1.6103,
|
| 750 |
-
"step": 990
|
| 751 |
-
},
|
| 752 |
-
{
|
| 753 |
-
"epoch": 27.77777777777778,
|
| 754 |
-
"grad_norm": 46.515586853027344,
|
| 755 |
-
"learning_rate": 4.5952202622296015e-06,
|
| 756 |
-
"loss": 1.6174,
|
| 757 |
-
"step": 1000
|
| 758 |
-
},
|
| 759 |
-
{
|
| 760 |
-
"epoch": 28.055555555555557,
|
| 761 |
-
"grad_norm": 83.15587615966797,
|
| 762 |
-
"learning_rate": 4.586433134303257e-06,
|
| 763 |
-
"loss": 1.477,
|
| 764 |
-
"step": 1010
|
| 765 |
-
},
|
| 766 |
-
{
|
| 767 |
-
"epoch": 28.333333333333332,
|
| 768 |
-
"grad_norm": 89.03128051757812,
|
| 769 |
-
"learning_rate": 4.57756024128276e-06,
|
| 770 |
-
"loss": 1.6058,
|
| 771 |
-
"step": 1020
|
| 772 |
-
},
|
| 773 |
-
{
|
| 774 |
-
"epoch": 28.61111111111111,
|
| 775 |
-
"grad_norm": 53.300315856933594,
|
| 776 |
-
"learning_rate": 4.5686019478979915e-06,
|
| 777 |
-
"loss": 1.392,
|
| 778 |
-
"step": 1030
|
| 779 |
-
},
|
| 780 |
-
{
|
| 781 |
-
"epoch": 28.88888888888889,
|
| 782 |
-
"grad_norm": 63.217716217041016,
|
| 783 |
-
"learning_rate": 4.559558622389304e-06,
|
| 784 |
-
"loss": 1.4695,
|
| 785 |
-
"step": 1040
|
| 786 |
-
},
|
| 787 |
-
{
|
| 788 |
-
"epoch": 29.166666666666668,
|
| 789 |
-
"grad_norm": 38.29002380371094,
|
| 790 |
-
"learning_rate": 4.55043063649239e-06,
|
| 791 |
-
"loss": 1.3374,
|
| 792 |
-
"step": 1050
|
| 793 |
-
},
|
| 794 |
-
{
|
| 795 |
-
"epoch": 29.166666666666668,
|
| 796 |
-
"eval_loss": 1.628559947013855,
|
| 797 |
-
"eval_runtime": 0.3368,
|
| 798 |
-
"eval_samples_per_second": 26.721,
|
| 799 |
-
"eval_steps_per_second": 26.721,
|
| 800 |
-
"step": 1050
|
| 801 |
}
|
| 802 |
],
|
| 803 |
"logging_steps": 10,
|
|
@@ -817,7 +139,7 @@
|
|
| 817 |
"attributes": {}
|
| 818 |
}
|
| 819 |
},
|
| 820 |
-
"total_flos":
|
| 821 |
"train_batch_size": 2,
|
| 822 |
"trial_name": null,
|
| 823 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.45632824301719666,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-150",
|
| 4 |
+
"epoch": 4.166666666666667,
|
| 5 |
"eval_steps": 150,
|
| 6 |
+
"global_step": 150,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.2777777777777778,
|
| 13 |
+
"grad_norm": 16.678560256958008,
|
| 14 |
+
"learning_rate": 1.8053203938204972e-06,
|
| 15 |
+
"loss": 0.4404,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.5555555555555556,
|
| 20 |
+
"grad_norm": 24.250707626342773,
|
| 21 |
+
"learning_rate": 3.6106407876409943e-06,
|
| 22 |
+
"loss": 0.4338,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.8333333333333334,
|
| 27 |
+
"grad_norm": 11.988567352294922,
|
| 28 |
+
"learning_rate": 5.4159611814614915e-06,
|
| 29 |
+
"loss": 0.5386,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 1.1111111111111112,
|
| 34 |
+
"grad_norm": 10.733481407165527,
|
| 35 |
+
"learning_rate": 7.221281575281989e-06,
|
| 36 |
+
"loss": 0.4805,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 1.3888888888888888,
|
| 41 |
+
"grad_norm": 10.659712791442871,
|
| 42 |
+
"learning_rate": 9.026601969102486e-06,
|
| 43 |
+
"loss": 0.4308,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 1.6666666666666665,
|
| 48 |
+
"grad_norm": 14.367152214050293,
|
| 49 |
+
"learning_rate": 1.0831922362922983e-05,
|
| 50 |
+
"loss": 0.4926,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 1.9444444444444444,
|
| 55 |
+
"grad_norm": 26.407075881958008,
|
| 56 |
+
"learning_rate": 1.263724275674348e-05,
|
| 57 |
+
"loss": 0.4749,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 2.2222222222222223,
|
| 62 |
+
"grad_norm": 16.550508499145508,
|
| 63 |
+
"learning_rate": 1.4442563150563977e-05,
|
| 64 |
+
"loss": 0.3476,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 2.5,
|
| 69 |
+
"grad_norm": 12.457433700561523,
|
| 70 |
+
"learning_rate": 1.6247883544384475e-05,
|
| 71 |
+
"loss": 0.4611,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 2.7777777777777777,
|
| 76 |
+
"grad_norm": 6.2512030601501465,
|
| 77 |
+
"learning_rate": 1.8053203938204972e-05,
|
| 78 |
+
"loss": 0.3172,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 3.0555555555555554,
|
| 83 |
+
"grad_norm": 12.345681190490723,
|
| 84 |
+
"learning_rate": 1.8053018414078887e-05,
|
| 85 |
+
"loss": 0.3607,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 3.3333333333333335,
|
| 90 |
+
"grad_norm": 10.975536346435547,
|
| 91 |
+
"learning_rate": 1.8052461849326804e-05,
|
| 92 |
+
"loss": 0.2315,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 3.611111111111111,
|
| 97 |
+
"grad_norm": 22.538253784179688,
|
| 98 |
+
"learning_rate": 1.8051534266826923e-05,
|
| 99 |
+
"loss": 0.2458,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 3.888888888888889,
|
| 104 |
+
"grad_norm": 9.7154541015625,
|
| 105 |
+
"learning_rate": 1.8050235704708523e-05,
|
| 106 |
+
"loss": 0.2693,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 4.166666666666667,
|
| 111 |
+
"grad_norm": 7.695099353790283,
|
| 112 |
+
"learning_rate": 1.8048566216350408e-05,
|
| 113 |
+
"loss": 0.2051,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 4.166666666666667,
|
| 118 |
+
"eval_loss": 0.45632824301719666,
|
| 119 |
+
"eval_runtime": 0.9401,
|
| 120 |
+
"eval_samples_per_second": 9.574,
|
| 121 |
+
"eval_steps_per_second": 9.574,
|
| 122 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
}
|
| 124 |
],
|
| 125 |
"logging_steps": 10,
|
|
|
|
| 139 |
"attributes": {}
|
| 140 |
}
|
| 141 |
},
|
| 142 |
+
"total_flos": 1908279321477120.0,
|
| 143 |
"train_batch_size": 2,
|
| 144 |
"trial_name": null,
|
| 145 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bdf1390d17124cf4f93eac9a9298192534d0bd0ab8b33fa14cac1a258bda108
|
| 3 |
+
size 5496
|