Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +138 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- checkpoint-10/README.md +21 -0
- checkpoint-10/adapter_config.json +21 -0
- checkpoint-10/adapter_model.safetensors +3 -0
- checkpoint-10/optimizer.pt +3 -0
- checkpoint-10/rng_state.pth +3 -0
- checkpoint-10/scheduler.pt +3 -0
- checkpoint-10/trainer_state.json +47 -0
- checkpoint-10/training_args.bin +3 -0
- checkpoint-740/README.md +21 -0
- checkpoint-740/adapter_config.json +21 -0
- checkpoint-740/adapter_model.safetensors +3 -0
- checkpoint-740/optimizer.pt +3 -0
- checkpoint-740/rng_state.pth +3 -0
- checkpoint-740/scheduler.pt +3 -0
- checkpoint-740/trainer_state.json +2091 -0
- checkpoint-740/training_args.bin +3 -0
- checkpoint-750/README.md +21 -0
- checkpoint-750/adapter_config.json +21 -0
- checkpoint-750/adapter_model.safetensors +3 -0
- checkpoint-750/optimizer.pt +3 -0
- checkpoint-750/rng_state.pth +3 -0
- checkpoint-750/scheduler.pt +3 -0
- checkpoint-750/trainer_state.json +2119 -0
- checkpoint-750/training_args.bin +3 -0
- checkpoint-760/README.md +21 -0
- checkpoint-760/adapter_config.json +21 -0
- checkpoint-760/adapter_model.safetensors +3 -0
- checkpoint-760/optimizer.pt +3 -0
- checkpoint-760/rng_state.pth +3 -0
- checkpoint-760/scheduler.pt +3 -0
- checkpoint-760/trainer_state.json +2147 -0
- checkpoint-760/training_args.bin +3 -0
- checkpoint-770/README.md +21 -0
- checkpoint-770/adapter_config.json +21 -0
- checkpoint-770/adapter_model.safetensors +3 -0
- checkpoint-770/optimizer.pt +3 -0
- checkpoint-770/rng_state.pth +3 -0
- checkpoint-770/scheduler.pt +3 -0
- checkpoint-770/trainer_state.json +2175 -0
- checkpoint-770/training_args.bin +3 -0
- config.json +39 -0
- logs/events.out.tfevents.1699989718.node0370.palmetto.clemson.edu.1119956.2 +3 -0
- logs/events.out.tfevents.1699989813.node0370.palmetto.clemson.edu.1119956.4 +3 -0
- logs/events.out.tfevents.1699994287.node0370.palmetto.clemson.edu.1126403.1 +3 -0
- logs/events.out.tfevents.1699995040.node0370.palmetto.clemson.edu.1127435.1 +3 -0
- logs/events.out.tfevents.1700064888.node0277.palmetto.clemson.edu.1971495.1 +3 -0
- logs/events.out.tfevents.1700066157.node0277.palmetto.clemson.edu.1973537.1 +3 -0
README.md
ADDED
|
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
|
| 19 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 20 |
+
- quant_method: bitsandbytes
|
| 21 |
+
- load_in_8bit: True
|
| 22 |
+
- load_in_4bit: False
|
| 23 |
+
- llm_int8_threshold: 6.0
|
| 24 |
+
- llm_int8_skip_modules: None
|
| 25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 26 |
+
- llm_int8_has_fp16_weight: False
|
| 27 |
+
- bnb_4bit_quant_type: fp4
|
| 28 |
+
- bnb_4bit_use_double_quant: False
|
| 29 |
+
- bnb_4bit_compute_dtype: float32
|
| 30 |
+
|
| 31 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 32 |
+
- quant_method: bitsandbytes
|
| 33 |
+
- load_in_8bit: True
|
| 34 |
+
- load_in_4bit: False
|
| 35 |
+
- llm_int8_threshold: 6.0
|
| 36 |
+
- llm_int8_skip_modules: None
|
| 37 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 38 |
+
- llm_int8_has_fp16_weight: False
|
| 39 |
+
- bnb_4bit_quant_type: fp4
|
| 40 |
+
- bnb_4bit_use_double_quant: False
|
| 41 |
+
- bnb_4bit_compute_dtype: float32
|
| 42 |
+
|
| 43 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 44 |
+
- quant_method: bitsandbytes
|
| 45 |
+
- load_in_8bit: True
|
| 46 |
+
- load_in_4bit: False
|
| 47 |
+
- llm_int8_threshold: 6.0
|
| 48 |
+
- llm_int8_skip_modules: None
|
| 49 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 50 |
+
- llm_int8_has_fp16_weight: False
|
| 51 |
+
- bnb_4bit_quant_type: fp4
|
| 52 |
+
- bnb_4bit_use_double_quant: False
|
| 53 |
+
- bnb_4bit_compute_dtype: float32
|
| 54 |
+
|
| 55 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 56 |
+
- quant_method: bitsandbytes
|
| 57 |
+
- load_in_8bit: True
|
| 58 |
+
- load_in_4bit: False
|
| 59 |
+
- llm_int8_threshold: 6.0
|
| 60 |
+
- llm_int8_skip_modules: None
|
| 61 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 62 |
+
- llm_int8_has_fp16_weight: False
|
| 63 |
+
- bnb_4bit_quant_type: fp4
|
| 64 |
+
- bnb_4bit_use_double_quant: False
|
| 65 |
+
- bnb_4bit_compute_dtype: float32
|
| 66 |
+
|
| 67 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 68 |
+
- quant_method: bitsandbytes
|
| 69 |
+
- load_in_8bit: True
|
| 70 |
+
- load_in_4bit: False
|
| 71 |
+
- llm_int8_threshold: 6.0
|
| 72 |
+
- llm_int8_skip_modules: None
|
| 73 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 74 |
+
- llm_int8_has_fp16_weight: False
|
| 75 |
+
- bnb_4bit_quant_type: fp4
|
| 76 |
+
- bnb_4bit_use_double_quant: False
|
| 77 |
+
- bnb_4bit_compute_dtype: float32
|
| 78 |
+
|
| 79 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 80 |
+
- quant_method: bitsandbytes
|
| 81 |
+
- load_in_8bit: True
|
| 82 |
+
- load_in_4bit: False
|
| 83 |
+
- llm_int8_threshold: 6.0
|
| 84 |
+
- llm_int8_skip_modules: None
|
| 85 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 86 |
+
- llm_int8_has_fp16_weight: False
|
| 87 |
+
- bnb_4bit_quant_type: fp4
|
| 88 |
+
- bnb_4bit_use_double_quant: False
|
| 89 |
+
- bnb_4bit_compute_dtype: float32
|
| 90 |
+
|
| 91 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 92 |
+
- quant_method: bitsandbytes
|
| 93 |
+
- load_in_8bit: True
|
| 94 |
+
- load_in_4bit: False
|
| 95 |
+
- llm_int8_threshold: 6.0
|
| 96 |
+
- llm_int8_skip_modules: None
|
| 97 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 98 |
+
- llm_int8_has_fp16_weight: False
|
| 99 |
+
- bnb_4bit_quant_type: fp4
|
| 100 |
+
- bnb_4bit_use_double_quant: False
|
| 101 |
+
- bnb_4bit_compute_dtype: float32
|
| 102 |
+
|
| 103 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 104 |
+
- quant_method: bitsandbytes
|
| 105 |
+
- load_in_8bit: True
|
| 106 |
+
- load_in_4bit: False
|
| 107 |
+
- llm_int8_threshold: 6.0
|
| 108 |
+
- llm_int8_skip_modules: None
|
| 109 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 110 |
+
- llm_int8_has_fp16_weight: False
|
| 111 |
+
- bnb_4bit_quant_type: fp4
|
| 112 |
+
- bnb_4bit_use_double_quant: False
|
| 113 |
+
- bnb_4bit_compute_dtype: float32
|
| 114 |
+
|
| 115 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 116 |
+
- quant_method: bitsandbytes
|
| 117 |
+
- load_in_8bit: True
|
| 118 |
+
- load_in_4bit: False
|
| 119 |
+
- llm_int8_threshold: 6.0
|
| 120 |
+
- llm_int8_skip_modules: None
|
| 121 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 122 |
+
- llm_int8_has_fp16_weight: False
|
| 123 |
+
- bnb_4bit_quant_type: fp4
|
| 124 |
+
- bnb_4bit_use_double_quant: False
|
| 125 |
+
- bnb_4bit_compute_dtype: float32
|
| 126 |
+
### Framework versions
|
| 127 |
+
|
| 128 |
+
- PEFT 0.5.0
|
| 129 |
+
- PEFT 0.5.0
|
| 130 |
+
- PEFT 0.5.0
|
| 131 |
+
- PEFT 0.5.0
|
| 132 |
+
- PEFT 0.5.0
|
| 133 |
+
- PEFT 0.5.0
|
| 134 |
+
- PEFT 0.5.0
|
| 135 |
+
- PEFT 0.5.0
|
| 136 |
+
- PEFT 0.5.0
|
| 137 |
+
|
| 138 |
+
- PEFT 0.5.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e89447616aaca469bb6106ebcb8ceb874e823d65a63eb3b53c8db20befadc78e
|
| 3 |
+
size 16823434
|
checkpoint-10/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.5.0
|
checkpoint-10/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-10/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ca7d05227d9acba4c7e6cfbf34f504664cb1204f380206708787481b36f515d
|
| 3 |
+
size 16794200
|
checkpoint-10/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe2e4ca09b0a6c6516a6e0065447618b3db4cd6de700dc91ddb551e63b925136
|
| 3 |
+
size 33663866
|
checkpoint-10/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfbd7c894a8329427aaddfb3f58ef2ae223d564384e6736a16a6c8f82f40c07a
|
| 3 |
+
size 14244
|
checkpoint-10/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be4a312bb2bd4504a249badcb489acaa3a989d6be708dfc5ab7e5fbf10ccf35e
|
| 3 |
+
size 1064
|
checkpoint-10/trainer_state.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.228980779647827,
|
| 3 |
+
"best_model_checkpoint": "/scratch/kwamea/llama-output/checkpoint-10",
|
| 4 |
+
"epoch": 0.7142857142857143,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 10,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.36,
|
| 13 |
+
"learning_rate": 6.428571428571429e-05,
|
| 14 |
+
"loss": 2.3035,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.36,
|
| 19 |
+
"eval_loss": 2.2832000255584717,
|
| 20 |
+
"eval_runtime": 2.2848,
|
| 21 |
+
"eval_samples_per_second": 2.626,
|
| 22 |
+
"eval_steps_per_second": 0.438,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.71,
|
| 27 |
+
"learning_rate": 2.857142857142857e-05,
|
| 28 |
+
"loss": 2.201,
|
| 29 |
+
"step": 10
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.71,
|
| 33 |
+
"eval_loss": 2.228980779647827,
|
| 34 |
+
"eval_runtime": 2.2845,
|
| 35 |
+
"eval_samples_per_second": 2.626,
|
| 36 |
+
"eval_steps_per_second": 0.438,
|
| 37 |
+
"step": 10
|
| 38 |
+
}
|
| 39 |
+
],
|
| 40 |
+
"logging_steps": 5,
|
| 41 |
+
"max_steps": 14,
|
| 42 |
+
"num_train_epochs": 1,
|
| 43 |
+
"save_steps": 10,
|
| 44 |
+
"total_flos": 3249703118438400.0,
|
| 45 |
+
"trial_name": null,
|
| 46 |
+
"trial_params": null
|
| 47 |
+
}
|
checkpoint-10/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e31c0035e9b22c0b3219696704e35bc756922ae5383b862d4d36c885235386d
|
| 3 |
+
size 4600
|
checkpoint-740/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.5.0
|
checkpoint-740/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-740/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f03e1c534886cae902eb7a95808425f743c4cc3a1c59b1e07887784083ecba1d
|
| 3 |
+
size 16794200
|
checkpoint-740/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74d299e76fecfc33dfb4e3257e588b1f1b71b75702404d67c6e7b40b83877416
|
| 3 |
+
size 33663866
|
checkpoint-740/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24f126ecca3177183e3c620be89ec9369ae206954d236b75754682aeb21d0ba2
|
| 3 |
+
size 14244
|
checkpoint-740/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6234655278ff34dff7cdc63b30f02513595625a8f6adbe76c717d04fbf89be9f
|
| 3 |
+
size 1064
|
checkpoint-740/trainer_state.json
ADDED
|
@@ -0,0 +1,2091 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.6580705642700195,
|
| 3 |
+
"best_model_checkpoint": "/scratch/kwamea/llama-output/checkpoint-700",
|
| 4 |
+
"epoch": 1.9023136246786634,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 740,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 9.93573264781491e-05,
|
| 14 |
+
"loss": 1.9824,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"eval_loss": 1.954728126525879,
|
| 20 |
+
"eval_runtime": 31.6803,
|
| 21 |
+
"eval_samples_per_second": 2.651,
|
| 22 |
+
"eval_steps_per_second": 0.347,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"learning_rate": 9.87146529562982e-05,
|
| 28 |
+
"loss": 1.9249,
|
| 29 |
+
"step": 10
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"eval_loss": 1.8934264183044434,
|
| 34 |
+
"eval_runtime": 31.7798,
|
| 35 |
+
"eval_samples_per_second": 2.643,
|
| 36 |
+
"eval_steps_per_second": 0.346,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04,
|
| 41 |
+
"learning_rate": 9.80719794344473e-05,
|
| 42 |
+
"loss": 1.8609,
|
| 43 |
+
"step": 15
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.04,
|
| 47 |
+
"eval_loss": 1.8421852588653564,
|
| 48 |
+
"eval_runtime": 31.7999,
|
| 49 |
+
"eval_samples_per_second": 2.642,
|
| 50 |
+
"eval_steps_per_second": 0.346,
|
| 51 |
+
"step": 15
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"learning_rate": 9.742930591259641e-05,
|
| 56 |
+
"loss": 1.8268,
|
| 57 |
+
"step": 20
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.05,
|
| 61 |
+
"eval_loss": 1.8279638290405273,
|
| 62 |
+
"eval_runtime": 31.8095,
|
| 63 |
+
"eval_samples_per_second": 2.641,
|
| 64 |
+
"eval_steps_per_second": 0.346,
|
| 65 |
+
"step": 20
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06,
|
| 69 |
+
"learning_rate": 9.67866323907455e-05,
|
| 70 |
+
"loss": 1.8349,
|
| 71 |
+
"step": 25
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.06,
|
| 75 |
+
"eval_loss": 1.813267469406128,
|
| 76 |
+
"eval_runtime": 31.8291,
|
| 77 |
+
"eval_samples_per_second": 2.639,
|
| 78 |
+
"eval_steps_per_second": 0.346,
|
| 79 |
+
"step": 25
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08,
|
| 83 |
+
"learning_rate": 9.61439588688946e-05,
|
| 84 |
+
"loss": 1.8239,
|
| 85 |
+
"step": 30
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.08,
|
| 89 |
+
"eval_loss": 1.8008779287338257,
|
| 90 |
+
"eval_runtime": 31.82,
|
| 91 |
+
"eval_samples_per_second": 2.64,
|
| 92 |
+
"eval_steps_per_second": 0.346,
|
| 93 |
+
"step": 30
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 9.550128534704372e-05,
|
| 98 |
+
"loss": 1.7177,
|
| 99 |
+
"step": 35
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.09,
|
| 103 |
+
"eval_loss": 1.789797067642212,
|
| 104 |
+
"eval_runtime": 31.8423,
|
| 105 |
+
"eval_samples_per_second": 2.638,
|
| 106 |
+
"eval_steps_per_second": 0.345,
|
| 107 |
+
"step": 35
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1,
|
| 111 |
+
"learning_rate": 9.485861182519281e-05,
|
| 112 |
+
"loss": 1.7962,
|
| 113 |
+
"step": 40
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.1,
|
| 117 |
+
"eval_loss": 1.7808287143707275,
|
| 118 |
+
"eval_runtime": 31.8387,
|
| 119 |
+
"eval_samples_per_second": 2.638,
|
| 120 |
+
"eval_steps_per_second": 0.345,
|
| 121 |
+
"step": 40
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.12,
|
| 125 |
+
"learning_rate": 9.421593830334192e-05,
|
| 126 |
+
"loss": 1.715,
|
| 127 |
+
"step": 45
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.12,
|
| 131 |
+
"eval_loss": 1.771236777305603,
|
| 132 |
+
"eval_runtime": 31.8526,
|
| 133 |
+
"eval_samples_per_second": 2.637,
|
| 134 |
+
"eval_steps_per_second": 0.345,
|
| 135 |
+
"step": 45
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13,
|
| 139 |
+
"learning_rate": 9.357326478149101e-05,
|
| 140 |
+
"loss": 1.7577,
|
| 141 |
+
"step": 50
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.13,
|
| 145 |
+
"eval_loss": 1.7619521617889404,
|
| 146 |
+
"eval_runtime": 31.828,
|
| 147 |
+
"eval_samples_per_second": 2.639,
|
| 148 |
+
"eval_steps_per_second": 0.346,
|
| 149 |
+
"step": 50
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.14,
|
| 153 |
+
"learning_rate": 9.29305912596401e-05,
|
| 154 |
+
"loss": 1.7323,
|
| 155 |
+
"step": 55
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.14,
|
| 159 |
+
"eval_loss": 1.7440986633300781,
|
| 160 |
+
"eval_runtime": 31.8301,
|
| 161 |
+
"eval_samples_per_second": 2.639,
|
| 162 |
+
"eval_steps_per_second": 0.346,
|
| 163 |
+
"step": 55
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.15,
|
| 167 |
+
"learning_rate": 9.228791773778921e-05,
|
| 168 |
+
"loss": 1.7122,
|
| 169 |
+
"step": 60
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.15,
|
| 173 |
+
"eval_loss": 1.712996006011963,
|
| 174 |
+
"eval_runtime": 31.8185,
|
| 175 |
+
"eval_samples_per_second": 2.64,
|
| 176 |
+
"eval_steps_per_second": 0.346,
|
| 177 |
+
"step": 60
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17,
|
| 181 |
+
"learning_rate": 9.16452442159383e-05,
|
| 182 |
+
"loss": 1.7042,
|
| 183 |
+
"step": 65
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.17,
|
| 187 |
+
"eval_loss": 1.7101707458496094,
|
| 188 |
+
"eval_runtime": 31.8153,
|
| 189 |
+
"eval_samples_per_second": 2.64,
|
| 190 |
+
"eval_steps_per_second": 0.346,
|
| 191 |
+
"step": 65
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.18,
|
| 195 |
+
"learning_rate": 9.100257069408741e-05,
|
| 196 |
+
"loss": 1.7242,
|
| 197 |
+
"step": 70
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.18,
|
| 201 |
+
"eval_loss": 1.7038702964782715,
|
| 202 |
+
"eval_runtime": 31.8191,
|
| 203 |
+
"eval_samples_per_second": 2.64,
|
| 204 |
+
"eval_steps_per_second": 0.346,
|
| 205 |
+
"step": 70
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19,
|
| 209 |
+
"learning_rate": 9.03598971722365e-05,
|
| 210 |
+
"loss": 1.7033,
|
| 211 |
+
"step": 75
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.19,
|
| 215 |
+
"eval_loss": 1.7004183530807495,
|
| 216 |
+
"eval_runtime": 31.811,
|
| 217 |
+
"eval_samples_per_second": 2.641,
|
| 218 |
+
"eval_steps_per_second": 0.346,
|
| 219 |
+
"step": 75
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21,
|
| 223 |
+
"learning_rate": 8.97172236503856e-05,
|
| 224 |
+
"loss": 1.6934,
|
| 225 |
+
"step": 80
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.21,
|
| 229 |
+
"eval_loss": 1.6985355615615845,
|
| 230 |
+
"eval_runtime": 31.8221,
|
| 231 |
+
"eval_samples_per_second": 2.64,
|
| 232 |
+
"eval_steps_per_second": 0.346,
|
| 233 |
+
"step": 80
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22,
|
| 237 |
+
"learning_rate": 8.907455012853471e-05,
|
| 238 |
+
"loss": 1.6443,
|
| 239 |
+
"step": 85
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.22,
|
| 243 |
+
"eval_loss": 1.696852684020996,
|
| 244 |
+
"eval_runtime": 31.8219,
|
| 245 |
+
"eval_samples_per_second": 2.64,
|
| 246 |
+
"eval_steps_per_second": 0.346,
|
| 247 |
+
"step": 85
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.23,
|
| 251 |
+
"learning_rate": 8.84318766066838e-05,
|
| 252 |
+
"loss": 1.7008,
|
| 253 |
+
"step": 90
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.23,
|
| 257 |
+
"eval_loss": 1.695594072341919,
|
| 258 |
+
"eval_runtime": 31.8205,
|
| 259 |
+
"eval_samples_per_second": 2.64,
|
| 260 |
+
"eval_steps_per_second": 0.346,
|
| 261 |
+
"step": 90
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.24,
|
| 265 |
+
"learning_rate": 8.778920308483291e-05,
|
| 266 |
+
"loss": 1.6873,
|
| 267 |
+
"step": 95
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.24,
|
| 271 |
+
"eval_loss": 1.6928850412368774,
|
| 272 |
+
"eval_runtime": 31.814,
|
| 273 |
+
"eval_samples_per_second": 2.64,
|
| 274 |
+
"eval_steps_per_second": 0.346,
|
| 275 |
+
"step": 95
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.26,
|
| 279 |
+
"learning_rate": 8.7146529562982e-05,
|
| 280 |
+
"loss": 1.6721,
|
| 281 |
+
"step": 100
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.26,
|
| 285 |
+
"eval_loss": 1.6919386386871338,
|
| 286 |
+
"eval_runtime": 31.8127,
|
| 287 |
+
"eval_samples_per_second": 2.64,
|
| 288 |
+
"eval_steps_per_second": 0.346,
|
| 289 |
+
"step": 100
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.27,
|
| 293 |
+
"learning_rate": 8.650385604113111e-05,
|
| 294 |
+
"loss": 1.6669,
|
| 295 |
+
"step": 105
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.27,
|
| 299 |
+
"eval_loss": 1.6905940771102905,
|
| 300 |
+
"eval_runtime": 31.8874,
|
| 301 |
+
"eval_samples_per_second": 2.634,
|
| 302 |
+
"eval_steps_per_second": 0.345,
|
| 303 |
+
"step": 105
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.28,
|
| 307 |
+
"learning_rate": 8.586118251928022e-05,
|
| 308 |
+
"loss": 1.7009,
|
| 309 |
+
"step": 110
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.28,
|
| 313 |
+
"eval_loss": 1.689422607421875,
|
| 314 |
+
"eval_runtime": 31.8489,
|
| 315 |
+
"eval_samples_per_second": 2.637,
|
| 316 |
+
"eval_steps_per_second": 0.345,
|
| 317 |
+
"step": 110
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.3,
|
| 321 |
+
"learning_rate": 8.521850899742931e-05,
|
| 322 |
+
"loss": 1.7151,
|
| 323 |
+
"step": 115
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.3,
|
| 327 |
+
"eval_loss": 1.688527226448059,
|
| 328 |
+
"eval_runtime": 31.8318,
|
| 329 |
+
"eval_samples_per_second": 2.639,
|
| 330 |
+
"eval_steps_per_second": 0.346,
|
| 331 |
+
"step": 115
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.31,
|
| 335 |
+
"learning_rate": 8.457583547557842e-05,
|
| 336 |
+
"loss": 1.7165,
|
| 337 |
+
"step": 120
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.31,
|
| 341 |
+
"eval_loss": 1.686748743057251,
|
| 342 |
+
"eval_runtime": 31.835,
|
| 343 |
+
"eval_samples_per_second": 2.639,
|
| 344 |
+
"eval_steps_per_second": 0.346,
|
| 345 |
+
"step": 120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.32,
|
| 349 |
+
"learning_rate": 8.393316195372751e-05,
|
| 350 |
+
"loss": 1.7015,
|
| 351 |
+
"step": 125
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.32,
|
| 355 |
+
"eval_loss": 1.6855812072753906,
|
| 356 |
+
"eval_runtime": 31.8269,
|
| 357 |
+
"eval_samples_per_second": 2.639,
|
| 358 |
+
"eval_steps_per_second": 0.346,
|
| 359 |
+
"step": 125
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.33,
|
| 363 |
+
"learning_rate": 8.32904884318766e-05,
|
| 364 |
+
"loss": 1.6818,
|
| 365 |
+
"step": 130
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.33,
|
| 369 |
+
"eval_loss": 1.6846078634262085,
|
| 370 |
+
"eval_runtime": 31.8617,
|
| 371 |
+
"eval_samples_per_second": 2.636,
|
| 372 |
+
"eval_steps_per_second": 0.345,
|
| 373 |
+
"step": 130
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.35,
|
| 377 |
+
"learning_rate": 8.264781491002571e-05,
|
| 378 |
+
"loss": 1.7151,
|
| 379 |
+
"step": 135
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.35,
|
| 383 |
+
"eval_loss": 1.6845166683197021,
|
| 384 |
+
"eval_runtime": 31.8631,
|
| 385 |
+
"eval_samples_per_second": 2.636,
|
| 386 |
+
"eval_steps_per_second": 0.345,
|
| 387 |
+
"step": 135
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.36,
|
| 391 |
+
"learning_rate": 8.200514138817481e-05,
|
| 392 |
+
"loss": 1.6667,
|
| 393 |
+
"step": 140
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.36,
|
| 397 |
+
"eval_loss": 1.6832246780395508,
|
| 398 |
+
"eval_runtime": 31.8276,
|
| 399 |
+
"eval_samples_per_second": 2.639,
|
| 400 |
+
"eval_steps_per_second": 0.346,
|
| 401 |
+
"step": 140
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.37,
|
| 405 |
+
"learning_rate": 8.136246786632391e-05,
|
| 406 |
+
"loss": 1.6586,
|
| 407 |
+
"step": 145
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.37,
|
| 411 |
+
"eval_loss": 1.6824573278427124,
|
| 412 |
+
"eval_runtime": 31.8115,
|
| 413 |
+
"eval_samples_per_second": 2.641,
|
| 414 |
+
"eval_steps_per_second": 0.346,
|
| 415 |
+
"step": 145
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.39,
|
| 419 |
+
"learning_rate": 8.071979434447301e-05,
|
| 420 |
+
"loss": 1.6999,
|
| 421 |
+
"step": 150
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.39,
|
| 425 |
+
"eval_loss": 1.681317687034607,
|
| 426 |
+
"eval_runtime": 31.805,
|
| 427 |
+
"eval_samples_per_second": 2.641,
|
| 428 |
+
"eval_steps_per_second": 0.346,
|
| 429 |
+
"step": 150
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4,
|
| 433 |
+
"learning_rate": 8.007712082262212e-05,
|
| 434 |
+
"loss": 1.6894,
|
| 435 |
+
"step": 155
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.4,
|
| 439 |
+
"eval_loss": 1.6812355518341064,
|
| 440 |
+
"eval_runtime": 31.8039,
|
| 441 |
+
"eval_samples_per_second": 2.641,
|
| 442 |
+
"eval_steps_per_second": 0.346,
|
| 443 |
+
"step": 155
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.41,
|
| 447 |
+
"learning_rate": 7.943444730077121e-05,
|
| 448 |
+
"loss": 1.6669,
|
| 449 |
+
"step": 160
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.41,
|
| 453 |
+
"eval_loss": 1.679802656173706,
|
| 454 |
+
"eval_runtime": 31.8021,
|
| 455 |
+
"eval_samples_per_second": 2.641,
|
| 456 |
+
"eval_steps_per_second": 0.346,
|
| 457 |
+
"step": 160
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.42,
|
| 461 |
+
"learning_rate": 7.87917737789203e-05,
|
| 462 |
+
"loss": 1.6481,
|
| 463 |
+
"step": 165
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.42,
|
| 467 |
+
"eval_loss": 1.679994821548462,
|
| 468 |
+
"eval_runtime": 31.8201,
|
| 469 |
+
"eval_samples_per_second": 2.64,
|
| 470 |
+
"eval_steps_per_second": 0.346,
|
| 471 |
+
"step": 165
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.44,
|
| 475 |
+
"learning_rate": 7.814910025706941e-05,
|
| 476 |
+
"loss": 1.7042,
|
| 477 |
+
"step": 170
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.44,
|
| 481 |
+
"eval_loss": 1.6786224842071533,
|
| 482 |
+
"eval_runtime": 31.8184,
|
| 483 |
+
"eval_samples_per_second": 2.64,
|
| 484 |
+
"eval_steps_per_second": 0.346,
|
| 485 |
+
"step": 170
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.45,
|
| 489 |
+
"learning_rate": 7.750642673521852e-05,
|
| 490 |
+
"loss": 1.6564,
|
| 491 |
+
"step": 175
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.45,
|
| 495 |
+
"eval_loss": 1.6783201694488525,
|
| 496 |
+
"eval_runtime": 31.8137,
|
| 497 |
+
"eval_samples_per_second": 2.64,
|
| 498 |
+
"eval_steps_per_second": 0.346,
|
| 499 |
+
"step": 175
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.46,
|
| 503 |
+
"learning_rate": 7.686375321336761e-05,
|
| 504 |
+
"loss": 1.6714,
|
| 505 |
+
"step": 180
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.46,
|
| 509 |
+
"eval_loss": 1.677714228630066,
|
| 510 |
+
"eval_runtime": 31.804,
|
| 511 |
+
"eval_samples_per_second": 2.641,
|
| 512 |
+
"eval_steps_per_second": 0.346,
|
| 513 |
+
"step": 180
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.48,
|
| 517 |
+
"learning_rate": 7.622107969151672e-05,
|
| 518 |
+
"loss": 1.6705,
|
| 519 |
+
"step": 185
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.48,
|
| 523 |
+
"eval_loss": 1.6772773265838623,
|
| 524 |
+
"eval_runtime": 31.8077,
|
| 525 |
+
"eval_samples_per_second": 2.641,
|
| 526 |
+
"eval_steps_per_second": 0.346,
|
| 527 |
+
"step": 185
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.49,
|
| 531 |
+
"learning_rate": 7.557840616966581e-05,
|
| 532 |
+
"loss": 1.6624,
|
| 533 |
+
"step": 190
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.49,
|
| 537 |
+
"eval_loss": 1.6766114234924316,
|
| 538 |
+
"eval_runtime": 31.8164,
|
| 539 |
+
"eval_samples_per_second": 2.64,
|
| 540 |
+
"eval_steps_per_second": 0.346,
|
| 541 |
+
"step": 190
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.5,
|
| 545 |
+
"learning_rate": 7.493573264781492e-05,
|
| 546 |
+
"loss": 1.6415,
|
| 547 |
+
"step": 195
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.5,
|
| 551 |
+
"eval_loss": 1.675940752029419,
|
| 552 |
+
"eval_runtime": 31.8124,
|
| 553 |
+
"eval_samples_per_second": 2.64,
|
| 554 |
+
"eval_steps_per_second": 0.346,
|
| 555 |
+
"step": 195
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.51,
|
| 559 |
+
"learning_rate": 7.429305912596401e-05,
|
| 560 |
+
"loss": 1.6633,
|
| 561 |
+
"step": 200
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.51,
|
| 565 |
+
"eval_loss": 1.6751865148544312,
|
| 566 |
+
"eval_runtime": 31.8123,
|
| 567 |
+
"eval_samples_per_second": 2.64,
|
| 568 |
+
"eval_steps_per_second": 0.346,
|
| 569 |
+
"step": 200
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.53,
|
| 573 |
+
"learning_rate": 7.365038560411311e-05,
|
| 574 |
+
"loss": 1.6142,
|
| 575 |
+
"step": 205
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.53,
|
| 579 |
+
"eval_loss": 1.6750575304031372,
|
| 580 |
+
"eval_runtime": 31.8049,
|
| 581 |
+
"eval_samples_per_second": 2.641,
|
| 582 |
+
"eval_steps_per_second": 0.346,
|
| 583 |
+
"step": 205
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.54,
|
| 587 |
+
"learning_rate": 7.300771208226222e-05,
|
| 588 |
+
"loss": 1.6736,
|
| 589 |
+
"step": 210
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.54,
|
| 593 |
+
"eval_loss": 1.6746423244476318,
|
| 594 |
+
"eval_runtime": 31.8111,
|
| 595 |
+
"eval_samples_per_second": 2.641,
|
| 596 |
+
"eval_steps_per_second": 0.346,
|
| 597 |
+
"step": 210
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.55,
|
| 601 |
+
"learning_rate": 7.236503856041131e-05,
|
| 602 |
+
"loss": 1.6414,
|
| 603 |
+
"step": 215
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.55,
|
| 607 |
+
"eval_loss": 1.6740491390228271,
|
| 608 |
+
"eval_runtime": 31.8083,
|
| 609 |
+
"eval_samples_per_second": 2.641,
|
| 610 |
+
"eval_steps_per_second": 0.346,
|
| 611 |
+
"step": 215
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.57,
|
| 615 |
+
"learning_rate": 7.172236503856042e-05,
|
| 616 |
+
"loss": 1.6725,
|
| 617 |
+
"step": 220
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.57,
|
| 621 |
+
"eval_loss": 1.673694372177124,
|
| 622 |
+
"eval_runtime": 31.8025,
|
| 623 |
+
"eval_samples_per_second": 2.641,
|
| 624 |
+
"eval_steps_per_second": 0.346,
|
| 625 |
+
"step": 220
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.58,
|
| 629 |
+
"learning_rate": 7.107969151670951e-05,
|
| 630 |
+
"loss": 1.679,
|
| 631 |
+
"step": 225
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.58,
|
| 635 |
+
"eval_loss": 1.6733818054199219,
|
| 636 |
+
"eval_runtime": 31.8077,
|
| 637 |
+
"eval_samples_per_second": 2.641,
|
| 638 |
+
"eval_steps_per_second": 0.346,
|
| 639 |
+
"step": 225
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.59,
|
| 643 |
+
"learning_rate": 7.043701799485862e-05,
|
| 644 |
+
"loss": 1.7204,
|
| 645 |
+
"step": 230
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.59,
|
| 649 |
+
"eval_loss": 1.6725033521652222,
|
| 650 |
+
"eval_runtime": 31.8079,
|
| 651 |
+
"eval_samples_per_second": 2.641,
|
| 652 |
+
"eval_steps_per_second": 0.346,
|
| 653 |
+
"step": 230
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.6,
|
| 657 |
+
"learning_rate": 6.979434447300771e-05,
|
| 658 |
+
"loss": 1.6816,
|
| 659 |
+
"step": 235
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.6,
|
| 663 |
+
"eval_loss": 1.67205011844635,
|
| 664 |
+
"eval_runtime": 31.809,
|
| 665 |
+
"eval_samples_per_second": 2.641,
|
| 666 |
+
"eval_steps_per_second": 0.346,
|
| 667 |
+
"step": 235
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.62,
|
| 671 |
+
"learning_rate": 6.91516709511568e-05,
|
| 672 |
+
"loss": 1.634,
|
| 673 |
+
"step": 240
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.62,
|
| 677 |
+
"eval_loss": 1.6717994213104248,
|
| 678 |
+
"eval_runtime": 31.8075,
|
| 679 |
+
"eval_samples_per_second": 2.641,
|
| 680 |
+
"eval_steps_per_second": 0.346,
|
| 681 |
+
"step": 240
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.63,
|
| 685 |
+
"learning_rate": 6.850899742930593e-05,
|
| 686 |
+
"loss": 1.6761,
|
| 687 |
+
"step": 245
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.63,
|
| 691 |
+
"eval_loss": 1.6714757680892944,
|
| 692 |
+
"eval_runtime": 31.8052,
|
| 693 |
+
"eval_samples_per_second": 2.641,
|
| 694 |
+
"eval_steps_per_second": 0.346,
|
| 695 |
+
"step": 245
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.64,
|
| 699 |
+
"learning_rate": 6.786632390745502e-05,
|
| 700 |
+
"loss": 1.6996,
|
| 701 |
+
"step": 250
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.64,
|
| 705 |
+
"eval_loss": 1.671559453010559,
|
| 706 |
+
"eval_runtime": 31.8089,
|
| 707 |
+
"eval_samples_per_second": 2.641,
|
| 708 |
+
"eval_steps_per_second": 0.346,
|
| 709 |
+
"step": 250
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.66,
|
| 713 |
+
"learning_rate": 6.722365038560411e-05,
|
| 714 |
+
"loss": 1.6302,
|
| 715 |
+
"step": 255
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.66,
|
| 719 |
+
"eval_loss": 1.6711652278900146,
|
| 720 |
+
"eval_runtime": 31.8105,
|
| 721 |
+
"eval_samples_per_second": 2.641,
|
| 722 |
+
"eval_steps_per_second": 0.346,
|
| 723 |
+
"step": 255
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.67,
|
| 727 |
+
"learning_rate": 6.658097686375322e-05,
|
| 728 |
+
"loss": 1.6611,
|
| 729 |
+
"step": 260
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.67,
|
| 733 |
+
"eval_loss": 1.6704061031341553,
|
| 734 |
+
"eval_runtime": 31.8135,
|
| 735 |
+
"eval_samples_per_second": 2.64,
|
| 736 |
+
"eval_steps_per_second": 0.346,
|
| 737 |
+
"step": 260
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.68,
|
| 741 |
+
"learning_rate": 6.593830334190231e-05,
|
| 742 |
+
"loss": 1.6586,
|
| 743 |
+
"step": 265
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.68,
|
| 747 |
+
"eval_loss": 1.6705658435821533,
|
| 748 |
+
"eval_runtime": 31.7998,
|
| 749 |
+
"eval_samples_per_second": 2.642,
|
| 750 |
+
"eval_steps_per_second": 0.346,
|
| 751 |
+
"step": 265
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.69,
|
| 755 |
+
"learning_rate": 6.529562982005142e-05,
|
| 756 |
+
"loss": 1.6838,
|
| 757 |
+
"step": 270
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.69,
|
| 761 |
+
"eval_loss": 1.6697953939437866,
|
| 762 |
+
"eval_runtime": 31.7994,
|
| 763 |
+
"eval_samples_per_second": 2.642,
|
| 764 |
+
"eval_steps_per_second": 0.346,
|
| 765 |
+
"step": 270
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.71,
|
| 769 |
+
"learning_rate": 6.465295629820052e-05,
|
| 770 |
+
"loss": 1.6499,
|
| 771 |
+
"step": 275
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.71,
|
| 775 |
+
"eval_loss": 1.669343113899231,
|
| 776 |
+
"eval_runtime": 31.8147,
|
| 777 |
+
"eval_samples_per_second": 2.64,
|
| 778 |
+
"eval_steps_per_second": 0.346,
|
| 779 |
+
"step": 275
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.72,
|
| 783 |
+
"learning_rate": 6.401028277634962e-05,
|
| 784 |
+
"loss": 1.6424,
|
| 785 |
+
"step": 280
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.72,
|
| 789 |
+
"eval_loss": 1.6693596839904785,
|
| 790 |
+
"eval_runtime": 31.8155,
|
| 791 |
+
"eval_samples_per_second": 2.64,
|
| 792 |
+
"eval_steps_per_second": 0.346,
|
| 793 |
+
"step": 280
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.73,
|
| 797 |
+
"learning_rate": 6.336760925449872e-05,
|
| 798 |
+
"loss": 1.6238,
|
| 799 |
+
"step": 285
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.73,
|
| 803 |
+
"eval_loss": 1.669128179550171,
|
| 804 |
+
"eval_runtime": 31.8219,
|
| 805 |
+
"eval_samples_per_second": 2.64,
|
| 806 |
+
"eval_steps_per_second": 0.346,
|
| 807 |
+
"step": 285
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.75,
|
| 811 |
+
"learning_rate": 6.272493573264781e-05,
|
| 812 |
+
"loss": 1.6538,
|
| 813 |
+
"step": 290
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.75,
|
| 817 |
+
"eval_loss": 1.6691263914108276,
|
| 818 |
+
"eval_runtime": 31.81,
|
| 819 |
+
"eval_samples_per_second": 2.641,
|
| 820 |
+
"eval_steps_per_second": 0.346,
|
| 821 |
+
"step": 290
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.76,
|
| 825 |
+
"learning_rate": 6.208226221079692e-05,
|
| 826 |
+
"loss": 1.656,
|
| 827 |
+
"step": 295
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.76,
|
| 831 |
+
"eval_loss": 1.66847825050354,
|
| 832 |
+
"eval_runtime": 31.7918,
|
| 833 |
+
"eval_samples_per_second": 2.642,
|
| 834 |
+
"eval_steps_per_second": 0.346,
|
| 835 |
+
"step": 295
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.77,
|
| 839 |
+
"learning_rate": 6.143958868894601e-05,
|
| 840 |
+
"loss": 1.6407,
|
| 841 |
+
"step": 300
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.77,
|
| 845 |
+
"eval_loss": 1.6683858633041382,
|
| 846 |
+
"eval_runtime": 31.8114,
|
| 847 |
+
"eval_samples_per_second": 2.641,
|
| 848 |
+
"eval_steps_per_second": 0.346,
|
| 849 |
+
"step": 300
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.78,
|
| 853 |
+
"learning_rate": 6.079691516709511e-05,
|
| 854 |
+
"loss": 1.6468,
|
| 855 |
+
"step": 305
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.78,
|
| 859 |
+
"eval_loss": 1.6678352355957031,
|
| 860 |
+
"eval_runtime": 31.7975,
|
| 861 |
+
"eval_samples_per_second": 2.642,
|
| 862 |
+
"eval_steps_per_second": 0.346,
|
| 863 |
+
"step": 305
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.8,
|
| 867 |
+
"learning_rate": 6.015424164524421e-05,
|
| 868 |
+
"loss": 1.6579,
|
| 869 |
+
"step": 310
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.8,
|
| 873 |
+
"eval_loss": 1.6675294637680054,
|
| 874 |
+
"eval_runtime": 31.8059,
|
| 875 |
+
"eval_samples_per_second": 2.641,
|
| 876 |
+
"eval_steps_per_second": 0.346,
|
| 877 |
+
"step": 310
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.81,
|
| 881 |
+
"learning_rate": 5.951156812339333e-05,
|
| 882 |
+
"loss": 1.6331,
|
| 883 |
+
"step": 315
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.81,
|
| 887 |
+
"eval_loss": 1.6670397520065308,
|
| 888 |
+
"eval_runtime": 31.7994,
|
| 889 |
+
"eval_samples_per_second": 2.642,
|
| 890 |
+
"eval_steps_per_second": 0.346,
|
| 891 |
+
"step": 315
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.82,
|
| 895 |
+
"learning_rate": 5.886889460154242e-05,
|
| 896 |
+
"loss": 1.6634,
|
| 897 |
+
"step": 320
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.82,
|
| 901 |
+
"eval_loss": 1.6668330430984497,
|
| 902 |
+
"eval_runtime": 31.807,
|
| 903 |
+
"eval_samples_per_second": 2.641,
|
| 904 |
+
"eval_steps_per_second": 0.346,
|
| 905 |
+
"step": 320
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.84,
|
| 909 |
+
"learning_rate": 5.822622107969152e-05,
|
| 910 |
+
"loss": 1.6406,
|
| 911 |
+
"step": 325
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.84,
|
| 915 |
+
"eval_loss": 1.6668546199798584,
|
| 916 |
+
"eval_runtime": 31.8004,
|
| 917 |
+
"eval_samples_per_second": 2.641,
|
| 918 |
+
"eval_steps_per_second": 0.346,
|
| 919 |
+
"step": 325
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.85,
|
| 923 |
+
"learning_rate": 5.758354755784062e-05,
|
| 924 |
+
"loss": 1.6614,
|
| 925 |
+
"step": 330
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.85,
|
| 929 |
+
"eval_loss": 1.666812539100647,
|
| 930 |
+
"eval_runtime": 31.8023,
|
| 931 |
+
"eval_samples_per_second": 2.641,
|
| 932 |
+
"eval_steps_per_second": 0.346,
|
| 933 |
+
"step": 330
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.86,
|
| 937 |
+
"learning_rate": 5.694087403598972e-05,
|
| 938 |
+
"loss": 1.6598,
|
| 939 |
+
"step": 335
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.86,
|
| 943 |
+
"eval_loss": 1.666398048400879,
|
| 944 |
+
"eval_runtime": 31.8087,
|
| 945 |
+
"eval_samples_per_second": 2.641,
|
| 946 |
+
"eval_steps_per_second": 0.346,
|
| 947 |
+
"step": 335
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.87,
|
| 951 |
+
"learning_rate": 5.6298200514138824e-05,
|
| 952 |
+
"loss": 1.6698,
|
| 953 |
+
"step": 340
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.87,
|
| 957 |
+
"eval_loss": 1.6660391092300415,
|
| 958 |
+
"eval_runtime": 31.8016,
|
| 959 |
+
"eval_samples_per_second": 2.641,
|
| 960 |
+
"eval_steps_per_second": 0.346,
|
| 961 |
+
"step": 340
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.89,
|
| 965 |
+
"learning_rate": 5.5655526992287924e-05,
|
| 966 |
+
"loss": 1.6346,
|
| 967 |
+
"step": 345
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.89,
|
| 971 |
+
"eval_loss": 1.665901780128479,
|
| 972 |
+
"eval_runtime": 31.7878,
|
| 973 |
+
"eval_samples_per_second": 2.643,
|
| 974 |
+
"eval_steps_per_second": 0.346,
|
| 975 |
+
"step": 345
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.9,
|
| 979 |
+
"learning_rate": 5.501285347043702e-05,
|
| 980 |
+
"loss": 1.6617,
|
| 981 |
+
"step": 350
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.9,
|
| 985 |
+
"eval_loss": 1.666027307510376,
|
| 986 |
+
"eval_runtime": 31.7999,
|
| 987 |
+
"eval_samples_per_second": 2.642,
|
| 988 |
+
"eval_steps_per_second": 0.346,
|
| 989 |
+
"step": 350
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.91,
|
| 993 |
+
"learning_rate": 5.437017994858612e-05,
|
| 994 |
+
"loss": 1.6623,
|
| 995 |
+
"step": 355
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.91,
|
| 999 |
+
"eval_loss": 1.6658612489700317,
|
| 1000 |
+
"eval_runtime": 31.8128,
|
| 1001 |
+
"eval_samples_per_second": 2.64,
|
| 1002 |
+
"eval_steps_per_second": 0.346,
|
| 1003 |
+
"step": 355
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.93,
|
| 1007 |
+
"learning_rate": 5.372750642673522e-05,
|
| 1008 |
+
"loss": 1.6737,
|
| 1009 |
+
"step": 360
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.93,
|
| 1013 |
+
"eval_loss": 1.6656837463378906,
|
| 1014 |
+
"eval_runtime": 31.8094,
|
| 1015 |
+
"eval_samples_per_second": 2.641,
|
| 1016 |
+
"eval_steps_per_second": 0.346,
|
| 1017 |
+
"step": 360
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.94,
|
| 1021 |
+
"learning_rate": 5.308483290488432e-05,
|
| 1022 |
+
"loss": 1.6981,
|
| 1023 |
+
"step": 365
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.94,
|
| 1027 |
+
"eval_loss": 1.6653661727905273,
|
| 1028 |
+
"eval_runtime": 31.8031,
|
| 1029 |
+
"eval_samples_per_second": 2.641,
|
| 1030 |
+
"eval_steps_per_second": 0.346,
|
| 1031 |
+
"step": 365
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.95,
|
| 1035 |
+
"learning_rate": 5.244215938303342e-05,
|
| 1036 |
+
"loss": 1.6832,
|
| 1037 |
+
"step": 370
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.95,
|
| 1041 |
+
"eval_loss": 1.6652257442474365,
|
| 1042 |
+
"eval_runtime": 31.8077,
|
| 1043 |
+
"eval_samples_per_second": 2.641,
|
| 1044 |
+
"eval_steps_per_second": 0.346,
|
| 1045 |
+
"step": 370
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.96,
|
| 1049 |
+
"learning_rate": 5.1799485861182514e-05,
|
| 1050 |
+
"loss": 1.6925,
|
| 1051 |
+
"step": 375
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.96,
|
| 1055 |
+
"eval_loss": 1.664839267730713,
|
| 1056 |
+
"eval_runtime": 31.8082,
|
| 1057 |
+
"eval_samples_per_second": 2.641,
|
| 1058 |
+
"eval_steps_per_second": 0.346,
|
| 1059 |
+
"step": 375
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.98,
|
| 1063 |
+
"learning_rate": 5.1156812339331615e-05,
|
| 1064 |
+
"loss": 1.6721,
|
| 1065 |
+
"step": 380
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.98,
|
| 1069 |
+
"eval_loss": 1.6642415523529053,
|
| 1070 |
+
"eval_runtime": 31.7927,
|
| 1071 |
+
"eval_samples_per_second": 2.642,
|
| 1072 |
+
"eval_steps_per_second": 0.346,
|
| 1073 |
+
"step": 380
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.99,
|
| 1077 |
+
"learning_rate": 5.051413881748073e-05,
|
| 1078 |
+
"loss": 1.6208,
|
| 1079 |
+
"step": 385
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.99,
|
| 1083 |
+
"eval_loss": 1.6641273498535156,
|
| 1084 |
+
"eval_runtime": 31.8006,
|
| 1085 |
+
"eval_samples_per_second": 2.641,
|
| 1086 |
+
"eval_steps_per_second": 0.346,
|
| 1087 |
+
"step": 385
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.0,
|
| 1091 |
+
"learning_rate": 4.987146529562982e-05,
|
| 1092 |
+
"loss": 1.6519,
|
| 1093 |
+
"step": 390
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.0,
|
| 1097 |
+
"eval_loss": 1.6645455360412598,
|
| 1098 |
+
"eval_runtime": 31.8026,
|
| 1099 |
+
"eval_samples_per_second": 2.641,
|
| 1100 |
+
"eval_steps_per_second": 0.346,
|
| 1101 |
+
"step": 390
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.02,
|
| 1105 |
+
"learning_rate": 4.922879177377892e-05,
|
| 1106 |
+
"loss": 1.6581,
|
| 1107 |
+
"step": 395
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.02,
|
| 1111 |
+
"eval_loss": 1.6641591787338257,
|
| 1112 |
+
"eval_runtime": 31.8025,
|
| 1113 |
+
"eval_samples_per_second": 2.641,
|
| 1114 |
+
"eval_steps_per_second": 0.346,
|
| 1115 |
+
"step": 395
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.03,
|
| 1119 |
+
"learning_rate": 4.8586118251928024e-05,
|
| 1120 |
+
"loss": 1.6768,
|
| 1121 |
+
"step": 400
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.03,
|
| 1125 |
+
"eval_loss": 1.6637850999832153,
|
| 1126 |
+
"eval_runtime": 31.806,
|
| 1127 |
+
"eval_samples_per_second": 2.641,
|
| 1128 |
+
"eval_steps_per_second": 0.346,
|
| 1129 |
+
"step": 400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.04,
|
| 1133 |
+
"learning_rate": 4.7943444730077124e-05,
|
| 1134 |
+
"loss": 1.6257,
|
| 1135 |
+
"step": 405
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 1.04,
|
| 1139 |
+
"eval_loss": 1.6636526584625244,
|
| 1140 |
+
"eval_runtime": 31.8116,
|
| 1141 |
+
"eval_samples_per_second": 2.641,
|
| 1142 |
+
"eval_steps_per_second": 0.346,
|
| 1143 |
+
"step": 405
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.05,
|
| 1147 |
+
"learning_rate": 4.7300771208226225e-05,
|
| 1148 |
+
"loss": 1.6522,
|
| 1149 |
+
"step": 410
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.05,
|
| 1153 |
+
"eval_loss": 1.6634690761566162,
|
| 1154 |
+
"eval_runtime": 31.8063,
|
| 1155 |
+
"eval_samples_per_second": 2.641,
|
| 1156 |
+
"eval_steps_per_second": 0.346,
|
| 1157 |
+
"step": 410
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.07,
|
| 1161 |
+
"learning_rate": 4.6658097686375325e-05,
|
| 1162 |
+
"loss": 1.615,
|
| 1163 |
+
"step": 415
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 1.07,
|
| 1167 |
+
"eval_loss": 1.6637413501739502,
|
| 1168 |
+
"eval_runtime": 31.8115,
|
| 1169 |
+
"eval_samples_per_second": 2.641,
|
| 1170 |
+
"eval_steps_per_second": 0.346,
|
| 1171 |
+
"step": 415
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.08,
|
| 1175 |
+
"learning_rate": 4.6015424164524426e-05,
|
| 1176 |
+
"loss": 1.5967,
|
| 1177 |
+
"step": 420
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.08,
|
| 1181 |
+
"eval_loss": 1.6633188724517822,
|
| 1182 |
+
"eval_runtime": 31.8016,
|
| 1183 |
+
"eval_samples_per_second": 2.641,
|
| 1184 |
+
"eval_steps_per_second": 0.346,
|
| 1185 |
+
"step": 420
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.09,
|
| 1189 |
+
"learning_rate": 4.537275064267352e-05,
|
| 1190 |
+
"loss": 1.6708,
|
| 1191 |
+
"step": 425
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.09,
|
| 1195 |
+
"eval_loss": 1.6634286642074585,
|
| 1196 |
+
"eval_runtime": 31.8074,
|
| 1197 |
+
"eval_samples_per_second": 2.641,
|
| 1198 |
+
"eval_steps_per_second": 0.346,
|
| 1199 |
+
"step": 425
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.11,
|
| 1203 |
+
"learning_rate": 4.473007712082262e-05,
|
| 1204 |
+
"loss": 1.6696,
|
| 1205 |
+
"step": 430
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.11,
|
| 1209 |
+
"eval_loss": 1.663163661956787,
|
| 1210 |
+
"eval_runtime": 31.799,
|
| 1211 |
+
"eval_samples_per_second": 2.642,
|
| 1212 |
+
"eval_steps_per_second": 0.346,
|
| 1213 |
+
"step": 430
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.12,
|
| 1217 |
+
"learning_rate": 4.408740359897173e-05,
|
| 1218 |
+
"loss": 1.6344,
|
| 1219 |
+
"step": 435
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.12,
|
| 1223 |
+
"eval_loss": 1.6632493734359741,
|
| 1224 |
+
"eval_runtime": 31.8032,
|
| 1225 |
+
"eval_samples_per_second": 2.641,
|
| 1226 |
+
"eval_steps_per_second": 0.346,
|
| 1227 |
+
"step": 435
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.13,
|
| 1231 |
+
"learning_rate": 4.344473007712083e-05,
|
| 1232 |
+
"loss": 1.5922,
|
| 1233 |
+
"step": 440
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.13,
|
| 1237 |
+
"eval_loss": 1.6627737283706665,
|
| 1238 |
+
"eval_runtime": 31.8064,
|
| 1239 |
+
"eval_samples_per_second": 2.641,
|
| 1240 |
+
"eval_steps_per_second": 0.346,
|
| 1241 |
+
"step": 440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.14,
|
| 1245 |
+
"learning_rate": 4.280205655526993e-05,
|
| 1246 |
+
"loss": 1.6541,
|
| 1247 |
+
"step": 445
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.14,
|
| 1251 |
+
"eval_loss": 1.6630815267562866,
|
| 1252 |
+
"eval_runtime": 31.8083,
|
| 1253 |
+
"eval_samples_per_second": 2.641,
|
| 1254 |
+
"eval_steps_per_second": 0.346,
|
| 1255 |
+
"step": 445
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.16,
|
| 1259 |
+
"learning_rate": 4.215938303341902e-05,
|
| 1260 |
+
"loss": 1.6348,
|
| 1261 |
+
"step": 450
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.16,
|
| 1265 |
+
"eval_loss": 1.662713885307312,
|
| 1266 |
+
"eval_runtime": 31.7977,
|
| 1267 |
+
"eval_samples_per_second": 2.642,
|
| 1268 |
+
"eval_steps_per_second": 0.346,
|
| 1269 |
+
"step": 450
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.17,
|
| 1273 |
+
"learning_rate": 4.151670951156812e-05,
|
| 1274 |
+
"loss": 1.6444,
|
| 1275 |
+
"step": 455
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.17,
|
| 1279 |
+
"eval_loss": 1.6629937887191772,
|
| 1280 |
+
"eval_runtime": 31.799,
|
| 1281 |
+
"eval_samples_per_second": 2.642,
|
| 1282 |
+
"eval_steps_per_second": 0.346,
|
| 1283 |
+
"step": 455
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.18,
|
| 1287 |
+
"learning_rate": 4.0874035989717224e-05,
|
| 1288 |
+
"loss": 1.6629,
|
| 1289 |
+
"step": 460
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 1.18,
|
| 1293 |
+
"eval_loss": 1.6626592874526978,
|
| 1294 |
+
"eval_runtime": 31.8136,
|
| 1295 |
+
"eval_samples_per_second": 2.64,
|
| 1296 |
+
"eval_steps_per_second": 0.346,
|
| 1297 |
+
"step": 460
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.2,
|
| 1301 |
+
"learning_rate": 4.0231362467866324e-05,
|
| 1302 |
+
"loss": 1.6327,
|
| 1303 |
+
"step": 465
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 1.2,
|
| 1307 |
+
"eval_loss": 1.6625391244888306,
|
| 1308 |
+
"eval_runtime": 31.802,
|
| 1309 |
+
"eval_samples_per_second": 2.641,
|
| 1310 |
+
"eval_steps_per_second": 0.346,
|
| 1311 |
+
"step": 465
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.21,
|
| 1315 |
+
"learning_rate": 3.958868894601543e-05,
|
| 1316 |
+
"loss": 1.6236,
|
| 1317 |
+
"step": 470
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 1.21,
|
| 1321 |
+
"eval_loss": 1.6622934341430664,
|
| 1322 |
+
"eval_runtime": 31.8055,
|
| 1323 |
+
"eval_samples_per_second": 2.641,
|
| 1324 |
+
"eval_steps_per_second": 0.346,
|
| 1325 |
+
"step": 470
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.22,
|
| 1329 |
+
"learning_rate": 3.8946015424164526e-05,
|
| 1330 |
+
"loss": 1.6232,
|
| 1331 |
+
"step": 475
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 1.22,
|
| 1335 |
+
"eval_loss": 1.661791443824768,
|
| 1336 |
+
"eval_runtime": 31.8035,
|
| 1337 |
+
"eval_samples_per_second": 2.641,
|
| 1338 |
+
"eval_steps_per_second": 0.346,
|
| 1339 |
+
"step": 475
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.23,
|
| 1343 |
+
"learning_rate": 3.8303341902313626e-05,
|
| 1344 |
+
"loss": 1.6374,
|
| 1345 |
+
"step": 480
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 1.23,
|
| 1349 |
+
"eval_loss": 1.6618887186050415,
|
| 1350 |
+
"eval_runtime": 31.7892,
|
| 1351 |
+
"eval_samples_per_second": 2.642,
|
| 1352 |
+
"eval_steps_per_second": 0.346,
|
| 1353 |
+
"step": 480
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.25,
|
| 1357 |
+
"learning_rate": 3.766066838046273e-05,
|
| 1358 |
+
"loss": 1.6422,
|
| 1359 |
+
"step": 485
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 1.25,
|
| 1363 |
+
"eval_loss": 1.6620476245880127,
|
| 1364 |
+
"eval_runtime": 31.7974,
|
| 1365 |
+
"eval_samples_per_second": 2.642,
|
| 1366 |
+
"eval_steps_per_second": 0.346,
|
| 1367 |
+
"step": 485
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.26,
|
| 1371 |
+
"learning_rate": 3.701799485861183e-05,
|
| 1372 |
+
"loss": 1.631,
|
| 1373 |
+
"step": 490
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 1.26,
|
| 1377 |
+
"eval_loss": 1.6622774600982666,
|
| 1378 |
+
"eval_runtime": 31.7978,
|
| 1379 |
+
"eval_samples_per_second": 2.642,
|
| 1380 |
+
"eval_steps_per_second": 0.346,
|
| 1381 |
+
"step": 490
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.27,
|
| 1385 |
+
"learning_rate": 3.637532133676093e-05,
|
| 1386 |
+
"loss": 1.609,
|
| 1387 |
+
"step": 495
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 1.27,
|
| 1391 |
+
"eval_loss": 1.661568284034729,
|
| 1392 |
+
"eval_runtime": 31.8034,
|
| 1393 |
+
"eval_samples_per_second": 2.641,
|
| 1394 |
+
"eval_steps_per_second": 0.346,
|
| 1395 |
+
"step": 495
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.29,
|
| 1399 |
+
"learning_rate": 3.573264781491003e-05,
|
| 1400 |
+
"loss": 1.6444,
|
| 1401 |
+
"step": 500
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 1.29,
|
| 1405 |
+
"eval_loss": 1.6610949039459229,
|
| 1406 |
+
"eval_runtime": 31.8005,
|
| 1407 |
+
"eval_samples_per_second": 2.641,
|
| 1408 |
+
"eval_steps_per_second": 0.346,
|
| 1409 |
+
"step": 500
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.3,
|
| 1413 |
+
"learning_rate": 3.508997429305913e-05,
|
| 1414 |
+
"loss": 1.6387,
|
| 1415 |
+
"step": 505
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 1.3,
|
| 1419 |
+
"eval_loss": 1.6611486673355103,
|
| 1420 |
+
"eval_runtime": 31.8079,
|
| 1421 |
+
"eval_samples_per_second": 2.641,
|
| 1422 |
+
"eval_steps_per_second": 0.346,
|
| 1423 |
+
"step": 505
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.31,
|
| 1427 |
+
"learning_rate": 3.444730077120823e-05,
|
| 1428 |
+
"loss": 1.6507,
|
| 1429 |
+
"step": 510
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 1.31,
|
| 1433 |
+
"eval_loss": 1.661084532737732,
|
| 1434 |
+
"eval_runtime": 31.8028,
|
| 1435 |
+
"eval_samples_per_second": 2.641,
|
| 1436 |
+
"eval_steps_per_second": 0.346,
|
| 1437 |
+
"step": 510
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.32,
|
| 1441 |
+
"learning_rate": 3.380462724935733e-05,
|
| 1442 |
+
"loss": 1.6377,
|
| 1443 |
+
"step": 515
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.32,
|
| 1447 |
+
"eval_loss": 1.6610103845596313,
|
| 1448 |
+
"eval_runtime": 31.8101,
|
| 1449 |
+
"eval_samples_per_second": 2.641,
|
| 1450 |
+
"eval_steps_per_second": 0.346,
|
| 1451 |
+
"step": 515
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.34,
|
| 1455 |
+
"learning_rate": 3.316195372750643e-05,
|
| 1456 |
+
"loss": 1.6351,
|
| 1457 |
+
"step": 520
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.34,
|
| 1461 |
+
"eval_loss": 1.6608690023422241,
|
| 1462 |
+
"eval_runtime": 31.7986,
|
| 1463 |
+
"eval_samples_per_second": 2.642,
|
| 1464 |
+
"eval_steps_per_second": 0.346,
|
| 1465 |
+
"step": 520
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.35,
|
| 1469 |
+
"learning_rate": 3.251928020565553e-05,
|
| 1470 |
+
"loss": 1.6196,
|
| 1471 |
+
"step": 525
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 1.35,
|
| 1475 |
+
"eval_loss": 1.6606587171554565,
|
| 1476 |
+
"eval_runtime": 31.8015,
|
| 1477 |
+
"eval_samples_per_second": 2.641,
|
| 1478 |
+
"eval_steps_per_second": 0.346,
|
| 1479 |
+
"step": 525
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.36,
|
| 1483 |
+
"learning_rate": 3.1876606683804625e-05,
|
| 1484 |
+
"loss": 1.646,
|
| 1485 |
+
"step": 530
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.36,
|
| 1489 |
+
"eval_loss": 1.6605886220932007,
|
| 1490 |
+
"eval_runtime": 31.804,
|
| 1491 |
+
"eval_samples_per_second": 2.641,
|
| 1492 |
+
"eval_steps_per_second": 0.346,
|
| 1493 |
+
"step": 530
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.38,
|
| 1497 |
+
"learning_rate": 3.1233933161953726e-05,
|
| 1498 |
+
"loss": 1.6824,
|
| 1499 |
+
"step": 535
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.38,
|
| 1503 |
+
"eval_loss": 1.6603879928588867,
|
| 1504 |
+
"eval_runtime": 31.8111,
|
| 1505 |
+
"eval_samples_per_second": 2.641,
|
| 1506 |
+
"eval_steps_per_second": 0.346,
|
| 1507 |
+
"step": 535
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.39,
|
| 1511 |
+
"learning_rate": 3.059125964010283e-05,
|
| 1512 |
+
"loss": 1.6115,
|
| 1513 |
+
"step": 540
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 1.39,
|
| 1517 |
+
"eval_loss": 1.660337209701538,
|
| 1518 |
+
"eval_runtime": 31.805,
|
| 1519 |
+
"eval_samples_per_second": 2.641,
|
| 1520 |
+
"eval_steps_per_second": 0.346,
|
| 1521 |
+
"step": 540
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.4,
|
| 1525 |
+
"learning_rate": 2.994858611825193e-05,
|
| 1526 |
+
"loss": 1.6243,
|
| 1527 |
+
"step": 545
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 1.4,
|
| 1531 |
+
"eval_loss": 1.6606225967407227,
|
| 1532 |
+
"eval_runtime": 31.808,
|
| 1533 |
+
"eval_samples_per_second": 2.641,
|
| 1534 |
+
"eval_steps_per_second": 0.346,
|
| 1535 |
+
"step": 545
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.41,
|
| 1539 |
+
"learning_rate": 2.930591259640103e-05,
|
| 1540 |
+
"loss": 1.6486,
|
| 1541 |
+
"step": 550
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 1.41,
|
| 1545 |
+
"eval_loss": 1.6604374647140503,
|
| 1546 |
+
"eval_runtime": 31.8072,
|
| 1547 |
+
"eval_samples_per_second": 2.641,
|
| 1548 |
+
"eval_steps_per_second": 0.346,
|
| 1549 |
+
"step": 550
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.43,
|
| 1553 |
+
"learning_rate": 2.866323907455013e-05,
|
| 1554 |
+
"loss": 1.6865,
|
| 1555 |
+
"step": 555
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 1.43,
|
| 1559 |
+
"eval_loss": 1.6601544618606567,
|
| 1560 |
+
"eval_runtime": 31.8069,
|
| 1561 |
+
"eval_samples_per_second": 2.641,
|
| 1562 |
+
"eval_steps_per_second": 0.346,
|
| 1563 |
+
"step": 555
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.44,
|
| 1567 |
+
"learning_rate": 2.802056555269923e-05,
|
| 1568 |
+
"loss": 1.6616,
|
| 1569 |
+
"step": 560
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.44,
|
| 1573 |
+
"eval_loss": 1.660386562347412,
|
| 1574 |
+
"eval_runtime": 31.803,
|
| 1575 |
+
"eval_samples_per_second": 2.641,
|
| 1576 |
+
"eval_steps_per_second": 0.346,
|
| 1577 |
+
"step": 560
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.45,
|
| 1581 |
+
"learning_rate": 2.737789203084833e-05,
|
| 1582 |
+
"loss": 1.6336,
|
| 1583 |
+
"step": 565
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 1.45,
|
| 1587 |
+
"eval_loss": 1.660247802734375,
|
| 1588 |
+
"eval_runtime": 31.8084,
|
| 1589 |
+
"eval_samples_per_second": 2.641,
|
| 1590 |
+
"eval_steps_per_second": 0.346,
|
| 1591 |
+
"step": 565
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.47,
|
| 1595 |
+
"learning_rate": 2.673521850899743e-05,
|
| 1596 |
+
"loss": 1.6699,
|
| 1597 |
+
"step": 570
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 1.47,
|
| 1601 |
+
"eval_loss": 1.660292148590088,
|
| 1602 |
+
"eval_runtime": 31.8031,
|
| 1603 |
+
"eval_samples_per_second": 2.641,
|
| 1604 |
+
"eval_steps_per_second": 0.346,
|
| 1605 |
+
"step": 570
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.48,
|
| 1609 |
+
"learning_rate": 2.6092544987146534e-05,
|
| 1610 |
+
"loss": 1.6472,
|
| 1611 |
+
"step": 575
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 1.48,
|
| 1615 |
+
"eval_loss": 1.6598683595657349,
|
| 1616 |
+
"eval_runtime": 31.8181,
|
| 1617 |
+
"eval_samples_per_second": 2.64,
|
| 1618 |
+
"eval_steps_per_second": 0.346,
|
| 1619 |
+
"step": 575
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.49,
|
| 1623 |
+
"learning_rate": 2.5449871465295634e-05,
|
| 1624 |
+
"loss": 1.6723,
|
| 1625 |
+
"step": 580
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.49,
|
| 1629 |
+
"eval_loss": 1.6599065065383911,
|
| 1630 |
+
"eval_runtime": 31.8124,
|
| 1631 |
+
"eval_samples_per_second": 2.64,
|
| 1632 |
+
"eval_steps_per_second": 0.346,
|
| 1633 |
+
"step": 580
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.5,
|
| 1637 |
+
"learning_rate": 2.480719794344473e-05,
|
| 1638 |
+
"loss": 1.663,
|
| 1639 |
+
"step": 585
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 1.5,
|
| 1643 |
+
"eval_loss": 1.6599762439727783,
|
| 1644 |
+
"eval_runtime": 31.8175,
|
| 1645 |
+
"eval_samples_per_second": 2.64,
|
| 1646 |
+
"eval_steps_per_second": 0.346,
|
| 1647 |
+
"step": 585
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.52,
|
| 1651 |
+
"learning_rate": 2.4164524421593832e-05,
|
| 1652 |
+
"loss": 1.6519,
|
| 1653 |
+
"step": 590
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 1.52,
|
| 1657 |
+
"eval_loss": 1.6599925756454468,
|
| 1658 |
+
"eval_runtime": 31.8209,
|
| 1659 |
+
"eval_samples_per_second": 2.64,
|
| 1660 |
+
"eval_steps_per_second": 0.346,
|
| 1661 |
+
"step": 590
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.53,
|
| 1665 |
+
"learning_rate": 2.3521850899742933e-05,
|
| 1666 |
+
"loss": 1.6345,
|
| 1667 |
+
"step": 595
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 1.53,
|
| 1671 |
+
"eval_loss": 1.6600078344345093,
|
| 1672 |
+
"eval_runtime": 31.8031,
|
| 1673 |
+
"eval_samples_per_second": 2.641,
|
| 1674 |
+
"eval_steps_per_second": 0.346,
|
| 1675 |
+
"step": 595
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.54,
|
| 1679 |
+
"learning_rate": 2.2879177377892033e-05,
|
| 1680 |
+
"loss": 1.654,
|
| 1681 |
+
"step": 600
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 1.54,
|
| 1685 |
+
"eval_loss": 1.6599884033203125,
|
| 1686 |
+
"eval_runtime": 31.8281,
|
| 1687 |
+
"eval_samples_per_second": 2.639,
|
| 1688 |
+
"eval_steps_per_second": 0.346,
|
| 1689 |
+
"step": 600
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.56,
|
| 1693 |
+
"learning_rate": 2.2236503856041134e-05,
|
| 1694 |
+
"loss": 1.691,
|
| 1695 |
+
"step": 605
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 1.56,
|
| 1699 |
+
"eval_loss": 1.6599520444869995,
|
| 1700 |
+
"eval_runtime": 31.8168,
|
| 1701 |
+
"eval_samples_per_second": 2.64,
|
| 1702 |
+
"eval_steps_per_second": 0.346,
|
| 1703 |
+
"step": 605
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.57,
|
| 1707 |
+
"learning_rate": 2.159383033419023e-05,
|
| 1708 |
+
"loss": 1.6714,
|
| 1709 |
+
"step": 610
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 1.57,
|
| 1713 |
+
"eval_loss": 1.659857988357544,
|
| 1714 |
+
"eval_runtime": 31.8153,
|
| 1715 |
+
"eval_samples_per_second": 2.64,
|
| 1716 |
+
"eval_steps_per_second": 0.346,
|
| 1717 |
+
"step": 610
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.58,
|
| 1721 |
+
"learning_rate": 2.095115681233933e-05,
|
| 1722 |
+
"loss": 1.5977,
|
| 1723 |
+
"step": 615
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 1.58,
|
| 1727 |
+
"eval_loss": 1.6596992015838623,
|
| 1728 |
+
"eval_runtime": 31.8087,
|
| 1729 |
+
"eval_samples_per_second": 2.641,
|
| 1730 |
+
"eval_steps_per_second": 0.346,
|
| 1731 |
+
"step": 615
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.59,
|
| 1735 |
+
"learning_rate": 2.0308483290488432e-05,
|
| 1736 |
+
"loss": 1.6429,
|
| 1737 |
+
"step": 620
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.59,
|
| 1741 |
+
"eval_loss": 1.6595497131347656,
|
| 1742 |
+
"eval_runtime": 31.8151,
|
| 1743 |
+
"eval_samples_per_second": 2.64,
|
| 1744 |
+
"eval_steps_per_second": 0.346,
|
| 1745 |
+
"step": 620
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.61,
|
| 1749 |
+
"learning_rate": 1.9665809768637533e-05,
|
| 1750 |
+
"loss": 1.6091,
|
| 1751 |
+
"step": 625
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 1.61,
|
| 1755 |
+
"eval_loss": 1.6597559452056885,
|
| 1756 |
+
"eval_runtime": 31.8076,
|
| 1757 |
+
"eval_samples_per_second": 2.641,
|
| 1758 |
+
"eval_steps_per_second": 0.346,
|
| 1759 |
+
"step": 625
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.62,
|
| 1763 |
+
"learning_rate": 1.9023136246786633e-05,
|
| 1764 |
+
"loss": 1.5956,
|
| 1765 |
+
"step": 630
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 1.62,
|
| 1769 |
+
"eval_loss": 1.6593599319458008,
|
| 1770 |
+
"eval_runtime": 31.8058,
|
| 1771 |
+
"eval_samples_per_second": 2.641,
|
| 1772 |
+
"eval_steps_per_second": 0.346,
|
| 1773 |
+
"step": 630
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.63,
|
| 1777 |
+
"learning_rate": 1.8380462724935734e-05,
|
| 1778 |
+
"loss": 1.6697,
|
| 1779 |
+
"step": 635
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.63,
|
| 1783 |
+
"eval_loss": 1.6592466831207275,
|
| 1784 |
+
"eval_runtime": 31.8589,
|
| 1785 |
+
"eval_samples_per_second": 2.637,
|
| 1786 |
+
"eval_steps_per_second": 0.345,
|
| 1787 |
+
"step": 635
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.65,
|
| 1791 |
+
"learning_rate": 1.7737789203084834e-05,
|
| 1792 |
+
"loss": 1.6535,
|
| 1793 |
+
"step": 640
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.65,
|
| 1797 |
+
"eval_loss": 1.6592165231704712,
|
| 1798 |
+
"eval_runtime": 31.8225,
|
| 1799 |
+
"eval_samples_per_second": 2.64,
|
| 1800 |
+
"eval_steps_per_second": 0.346,
|
| 1801 |
+
"step": 640
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.66,
|
| 1805 |
+
"learning_rate": 1.7095115681233935e-05,
|
| 1806 |
+
"loss": 1.6722,
|
| 1807 |
+
"step": 645
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 1.66,
|
| 1811 |
+
"eval_loss": 1.659324049949646,
|
| 1812 |
+
"eval_runtime": 31.8388,
|
| 1813 |
+
"eval_samples_per_second": 2.638,
|
| 1814 |
+
"eval_steps_per_second": 0.345,
|
| 1815 |
+
"step": 645
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.67,
|
| 1819 |
+
"learning_rate": 1.6452442159383032e-05,
|
| 1820 |
+
"loss": 1.6347,
|
| 1821 |
+
"step": 650
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 1.67,
|
| 1825 |
+
"eval_loss": 1.6590396165847778,
|
| 1826 |
+
"eval_runtime": 31.8174,
|
| 1827 |
+
"eval_samples_per_second": 2.64,
|
| 1828 |
+
"eval_steps_per_second": 0.346,
|
| 1829 |
+
"step": 650
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.68,
|
| 1833 |
+
"learning_rate": 1.5809768637532136e-05,
|
| 1834 |
+
"loss": 1.6223,
|
| 1835 |
+
"step": 655
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.68,
|
| 1839 |
+
"eval_loss": 1.658969521522522,
|
| 1840 |
+
"eval_runtime": 31.8275,
|
| 1841 |
+
"eval_samples_per_second": 2.639,
|
| 1842 |
+
"eval_steps_per_second": 0.346,
|
| 1843 |
+
"step": 655
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.7,
|
| 1847 |
+
"learning_rate": 1.5167095115681235e-05,
|
| 1848 |
+
"loss": 1.6309,
|
| 1849 |
+
"step": 660
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.7,
|
| 1853 |
+
"eval_loss": 1.6587274074554443,
|
| 1854 |
+
"eval_runtime": 31.8146,
|
| 1855 |
+
"eval_samples_per_second": 2.64,
|
| 1856 |
+
"eval_steps_per_second": 0.346,
|
| 1857 |
+
"step": 660
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.71,
|
| 1861 |
+
"learning_rate": 1.4524421593830334e-05,
|
| 1862 |
+
"loss": 1.6499,
|
| 1863 |
+
"step": 665
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.71,
|
| 1867 |
+
"eval_loss": 1.65865957736969,
|
| 1868 |
+
"eval_runtime": 31.8091,
|
| 1869 |
+
"eval_samples_per_second": 2.641,
|
| 1870 |
+
"eval_steps_per_second": 0.346,
|
| 1871 |
+
"step": 665
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.72,
|
| 1875 |
+
"learning_rate": 1.3881748071979436e-05,
|
| 1876 |
+
"loss": 1.6713,
|
| 1877 |
+
"step": 670
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 1.72,
|
| 1881 |
+
"eval_loss": 1.6586016416549683,
|
| 1882 |
+
"eval_runtime": 31.8229,
|
| 1883 |
+
"eval_samples_per_second": 2.64,
|
| 1884 |
+
"eval_steps_per_second": 0.346,
|
| 1885 |
+
"step": 670
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.74,
|
| 1889 |
+
"learning_rate": 1.3239074550128535e-05,
|
| 1890 |
+
"loss": 1.6348,
|
| 1891 |
+
"step": 675
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.74,
|
| 1895 |
+
"eval_loss": 1.6584962606430054,
|
| 1896 |
+
"eval_runtime": 31.8035,
|
| 1897 |
+
"eval_samples_per_second": 2.641,
|
| 1898 |
+
"eval_steps_per_second": 0.346,
|
| 1899 |
+
"step": 675
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.75,
|
| 1903 |
+
"learning_rate": 1.2596401028277636e-05,
|
| 1904 |
+
"loss": 1.6447,
|
| 1905 |
+
"step": 680
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.75,
|
| 1909 |
+
"eval_loss": 1.6585614681243896,
|
| 1910 |
+
"eval_runtime": 31.8101,
|
| 1911 |
+
"eval_samples_per_second": 2.641,
|
| 1912 |
+
"eval_steps_per_second": 0.346,
|
| 1913 |
+
"step": 680
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.76,
|
| 1917 |
+
"learning_rate": 1.1953727506426736e-05,
|
| 1918 |
+
"loss": 1.6511,
|
| 1919 |
+
"step": 685
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.76,
|
| 1923 |
+
"eval_loss": 1.6583601236343384,
|
| 1924 |
+
"eval_runtime": 31.8125,
|
| 1925 |
+
"eval_samples_per_second": 2.64,
|
| 1926 |
+
"eval_steps_per_second": 0.346,
|
| 1927 |
+
"step": 685
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.77,
|
| 1931 |
+
"learning_rate": 1.1311053984575835e-05,
|
| 1932 |
+
"loss": 1.6496,
|
| 1933 |
+
"step": 690
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.77,
|
| 1937 |
+
"eval_loss": 1.6583328247070312,
|
| 1938 |
+
"eval_runtime": 31.8179,
|
| 1939 |
+
"eval_samples_per_second": 2.64,
|
| 1940 |
+
"eval_steps_per_second": 0.346,
|
| 1941 |
+
"step": 690
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.79,
|
| 1945 |
+
"learning_rate": 1.0668380462724936e-05,
|
| 1946 |
+
"loss": 1.6421,
|
| 1947 |
+
"step": 695
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 1.79,
|
| 1951 |
+
"eval_loss": 1.6583188772201538,
|
| 1952 |
+
"eval_runtime": 31.8165,
|
| 1953 |
+
"eval_samples_per_second": 2.64,
|
| 1954 |
+
"eval_steps_per_second": 0.346,
|
| 1955 |
+
"step": 695
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.8,
|
| 1959 |
+
"learning_rate": 1.0025706940874038e-05,
|
| 1960 |
+
"loss": 1.6126,
|
| 1961 |
+
"step": 700
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 1.8,
|
| 1965 |
+
"eval_loss": 1.6580705642700195,
|
| 1966 |
+
"eval_runtime": 31.8164,
|
| 1967 |
+
"eval_samples_per_second": 2.64,
|
| 1968 |
+
"eval_steps_per_second": 0.346,
|
| 1969 |
+
"step": 700
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.81,
|
| 1973 |
+
"learning_rate": 9.383033419023137e-06,
|
| 1974 |
+
"loss": 1.6226,
|
| 1975 |
+
"step": 705
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 1.81,
|
| 1979 |
+
"eval_loss": 1.6584465503692627,
|
| 1980 |
+
"eval_runtime": 31.816,
|
| 1981 |
+
"eval_samples_per_second": 2.64,
|
| 1982 |
+
"eval_steps_per_second": 0.346,
|
| 1983 |
+
"step": 705
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.83,
|
| 1987 |
+
"learning_rate": 8.740359897172237e-06,
|
| 1988 |
+
"loss": 1.6923,
|
| 1989 |
+
"step": 710
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.83,
|
| 1993 |
+
"eval_loss": 1.658342957496643,
|
| 1994 |
+
"eval_runtime": 31.8215,
|
| 1995 |
+
"eval_samples_per_second": 2.64,
|
| 1996 |
+
"eval_steps_per_second": 0.346,
|
| 1997 |
+
"step": 710
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.84,
|
| 2001 |
+
"learning_rate": 8.097686375321336e-06,
|
| 2002 |
+
"loss": 1.6224,
|
| 2003 |
+
"step": 715
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 1.84,
|
| 2007 |
+
"eval_loss": 1.6582502126693726,
|
| 2008 |
+
"eval_runtime": 31.812,
|
| 2009 |
+
"eval_samples_per_second": 2.641,
|
| 2010 |
+
"eval_steps_per_second": 0.346,
|
| 2011 |
+
"step": 715
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.85,
|
| 2015 |
+
"learning_rate": 7.4550128534704376e-06,
|
| 2016 |
+
"loss": 1.6587,
|
| 2017 |
+
"step": 720
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 1.85,
|
| 2021 |
+
"eval_loss": 1.658232569694519,
|
| 2022 |
+
"eval_runtime": 31.8059,
|
| 2023 |
+
"eval_samples_per_second": 2.641,
|
| 2024 |
+
"eval_steps_per_second": 0.346,
|
| 2025 |
+
"step": 720
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.86,
|
| 2029 |
+
"learning_rate": 6.812339331619537e-06,
|
| 2030 |
+
"loss": 1.6641,
|
| 2031 |
+
"step": 725
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 1.86,
|
| 2035 |
+
"eval_loss": 1.6582419872283936,
|
| 2036 |
+
"eval_runtime": 31.81,
|
| 2037 |
+
"eval_samples_per_second": 2.641,
|
| 2038 |
+
"eval_steps_per_second": 0.346,
|
| 2039 |
+
"step": 725
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.88,
|
| 2043 |
+
"learning_rate": 6.169665809768638e-06,
|
| 2044 |
+
"loss": 1.6419,
|
| 2045 |
+
"step": 730
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.88,
|
| 2049 |
+
"eval_loss": 1.6582107543945312,
|
| 2050 |
+
"eval_runtime": 31.833,
|
| 2051 |
+
"eval_samples_per_second": 2.639,
|
| 2052 |
+
"eval_steps_per_second": 0.346,
|
| 2053 |
+
"step": 730
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.89,
|
| 2057 |
+
"learning_rate": 5.526992287917738e-06,
|
| 2058 |
+
"loss": 1.652,
|
| 2059 |
+
"step": 735
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 1.89,
|
| 2063 |
+
"eval_loss": 1.6582270860671997,
|
| 2064 |
+
"eval_runtime": 31.8801,
|
| 2065 |
+
"eval_samples_per_second": 2.635,
|
| 2066 |
+
"eval_steps_per_second": 0.345,
|
| 2067 |
+
"step": 735
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.9,
|
| 2071 |
+
"learning_rate": 4.884318766066838e-06,
|
| 2072 |
+
"loss": 1.6487,
|
| 2073 |
+
"step": 740
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.9,
|
| 2077 |
+
"eval_loss": 1.6582915782928467,
|
| 2078 |
+
"eval_runtime": 31.8265,
|
| 2079 |
+
"eval_samples_per_second": 2.639,
|
| 2080 |
+
"eval_steps_per_second": 0.346,
|
| 2081 |
+
"step": 740
|
| 2082 |
+
}
|
| 2083 |
+
],
|
| 2084 |
+
"logging_steps": 5,
|
| 2085 |
+
"max_steps": 778,
|
| 2086 |
+
"num_train_epochs": 2,
|
| 2087 |
+
"save_steps": 10,
|
| 2088 |
+
"total_flos": 2.4039678818648064e+17,
|
| 2089 |
+
"trial_name": null,
|
| 2090 |
+
"trial_params": null
|
| 2091 |
+
}
|
checkpoint-740/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc6a8542abd91027de58ebfccafdf919108680707834fe188d91cae077ef8e9
|
| 3 |
+
size 4600
|
checkpoint-750/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.5.0
|
checkpoint-750/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-750/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0db055afa4e779064330cfa471192b67fc333a5cae786bb3fa230f8be5a897f
|
| 3 |
+
size 16794200
|
checkpoint-750/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07c6460edcba33b54b6ac46970a9eb988c702b55e3f0bc05da88f3f21dbc55b5
|
| 3 |
+
size 33663866
|
checkpoint-750/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67ce38b2aa4d6ac4ebbc000d2ae5e7ed24241a918687e62a058926935f4a4446
|
| 3 |
+
size 14244
|
checkpoint-750/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c4aa7fa9070b6f1e0780c2b6ec486cdbc883e6f06e8f42ae16069e6d9cd1a7c
|
| 3 |
+
size 1064
|
checkpoint-750/trainer_state.json
ADDED
|
@@ -0,0 +1,2119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.6578683853149414,
|
| 3 |
+
"best_model_checkpoint": "/scratch/kwamea/llama-output/checkpoint-750",
|
| 4 |
+
"epoch": 1.9280205655526992,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 750,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 9.93573264781491e-05,
|
| 14 |
+
"loss": 1.9824,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"eval_loss": 1.954728126525879,
|
| 20 |
+
"eval_runtime": 31.6803,
|
| 21 |
+
"eval_samples_per_second": 2.651,
|
| 22 |
+
"eval_steps_per_second": 0.347,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"learning_rate": 9.87146529562982e-05,
|
| 28 |
+
"loss": 1.9249,
|
| 29 |
+
"step": 10
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"eval_loss": 1.8934264183044434,
|
| 34 |
+
"eval_runtime": 31.7798,
|
| 35 |
+
"eval_samples_per_second": 2.643,
|
| 36 |
+
"eval_steps_per_second": 0.346,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04,
|
| 41 |
+
"learning_rate": 9.80719794344473e-05,
|
| 42 |
+
"loss": 1.8609,
|
| 43 |
+
"step": 15
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.04,
|
| 47 |
+
"eval_loss": 1.8421852588653564,
|
| 48 |
+
"eval_runtime": 31.7999,
|
| 49 |
+
"eval_samples_per_second": 2.642,
|
| 50 |
+
"eval_steps_per_second": 0.346,
|
| 51 |
+
"step": 15
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"learning_rate": 9.742930591259641e-05,
|
| 56 |
+
"loss": 1.8268,
|
| 57 |
+
"step": 20
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.05,
|
| 61 |
+
"eval_loss": 1.8279638290405273,
|
| 62 |
+
"eval_runtime": 31.8095,
|
| 63 |
+
"eval_samples_per_second": 2.641,
|
| 64 |
+
"eval_steps_per_second": 0.346,
|
| 65 |
+
"step": 20
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06,
|
| 69 |
+
"learning_rate": 9.67866323907455e-05,
|
| 70 |
+
"loss": 1.8349,
|
| 71 |
+
"step": 25
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.06,
|
| 75 |
+
"eval_loss": 1.813267469406128,
|
| 76 |
+
"eval_runtime": 31.8291,
|
| 77 |
+
"eval_samples_per_second": 2.639,
|
| 78 |
+
"eval_steps_per_second": 0.346,
|
| 79 |
+
"step": 25
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08,
|
| 83 |
+
"learning_rate": 9.61439588688946e-05,
|
| 84 |
+
"loss": 1.8239,
|
| 85 |
+
"step": 30
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.08,
|
| 89 |
+
"eval_loss": 1.8008779287338257,
|
| 90 |
+
"eval_runtime": 31.82,
|
| 91 |
+
"eval_samples_per_second": 2.64,
|
| 92 |
+
"eval_steps_per_second": 0.346,
|
| 93 |
+
"step": 30
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 9.550128534704372e-05,
|
| 98 |
+
"loss": 1.7177,
|
| 99 |
+
"step": 35
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.09,
|
| 103 |
+
"eval_loss": 1.789797067642212,
|
| 104 |
+
"eval_runtime": 31.8423,
|
| 105 |
+
"eval_samples_per_second": 2.638,
|
| 106 |
+
"eval_steps_per_second": 0.345,
|
| 107 |
+
"step": 35
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1,
|
| 111 |
+
"learning_rate": 9.485861182519281e-05,
|
| 112 |
+
"loss": 1.7962,
|
| 113 |
+
"step": 40
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.1,
|
| 117 |
+
"eval_loss": 1.7808287143707275,
|
| 118 |
+
"eval_runtime": 31.8387,
|
| 119 |
+
"eval_samples_per_second": 2.638,
|
| 120 |
+
"eval_steps_per_second": 0.345,
|
| 121 |
+
"step": 40
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.12,
|
| 125 |
+
"learning_rate": 9.421593830334192e-05,
|
| 126 |
+
"loss": 1.715,
|
| 127 |
+
"step": 45
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.12,
|
| 131 |
+
"eval_loss": 1.771236777305603,
|
| 132 |
+
"eval_runtime": 31.8526,
|
| 133 |
+
"eval_samples_per_second": 2.637,
|
| 134 |
+
"eval_steps_per_second": 0.345,
|
| 135 |
+
"step": 45
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13,
|
| 139 |
+
"learning_rate": 9.357326478149101e-05,
|
| 140 |
+
"loss": 1.7577,
|
| 141 |
+
"step": 50
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.13,
|
| 145 |
+
"eval_loss": 1.7619521617889404,
|
| 146 |
+
"eval_runtime": 31.828,
|
| 147 |
+
"eval_samples_per_second": 2.639,
|
| 148 |
+
"eval_steps_per_second": 0.346,
|
| 149 |
+
"step": 50
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.14,
|
| 153 |
+
"learning_rate": 9.29305912596401e-05,
|
| 154 |
+
"loss": 1.7323,
|
| 155 |
+
"step": 55
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.14,
|
| 159 |
+
"eval_loss": 1.7440986633300781,
|
| 160 |
+
"eval_runtime": 31.8301,
|
| 161 |
+
"eval_samples_per_second": 2.639,
|
| 162 |
+
"eval_steps_per_second": 0.346,
|
| 163 |
+
"step": 55
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.15,
|
| 167 |
+
"learning_rate": 9.228791773778921e-05,
|
| 168 |
+
"loss": 1.7122,
|
| 169 |
+
"step": 60
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.15,
|
| 173 |
+
"eval_loss": 1.712996006011963,
|
| 174 |
+
"eval_runtime": 31.8185,
|
| 175 |
+
"eval_samples_per_second": 2.64,
|
| 176 |
+
"eval_steps_per_second": 0.346,
|
| 177 |
+
"step": 60
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17,
|
| 181 |
+
"learning_rate": 9.16452442159383e-05,
|
| 182 |
+
"loss": 1.7042,
|
| 183 |
+
"step": 65
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.17,
|
| 187 |
+
"eval_loss": 1.7101707458496094,
|
| 188 |
+
"eval_runtime": 31.8153,
|
| 189 |
+
"eval_samples_per_second": 2.64,
|
| 190 |
+
"eval_steps_per_second": 0.346,
|
| 191 |
+
"step": 65
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.18,
|
| 195 |
+
"learning_rate": 9.100257069408741e-05,
|
| 196 |
+
"loss": 1.7242,
|
| 197 |
+
"step": 70
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.18,
|
| 201 |
+
"eval_loss": 1.7038702964782715,
|
| 202 |
+
"eval_runtime": 31.8191,
|
| 203 |
+
"eval_samples_per_second": 2.64,
|
| 204 |
+
"eval_steps_per_second": 0.346,
|
| 205 |
+
"step": 70
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19,
|
| 209 |
+
"learning_rate": 9.03598971722365e-05,
|
| 210 |
+
"loss": 1.7033,
|
| 211 |
+
"step": 75
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.19,
|
| 215 |
+
"eval_loss": 1.7004183530807495,
|
| 216 |
+
"eval_runtime": 31.811,
|
| 217 |
+
"eval_samples_per_second": 2.641,
|
| 218 |
+
"eval_steps_per_second": 0.346,
|
| 219 |
+
"step": 75
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21,
|
| 223 |
+
"learning_rate": 8.97172236503856e-05,
|
| 224 |
+
"loss": 1.6934,
|
| 225 |
+
"step": 80
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.21,
|
| 229 |
+
"eval_loss": 1.6985355615615845,
|
| 230 |
+
"eval_runtime": 31.8221,
|
| 231 |
+
"eval_samples_per_second": 2.64,
|
| 232 |
+
"eval_steps_per_second": 0.346,
|
| 233 |
+
"step": 80
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22,
|
| 237 |
+
"learning_rate": 8.907455012853471e-05,
|
| 238 |
+
"loss": 1.6443,
|
| 239 |
+
"step": 85
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.22,
|
| 243 |
+
"eval_loss": 1.696852684020996,
|
| 244 |
+
"eval_runtime": 31.8219,
|
| 245 |
+
"eval_samples_per_second": 2.64,
|
| 246 |
+
"eval_steps_per_second": 0.346,
|
| 247 |
+
"step": 85
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.23,
|
| 251 |
+
"learning_rate": 8.84318766066838e-05,
|
| 252 |
+
"loss": 1.7008,
|
| 253 |
+
"step": 90
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.23,
|
| 257 |
+
"eval_loss": 1.695594072341919,
|
| 258 |
+
"eval_runtime": 31.8205,
|
| 259 |
+
"eval_samples_per_second": 2.64,
|
| 260 |
+
"eval_steps_per_second": 0.346,
|
| 261 |
+
"step": 90
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.24,
|
| 265 |
+
"learning_rate": 8.778920308483291e-05,
|
| 266 |
+
"loss": 1.6873,
|
| 267 |
+
"step": 95
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.24,
|
| 271 |
+
"eval_loss": 1.6928850412368774,
|
| 272 |
+
"eval_runtime": 31.814,
|
| 273 |
+
"eval_samples_per_second": 2.64,
|
| 274 |
+
"eval_steps_per_second": 0.346,
|
| 275 |
+
"step": 95
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.26,
|
| 279 |
+
"learning_rate": 8.7146529562982e-05,
|
| 280 |
+
"loss": 1.6721,
|
| 281 |
+
"step": 100
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.26,
|
| 285 |
+
"eval_loss": 1.6919386386871338,
|
| 286 |
+
"eval_runtime": 31.8127,
|
| 287 |
+
"eval_samples_per_second": 2.64,
|
| 288 |
+
"eval_steps_per_second": 0.346,
|
| 289 |
+
"step": 100
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.27,
|
| 293 |
+
"learning_rate": 8.650385604113111e-05,
|
| 294 |
+
"loss": 1.6669,
|
| 295 |
+
"step": 105
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.27,
|
| 299 |
+
"eval_loss": 1.6905940771102905,
|
| 300 |
+
"eval_runtime": 31.8874,
|
| 301 |
+
"eval_samples_per_second": 2.634,
|
| 302 |
+
"eval_steps_per_second": 0.345,
|
| 303 |
+
"step": 105
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.28,
|
| 307 |
+
"learning_rate": 8.586118251928022e-05,
|
| 308 |
+
"loss": 1.7009,
|
| 309 |
+
"step": 110
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.28,
|
| 313 |
+
"eval_loss": 1.689422607421875,
|
| 314 |
+
"eval_runtime": 31.8489,
|
| 315 |
+
"eval_samples_per_second": 2.637,
|
| 316 |
+
"eval_steps_per_second": 0.345,
|
| 317 |
+
"step": 110
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.3,
|
| 321 |
+
"learning_rate": 8.521850899742931e-05,
|
| 322 |
+
"loss": 1.7151,
|
| 323 |
+
"step": 115
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.3,
|
| 327 |
+
"eval_loss": 1.688527226448059,
|
| 328 |
+
"eval_runtime": 31.8318,
|
| 329 |
+
"eval_samples_per_second": 2.639,
|
| 330 |
+
"eval_steps_per_second": 0.346,
|
| 331 |
+
"step": 115
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.31,
|
| 335 |
+
"learning_rate": 8.457583547557842e-05,
|
| 336 |
+
"loss": 1.7165,
|
| 337 |
+
"step": 120
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.31,
|
| 341 |
+
"eval_loss": 1.686748743057251,
|
| 342 |
+
"eval_runtime": 31.835,
|
| 343 |
+
"eval_samples_per_second": 2.639,
|
| 344 |
+
"eval_steps_per_second": 0.346,
|
| 345 |
+
"step": 120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.32,
|
| 349 |
+
"learning_rate": 8.393316195372751e-05,
|
| 350 |
+
"loss": 1.7015,
|
| 351 |
+
"step": 125
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.32,
|
| 355 |
+
"eval_loss": 1.6855812072753906,
|
| 356 |
+
"eval_runtime": 31.8269,
|
| 357 |
+
"eval_samples_per_second": 2.639,
|
| 358 |
+
"eval_steps_per_second": 0.346,
|
| 359 |
+
"step": 125
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.33,
|
| 363 |
+
"learning_rate": 8.32904884318766e-05,
|
| 364 |
+
"loss": 1.6818,
|
| 365 |
+
"step": 130
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.33,
|
| 369 |
+
"eval_loss": 1.6846078634262085,
|
| 370 |
+
"eval_runtime": 31.8617,
|
| 371 |
+
"eval_samples_per_second": 2.636,
|
| 372 |
+
"eval_steps_per_second": 0.345,
|
| 373 |
+
"step": 130
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.35,
|
| 377 |
+
"learning_rate": 8.264781491002571e-05,
|
| 378 |
+
"loss": 1.7151,
|
| 379 |
+
"step": 135
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.35,
|
| 383 |
+
"eval_loss": 1.6845166683197021,
|
| 384 |
+
"eval_runtime": 31.8631,
|
| 385 |
+
"eval_samples_per_second": 2.636,
|
| 386 |
+
"eval_steps_per_second": 0.345,
|
| 387 |
+
"step": 135
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.36,
|
| 391 |
+
"learning_rate": 8.200514138817481e-05,
|
| 392 |
+
"loss": 1.6667,
|
| 393 |
+
"step": 140
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.36,
|
| 397 |
+
"eval_loss": 1.6832246780395508,
|
| 398 |
+
"eval_runtime": 31.8276,
|
| 399 |
+
"eval_samples_per_second": 2.639,
|
| 400 |
+
"eval_steps_per_second": 0.346,
|
| 401 |
+
"step": 140
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.37,
|
| 405 |
+
"learning_rate": 8.136246786632391e-05,
|
| 406 |
+
"loss": 1.6586,
|
| 407 |
+
"step": 145
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.37,
|
| 411 |
+
"eval_loss": 1.6824573278427124,
|
| 412 |
+
"eval_runtime": 31.8115,
|
| 413 |
+
"eval_samples_per_second": 2.641,
|
| 414 |
+
"eval_steps_per_second": 0.346,
|
| 415 |
+
"step": 145
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.39,
|
| 419 |
+
"learning_rate": 8.071979434447301e-05,
|
| 420 |
+
"loss": 1.6999,
|
| 421 |
+
"step": 150
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.39,
|
| 425 |
+
"eval_loss": 1.681317687034607,
|
| 426 |
+
"eval_runtime": 31.805,
|
| 427 |
+
"eval_samples_per_second": 2.641,
|
| 428 |
+
"eval_steps_per_second": 0.346,
|
| 429 |
+
"step": 150
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4,
|
| 433 |
+
"learning_rate": 8.007712082262212e-05,
|
| 434 |
+
"loss": 1.6894,
|
| 435 |
+
"step": 155
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.4,
|
| 439 |
+
"eval_loss": 1.6812355518341064,
|
| 440 |
+
"eval_runtime": 31.8039,
|
| 441 |
+
"eval_samples_per_second": 2.641,
|
| 442 |
+
"eval_steps_per_second": 0.346,
|
| 443 |
+
"step": 155
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.41,
|
| 447 |
+
"learning_rate": 7.943444730077121e-05,
|
| 448 |
+
"loss": 1.6669,
|
| 449 |
+
"step": 160
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.41,
|
| 453 |
+
"eval_loss": 1.679802656173706,
|
| 454 |
+
"eval_runtime": 31.8021,
|
| 455 |
+
"eval_samples_per_second": 2.641,
|
| 456 |
+
"eval_steps_per_second": 0.346,
|
| 457 |
+
"step": 160
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.42,
|
| 461 |
+
"learning_rate": 7.87917737789203e-05,
|
| 462 |
+
"loss": 1.6481,
|
| 463 |
+
"step": 165
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.42,
|
| 467 |
+
"eval_loss": 1.679994821548462,
|
| 468 |
+
"eval_runtime": 31.8201,
|
| 469 |
+
"eval_samples_per_second": 2.64,
|
| 470 |
+
"eval_steps_per_second": 0.346,
|
| 471 |
+
"step": 165
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.44,
|
| 475 |
+
"learning_rate": 7.814910025706941e-05,
|
| 476 |
+
"loss": 1.7042,
|
| 477 |
+
"step": 170
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.44,
|
| 481 |
+
"eval_loss": 1.6786224842071533,
|
| 482 |
+
"eval_runtime": 31.8184,
|
| 483 |
+
"eval_samples_per_second": 2.64,
|
| 484 |
+
"eval_steps_per_second": 0.346,
|
| 485 |
+
"step": 170
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.45,
|
| 489 |
+
"learning_rate": 7.750642673521852e-05,
|
| 490 |
+
"loss": 1.6564,
|
| 491 |
+
"step": 175
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.45,
|
| 495 |
+
"eval_loss": 1.6783201694488525,
|
| 496 |
+
"eval_runtime": 31.8137,
|
| 497 |
+
"eval_samples_per_second": 2.64,
|
| 498 |
+
"eval_steps_per_second": 0.346,
|
| 499 |
+
"step": 175
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.46,
|
| 503 |
+
"learning_rate": 7.686375321336761e-05,
|
| 504 |
+
"loss": 1.6714,
|
| 505 |
+
"step": 180
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.46,
|
| 509 |
+
"eval_loss": 1.677714228630066,
|
| 510 |
+
"eval_runtime": 31.804,
|
| 511 |
+
"eval_samples_per_second": 2.641,
|
| 512 |
+
"eval_steps_per_second": 0.346,
|
| 513 |
+
"step": 180
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.48,
|
| 517 |
+
"learning_rate": 7.622107969151672e-05,
|
| 518 |
+
"loss": 1.6705,
|
| 519 |
+
"step": 185
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.48,
|
| 523 |
+
"eval_loss": 1.6772773265838623,
|
| 524 |
+
"eval_runtime": 31.8077,
|
| 525 |
+
"eval_samples_per_second": 2.641,
|
| 526 |
+
"eval_steps_per_second": 0.346,
|
| 527 |
+
"step": 185
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.49,
|
| 531 |
+
"learning_rate": 7.557840616966581e-05,
|
| 532 |
+
"loss": 1.6624,
|
| 533 |
+
"step": 190
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.49,
|
| 537 |
+
"eval_loss": 1.6766114234924316,
|
| 538 |
+
"eval_runtime": 31.8164,
|
| 539 |
+
"eval_samples_per_second": 2.64,
|
| 540 |
+
"eval_steps_per_second": 0.346,
|
| 541 |
+
"step": 190
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.5,
|
| 545 |
+
"learning_rate": 7.493573264781492e-05,
|
| 546 |
+
"loss": 1.6415,
|
| 547 |
+
"step": 195
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.5,
|
| 551 |
+
"eval_loss": 1.675940752029419,
|
| 552 |
+
"eval_runtime": 31.8124,
|
| 553 |
+
"eval_samples_per_second": 2.64,
|
| 554 |
+
"eval_steps_per_second": 0.346,
|
| 555 |
+
"step": 195
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.51,
|
| 559 |
+
"learning_rate": 7.429305912596401e-05,
|
| 560 |
+
"loss": 1.6633,
|
| 561 |
+
"step": 200
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.51,
|
| 565 |
+
"eval_loss": 1.6751865148544312,
|
| 566 |
+
"eval_runtime": 31.8123,
|
| 567 |
+
"eval_samples_per_second": 2.64,
|
| 568 |
+
"eval_steps_per_second": 0.346,
|
| 569 |
+
"step": 200
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.53,
|
| 573 |
+
"learning_rate": 7.365038560411311e-05,
|
| 574 |
+
"loss": 1.6142,
|
| 575 |
+
"step": 205
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.53,
|
| 579 |
+
"eval_loss": 1.6750575304031372,
|
| 580 |
+
"eval_runtime": 31.8049,
|
| 581 |
+
"eval_samples_per_second": 2.641,
|
| 582 |
+
"eval_steps_per_second": 0.346,
|
| 583 |
+
"step": 205
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.54,
|
| 587 |
+
"learning_rate": 7.300771208226222e-05,
|
| 588 |
+
"loss": 1.6736,
|
| 589 |
+
"step": 210
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.54,
|
| 593 |
+
"eval_loss": 1.6746423244476318,
|
| 594 |
+
"eval_runtime": 31.8111,
|
| 595 |
+
"eval_samples_per_second": 2.641,
|
| 596 |
+
"eval_steps_per_second": 0.346,
|
| 597 |
+
"step": 210
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.55,
|
| 601 |
+
"learning_rate": 7.236503856041131e-05,
|
| 602 |
+
"loss": 1.6414,
|
| 603 |
+
"step": 215
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.55,
|
| 607 |
+
"eval_loss": 1.6740491390228271,
|
| 608 |
+
"eval_runtime": 31.8083,
|
| 609 |
+
"eval_samples_per_second": 2.641,
|
| 610 |
+
"eval_steps_per_second": 0.346,
|
| 611 |
+
"step": 215
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.57,
|
| 615 |
+
"learning_rate": 7.172236503856042e-05,
|
| 616 |
+
"loss": 1.6725,
|
| 617 |
+
"step": 220
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.57,
|
| 621 |
+
"eval_loss": 1.673694372177124,
|
| 622 |
+
"eval_runtime": 31.8025,
|
| 623 |
+
"eval_samples_per_second": 2.641,
|
| 624 |
+
"eval_steps_per_second": 0.346,
|
| 625 |
+
"step": 220
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.58,
|
| 629 |
+
"learning_rate": 7.107969151670951e-05,
|
| 630 |
+
"loss": 1.679,
|
| 631 |
+
"step": 225
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.58,
|
| 635 |
+
"eval_loss": 1.6733818054199219,
|
| 636 |
+
"eval_runtime": 31.8077,
|
| 637 |
+
"eval_samples_per_second": 2.641,
|
| 638 |
+
"eval_steps_per_second": 0.346,
|
| 639 |
+
"step": 225
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.59,
|
| 643 |
+
"learning_rate": 7.043701799485862e-05,
|
| 644 |
+
"loss": 1.7204,
|
| 645 |
+
"step": 230
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.59,
|
| 649 |
+
"eval_loss": 1.6725033521652222,
|
| 650 |
+
"eval_runtime": 31.8079,
|
| 651 |
+
"eval_samples_per_second": 2.641,
|
| 652 |
+
"eval_steps_per_second": 0.346,
|
| 653 |
+
"step": 230
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.6,
|
| 657 |
+
"learning_rate": 6.979434447300771e-05,
|
| 658 |
+
"loss": 1.6816,
|
| 659 |
+
"step": 235
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.6,
|
| 663 |
+
"eval_loss": 1.67205011844635,
|
| 664 |
+
"eval_runtime": 31.809,
|
| 665 |
+
"eval_samples_per_second": 2.641,
|
| 666 |
+
"eval_steps_per_second": 0.346,
|
| 667 |
+
"step": 235
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.62,
|
| 671 |
+
"learning_rate": 6.91516709511568e-05,
|
| 672 |
+
"loss": 1.634,
|
| 673 |
+
"step": 240
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.62,
|
| 677 |
+
"eval_loss": 1.6717994213104248,
|
| 678 |
+
"eval_runtime": 31.8075,
|
| 679 |
+
"eval_samples_per_second": 2.641,
|
| 680 |
+
"eval_steps_per_second": 0.346,
|
| 681 |
+
"step": 240
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.63,
|
| 685 |
+
"learning_rate": 6.850899742930593e-05,
|
| 686 |
+
"loss": 1.6761,
|
| 687 |
+
"step": 245
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.63,
|
| 691 |
+
"eval_loss": 1.6714757680892944,
|
| 692 |
+
"eval_runtime": 31.8052,
|
| 693 |
+
"eval_samples_per_second": 2.641,
|
| 694 |
+
"eval_steps_per_second": 0.346,
|
| 695 |
+
"step": 245
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.64,
|
| 699 |
+
"learning_rate": 6.786632390745502e-05,
|
| 700 |
+
"loss": 1.6996,
|
| 701 |
+
"step": 250
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.64,
|
| 705 |
+
"eval_loss": 1.671559453010559,
|
| 706 |
+
"eval_runtime": 31.8089,
|
| 707 |
+
"eval_samples_per_second": 2.641,
|
| 708 |
+
"eval_steps_per_second": 0.346,
|
| 709 |
+
"step": 250
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.66,
|
| 713 |
+
"learning_rate": 6.722365038560411e-05,
|
| 714 |
+
"loss": 1.6302,
|
| 715 |
+
"step": 255
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.66,
|
| 719 |
+
"eval_loss": 1.6711652278900146,
|
| 720 |
+
"eval_runtime": 31.8105,
|
| 721 |
+
"eval_samples_per_second": 2.641,
|
| 722 |
+
"eval_steps_per_second": 0.346,
|
| 723 |
+
"step": 255
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.67,
|
| 727 |
+
"learning_rate": 6.658097686375322e-05,
|
| 728 |
+
"loss": 1.6611,
|
| 729 |
+
"step": 260
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.67,
|
| 733 |
+
"eval_loss": 1.6704061031341553,
|
| 734 |
+
"eval_runtime": 31.8135,
|
| 735 |
+
"eval_samples_per_second": 2.64,
|
| 736 |
+
"eval_steps_per_second": 0.346,
|
| 737 |
+
"step": 260
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.68,
|
| 741 |
+
"learning_rate": 6.593830334190231e-05,
|
| 742 |
+
"loss": 1.6586,
|
| 743 |
+
"step": 265
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.68,
|
| 747 |
+
"eval_loss": 1.6705658435821533,
|
| 748 |
+
"eval_runtime": 31.7998,
|
| 749 |
+
"eval_samples_per_second": 2.642,
|
| 750 |
+
"eval_steps_per_second": 0.346,
|
| 751 |
+
"step": 265
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.69,
|
| 755 |
+
"learning_rate": 6.529562982005142e-05,
|
| 756 |
+
"loss": 1.6838,
|
| 757 |
+
"step": 270
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.69,
|
| 761 |
+
"eval_loss": 1.6697953939437866,
|
| 762 |
+
"eval_runtime": 31.7994,
|
| 763 |
+
"eval_samples_per_second": 2.642,
|
| 764 |
+
"eval_steps_per_second": 0.346,
|
| 765 |
+
"step": 270
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.71,
|
| 769 |
+
"learning_rate": 6.465295629820052e-05,
|
| 770 |
+
"loss": 1.6499,
|
| 771 |
+
"step": 275
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.71,
|
| 775 |
+
"eval_loss": 1.669343113899231,
|
| 776 |
+
"eval_runtime": 31.8147,
|
| 777 |
+
"eval_samples_per_second": 2.64,
|
| 778 |
+
"eval_steps_per_second": 0.346,
|
| 779 |
+
"step": 275
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.72,
|
| 783 |
+
"learning_rate": 6.401028277634962e-05,
|
| 784 |
+
"loss": 1.6424,
|
| 785 |
+
"step": 280
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.72,
|
| 789 |
+
"eval_loss": 1.6693596839904785,
|
| 790 |
+
"eval_runtime": 31.8155,
|
| 791 |
+
"eval_samples_per_second": 2.64,
|
| 792 |
+
"eval_steps_per_second": 0.346,
|
| 793 |
+
"step": 280
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.73,
|
| 797 |
+
"learning_rate": 6.336760925449872e-05,
|
| 798 |
+
"loss": 1.6238,
|
| 799 |
+
"step": 285
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.73,
|
| 803 |
+
"eval_loss": 1.669128179550171,
|
| 804 |
+
"eval_runtime": 31.8219,
|
| 805 |
+
"eval_samples_per_second": 2.64,
|
| 806 |
+
"eval_steps_per_second": 0.346,
|
| 807 |
+
"step": 285
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.75,
|
| 811 |
+
"learning_rate": 6.272493573264781e-05,
|
| 812 |
+
"loss": 1.6538,
|
| 813 |
+
"step": 290
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.75,
|
| 817 |
+
"eval_loss": 1.6691263914108276,
|
| 818 |
+
"eval_runtime": 31.81,
|
| 819 |
+
"eval_samples_per_second": 2.641,
|
| 820 |
+
"eval_steps_per_second": 0.346,
|
| 821 |
+
"step": 290
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.76,
|
| 825 |
+
"learning_rate": 6.208226221079692e-05,
|
| 826 |
+
"loss": 1.656,
|
| 827 |
+
"step": 295
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.76,
|
| 831 |
+
"eval_loss": 1.66847825050354,
|
| 832 |
+
"eval_runtime": 31.7918,
|
| 833 |
+
"eval_samples_per_second": 2.642,
|
| 834 |
+
"eval_steps_per_second": 0.346,
|
| 835 |
+
"step": 295
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.77,
|
| 839 |
+
"learning_rate": 6.143958868894601e-05,
|
| 840 |
+
"loss": 1.6407,
|
| 841 |
+
"step": 300
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.77,
|
| 845 |
+
"eval_loss": 1.6683858633041382,
|
| 846 |
+
"eval_runtime": 31.8114,
|
| 847 |
+
"eval_samples_per_second": 2.641,
|
| 848 |
+
"eval_steps_per_second": 0.346,
|
| 849 |
+
"step": 300
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.78,
|
| 853 |
+
"learning_rate": 6.079691516709511e-05,
|
| 854 |
+
"loss": 1.6468,
|
| 855 |
+
"step": 305
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.78,
|
| 859 |
+
"eval_loss": 1.6678352355957031,
|
| 860 |
+
"eval_runtime": 31.7975,
|
| 861 |
+
"eval_samples_per_second": 2.642,
|
| 862 |
+
"eval_steps_per_second": 0.346,
|
| 863 |
+
"step": 305
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.8,
|
| 867 |
+
"learning_rate": 6.015424164524421e-05,
|
| 868 |
+
"loss": 1.6579,
|
| 869 |
+
"step": 310
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.8,
|
| 873 |
+
"eval_loss": 1.6675294637680054,
|
| 874 |
+
"eval_runtime": 31.8059,
|
| 875 |
+
"eval_samples_per_second": 2.641,
|
| 876 |
+
"eval_steps_per_second": 0.346,
|
| 877 |
+
"step": 310
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.81,
|
| 881 |
+
"learning_rate": 5.951156812339333e-05,
|
| 882 |
+
"loss": 1.6331,
|
| 883 |
+
"step": 315
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.81,
|
| 887 |
+
"eval_loss": 1.6670397520065308,
|
| 888 |
+
"eval_runtime": 31.7994,
|
| 889 |
+
"eval_samples_per_second": 2.642,
|
| 890 |
+
"eval_steps_per_second": 0.346,
|
| 891 |
+
"step": 315
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.82,
|
| 895 |
+
"learning_rate": 5.886889460154242e-05,
|
| 896 |
+
"loss": 1.6634,
|
| 897 |
+
"step": 320
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.82,
|
| 901 |
+
"eval_loss": 1.6668330430984497,
|
| 902 |
+
"eval_runtime": 31.807,
|
| 903 |
+
"eval_samples_per_second": 2.641,
|
| 904 |
+
"eval_steps_per_second": 0.346,
|
| 905 |
+
"step": 320
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.84,
|
| 909 |
+
"learning_rate": 5.822622107969152e-05,
|
| 910 |
+
"loss": 1.6406,
|
| 911 |
+
"step": 325
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.84,
|
| 915 |
+
"eval_loss": 1.6668546199798584,
|
| 916 |
+
"eval_runtime": 31.8004,
|
| 917 |
+
"eval_samples_per_second": 2.641,
|
| 918 |
+
"eval_steps_per_second": 0.346,
|
| 919 |
+
"step": 325
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.85,
|
| 923 |
+
"learning_rate": 5.758354755784062e-05,
|
| 924 |
+
"loss": 1.6614,
|
| 925 |
+
"step": 330
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.85,
|
| 929 |
+
"eval_loss": 1.666812539100647,
|
| 930 |
+
"eval_runtime": 31.8023,
|
| 931 |
+
"eval_samples_per_second": 2.641,
|
| 932 |
+
"eval_steps_per_second": 0.346,
|
| 933 |
+
"step": 330
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.86,
|
| 937 |
+
"learning_rate": 5.694087403598972e-05,
|
| 938 |
+
"loss": 1.6598,
|
| 939 |
+
"step": 335
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.86,
|
| 943 |
+
"eval_loss": 1.666398048400879,
|
| 944 |
+
"eval_runtime": 31.8087,
|
| 945 |
+
"eval_samples_per_second": 2.641,
|
| 946 |
+
"eval_steps_per_second": 0.346,
|
| 947 |
+
"step": 335
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.87,
|
| 951 |
+
"learning_rate": 5.6298200514138824e-05,
|
| 952 |
+
"loss": 1.6698,
|
| 953 |
+
"step": 340
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.87,
|
| 957 |
+
"eval_loss": 1.6660391092300415,
|
| 958 |
+
"eval_runtime": 31.8016,
|
| 959 |
+
"eval_samples_per_second": 2.641,
|
| 960 |
+
"eval_steps_per_second": 0.346,
|
| 961 |
+
"step": 340
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.89,
|
| 965 |
+
"learning_rate": 5.5655526992287924e-05,
|
| 966 |
+
"loss": 1.6346,
|
| 967 |
+
"step": 345
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.89,
|
| 971 |
+
"eval_loss": 1.665901780128479,
|
| 972 |
+
"eval_runtime": 31.7878,
|
| 973 |
+
"eval_samples_per_second": 2.643,
|
| 974 |
+
"eval_steps_per_second": 0.346,
|
| 975 |
+
"step": 345
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.9,
|
| 979 |
+
"learning_rate": 5.501285347043702e-05,
|
| 980 |
+
"loss": 1.6617,
|
| 981 |
+
"step": 350
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.9,
|
| 985 |
+
"eval_loss": 1.666027307510376,
|
| 986 |
+
"eval_runtime": 31.7999,
|
| 987 |
+
"eval_samples_per_second": 2.642,
|
| 988 |
+
"eval_steps_per_second": 0.346,
|
| 989 |
+
"step": 350
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.91,
|
| 993 |
+
"learning_rate": 5.437017994858612e-05,
|
| 994 |
+
"loss": 1.6623,
|
| 995 |
+
"step": 355
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.91,
|
| 999 |
+
"eval_loss": 1.6658612489700317,
|
| 1000 |
+
"eval_runtime": 31.8128,
|
| 1001 |
+
"eval_samples_per_second": 2.64,
|
| 1002 |
+
"eval_steps_per_second": 0.346,
|
| 1003 |
+
"step": 355
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.93,
|
| 1007 |
+
"learning_rate": 5.372750642673522e-05,
|
| 1008 |
+
"loss": 1.6737,
|
| 1009 |
+
"step": 360
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.93,
|
| 1013 |
+
"eval_loss": 1.6656837463378906,
|
| 1014 |
+
"eval_runtime": 31.8094,
|
| 1015 |
+
"eval_samples_per_second": 2.641,
|
| 1016 |
+
"eval_steps_per_second": 0.346,
|
| 1017 |
+
"step": 360
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.94,
|
| 1021 |
+
"learning_rate": 5.308483290488432e-05,
|
| 1022 |
+
"loss": 1.6981,
|
| 1023 |
+
"step": 365
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.94,
|
| 1027 |
+
"eval_loss": 1.6653661727905273,
|
| 1028 |
+
"eval_runtime": 31.8031,
|
| 1029 |
+
"eval_samples_per_second": 2.641,
|
| 1030 |
+
"eval_steps_per_second": 0.346,
|
| 1031 |
+
"step": 365
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.95,
|
| 1035 |
+
"learning_rate": 5.244215938303342e-05,
|
| 1036 |
+
"loss": 1.6832,
|
| 1037 |
+
"step": 370
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.95,
|
| 1041 |
+
"eval_loss": 1.6652257442474365,
|
| 1042 |
+
"eval_runtime": 31.8077,
|
| 1043 |
+
"eval_samples_per_second": 2.641,
|
| 1044 |
+
"eval_steps_per_second": 0.346,
|
| 1045 |
+
"step": 370
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.96,
|
| 1049 |
+
"learning_rate": 5.1799485861182514e-05,
|
| 1050 |
+
"loss": 1.6925,
|
| 1051 |
+
"step": 375
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.96,
|
| 1055 |
+
"eval_loss": 1.664839267730713,
|
| 1056 |
+
"eval_runtime": 31.8082,
|
| 1057 |
+
"eval_samples_per_second": 2.641,
|
| 1058 |
+
"eval_steps_per_second": 0.346,
|
| 1059 |
+
"step": 375
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.98,
|
| 1063 |
+
"learning_rate": 5.1156812339331615e-05,
|
| 1064 |
+
"loss": 1.6721,
|
| 1065 |
+
"step": 380
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.98,
|
| 1069 |
+
"eval_loss": 1.6642415523529053,
|
| 1070 |
+
"eval_runtime": 31.7927,
|
| 1071 |
+
"eval_samples_per_second": 2.642,
|
| 1072 |
+
"eval_steps_per_second": 0.346,
|
| 1073 |
+
"step": 380
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.99,
|
| 1077 |
+
"learning_rate": 5.051413881748073e-05,
|
| 1078 |
+
"loss": 1.6208,
|
| 1079 |
+
"step": 385
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.99,
|
| 1083 |
+
"eval_loss": 1.6641273498535156,
|
| 1084 |
+
"eval_runtime": 31.8006,
|
| 1085 |
+
"eval_samples_per_second": 2.641,
|
| 1086 |
+
"eval_steps_per_second": 0.346,
|
| 1087 |
+
"step": 385
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.0,
|
| 1091 |
+
"learning_rate": 4.987146529562982e-05,
|
| 1092 |
+
"loss": 1.6519,
|
| 1093 |
+
"step": 390
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.0,
|
| 1097 |
+
"eval_loss": 1.6645455360412598,
|
| 1098 |
+
"eval_runtime": 31.8026,
|
| 1099 |
+
"eval_samples_per_second": 2.641,
|
| 1100 |
+
"eval_steps_per_second": 0.346,
|
| 1101 |
+
"step": 390
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.02,
|
| 1105 |
+
"learning_rate": 4.922879177377892e-05,
|
| 1106 |
+
"loss": 1.6581,
|
| 1107 |
+
"step": 395
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.02,
|
| 1111 |
+
"eval_loss": 1.6641591787338257,
|
| 1112 |
+
"eval_runtime": 31.8025,
|
| 1113 |
+
"eval_samples_per_second": 2.641,
|
| 1114 |
+
"eval_steps_per_second": 0.346,
|
| 1115 |
+
"step": 395
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.03,
|
| 1119 |
+
"learning_rate": 4.8586118251928024e-05,
|
| 1120 |
+
"loss": 1.6768,
|
| 1121 |
+
"step": 400
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.03,
|
| 1125 |
+
"eval_loss": 1.6637850999832153,
|
| 1126 |
+
"eval_runtime": 31.806,
|
| 1127 |
+
"eval_samples_per_second": 2.641,
|
| 1128 |
+
"eval_steps_per_second": 0.346,
|
| 1129 |
+
"step": 400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.04,
|
| 1133 |
+
"learning_rate": 4.7943444730077124e-05,
|
| 1134 |
+
"loss": 1.6257,
|
| 1135 |
+
"step": 405
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 1.04,
|
| 1139 |
+
"eval_loss": 1.6636526584625244,
|
| 1140 |
+
"eval_runtime": 31.8116,
|
| 1141 |
+
"eval_samples_per_second": 2.641,
|
| 1142 |
+
"eval_steps_per_second": 0.346,
|
| 1143 |
+
"step": 405
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.05,
|
| 1147 |
+
"learning_rate": 4.7300771208226225e-05,
|
| 1148 |
+
"loss": 1.6522,
|
| 1149 |
+
"step": 410
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.05,
|
| 1153 |
+
"eval_loss": 1.6634690761566162,
|
| 1154 |
+
"eval_runtime": 31.8063,
|
| 1155 |
+
"eval_samples_per_second": 2.641,
|
| 1156 |
+
"eval_steps_per_second": 0.346,
|
| 1157 |
+
"step": 410
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.07,
|
| 1161 |
+
"learning_rate": 4.6658097686375325e-05,
|
| 1162 |
+
"loss": 1.615,
|
| 1163 |
+
"step": 415
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 1.07,
|
| 1167 |
+
"eval_loss": 1.6637413501739502,
|
| 1168 |
+
"eval_runtime": 31.8115,
|
| 1169 |
+
"eval_samples_per_second": 2.641,
|
| 1170 |
+
"eval_steps_per_second": 0.346,
|
| 1171 |
+
"step": 415
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.08,
|
| 1175 |
+
"learning_rate": 4.6015424164524426e-05,
|
| 1176 |
+
"loss": 1.5967,
|
| 1177 |
+
"step": 420
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.08,
|
| 1181 |
+
"eval_loss": 1.6633188724517822,
|
| 1182 |
+
"eval_runtime": 31.8016,
|
| 1183 |
+
"eval_samples_per_second": 2.641,
|
| 1184 |
+
"eval_steps_per_second": 0.346,
|
| 1185 |
+
"step": 420
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.09,
|
| 1189 |
+
"learning_rate": 4.537275064267352e-05,
|
| 1190 |
+
"loss": 1.6708,
|
| 1191 |
+
"step": 425
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.09,
|
| 1195 |
+
"eval_loss": 1.6634286642074585,
|
| 1196 |
+
"eval_runtime": 31.8074,
|
| 1197 |
+
"eval_samples_per_second": 2.641,
|
| 1198 |
+
"eval_steps_per_second": 0.346,
|
| 1199 |
+
"step": 425
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.11,
|
| 1203 |
+
"learning_rate": 4.473007712082262e-05,
|
| 1204 |
+
"loss": 1.6696,
|
| 1205 |
+
"step": 430
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.11,
|
| 1209 |
+
"eval_loss": 1.663163661956787,
|
| 1210 |
+
"eval_runtime": 31.799,
|
| 1211 |
+
"eval_samples_per_second": 2.642,
|
| 1212 |
+
"eval_steps_per_second": 0.346,
|
| 1213 |
+
"step": 430
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.12,
|
| 1217 |
+
"learning_rate": 4.408740359897173e-05,
|
| 1218 |
+
"loss": 1.6344,
|
| 1219 |
+
"step": 435
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.12,
|
| 1223 |
+
"eval_loss": 1.6632493734359741,
|
| 1224 |
+
"eval_runtime": 31.8032,
|
| 1225 |
+
"eval_samples_per_second": 2.641,
|
| 1226 |
+
"eval_steps_per_second": 0.346,
|
| 1227 |
+
"step": 435
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.13,
|
| 1231 |
+
"learning_rate": 4.344473007712083e-05,
|
| 1232 |
+
"loss": 1.5922,
|
| 1233 |
+
"step": 440
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.13,
|
| 1237 |
+
"eval_loss": 1.6627737283706665,
|
| 1238 |
+
"eval_runtime": 31.8064,
|
| 1239 |
+
"eval_samples_per_second": 2.641,
|
| 1240 |
+
"eval_steps_per_second": 0.346,
|
| 1241 |
+
"step": 440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.14,
|
| 1245 |
+
"learning_rate": 4.280205655526993e-05,
|
| 1246 |
+
"loss": 1.6541,
|
| 1247 |
+
"step": 445
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.14,
|
| 1251 |
+
"eval_loss": 1.6630815267562866,
|
| 1252 |
+
"eval_runtime": 31.8083,
|
| 1253 |
+
"eval_samples_per_second": 2.641,
|
| 1254 |
+
"eval_steps_per_second": 0.346,
|
| 1255 |
+
"step": 445
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.16,
|
| 1259 |
+
"learning_rate": 4.215938303341902e-05,
|
| 1260 |
+
"loss": 1.6348,
|
| 1261 |
+
"step": 450
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.16,
|
| 1265 |
+
"eval_loss": 1.662713885307312,
|
| 1266 |
+
"eval_runtime": 31.7977,
|
| 1267 |
+
"eval_samples_per_second": 2.642,
|
| 1268 |
+
"eval_steps_per_second": 0.346,
|
| 1269 |
+
"step": 450
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.17,
|
| 1273 |
+
"learning_rate": 4.151670951156812e-05,
|
| 1274 |
+
"loss": 1.6444,
|
| 1275 |
+
"step": 455
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.17,
|
| 1279 |
+
"eval_loss": 1.6629937887191772,
|
| 1280 |
+
"eval_runtime": 31.799,
|
| 1281 |
+
"eval_samples_per_second": 2.642,
|
| 1282 |
+
"eval_steps_per_second": 0.346,
|
| 1283 |
+
"step": 455
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.18,
|
| 1287 |
+
"learning_rate": 4.0874035989717224e-05,
|
| 1288 |
+
"loss": 1.6629,
|
| 1289 |
+
"step": 460
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 1.18,
|
| 1293 |
+
"eval_loss": 1.6626592874526978,
|
| 1294 |
+
"eval_runtime": 31.8136,
|
| 1295 |
+
"eval_samples_per_second": 2.64,
|
| 1296 |
+
"eval_steps_per_second": 0.346,
|
| 1297 |
+
"step": 460
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.2,
|
| 1301 |
+
"learning_rate": 4.0231362467866324e-05,
|
| 1302 |
+
"loss": 1.6327,
|
| 1303 |
+
"step": 465
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 1.2,
|
| 1307 |
+
"eval_loss": 1.6625391244888306,
|
| 1308 |
+
"eval_runtime": 31.802,
|
| 1309 |
+
"eval_samples_per_second": 2.641,
|
| 1310 |
+
"eval_steps_per_second": 0.346,
|
| 1311 |
+
"step": 465
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.21,
|
| 1315 |
+
"learning_rate": 3.958868894601543e-05,
|
| 1316 |
+
"loss": 1.6236,
|
| 1317 |
+
"step": 470
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 1.21,
|
| 1321 |
+
"eval_loss": 1.6622934341430664,
|
| 1322 |
+
"eval_runtime": 31.8055,
|
| 1323 |
+
"eval_samples_per_second": 2.641,
|
| 1324 |
+
"eval_steps_per_second": 0.346,
|
| 1325 |
+
"step": 470
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.22,
|
| 1329 |
+
"learning_rate": 3.8946015424164526e-05,
|
| 1330 |
+
"loss": 1.6232,
|
| 1331 |
+
"step": 475
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 1.22,
|
| 1335 |
+
"eval_loss": 1.661791443824768,
|
| 1336 |
+
"eval_runtime": 31.8035,
|
| 1337 |
+
"eval_samples_per_second": 2.641,
|
| 1338 |
+
"eval_steps_per_second": 0.346,
|
| 1339 |
+
"step": 475
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.23,
|
| 1343 |
+
"learning_rate": 3.8303341902313626e-05,
|
| 1344 |
+
"loss": 1.6374,
|
| 1345 |
+
"step": 480
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 1.23,
|
| 1349 |
+
"eval_loss": 1.6618887186050415,
|
| 1350 |
+
"eval_runtime": 31.7892,
|
| 1351 |
+
"eval_samples_per_second": 2.642,
|
| 1352 |
+
"eval_steps_per_second": 0.346,
|
| 1353 |
+
"step": 480
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.25,
|
| 1357 |
+
"learning_rate": 3.766066838046273e-05,
|
| 1358 |
+
"loss": 1.6422,
|
| 1359 |
+
"step": 485
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 1.25,
|
| 1363 |
+
"eval_loss": 1.6620476245880127,
|
| 1364 |
+
"eval_runtime": 31.7974,
|
| 1365 |
+
"eval_samples_per_second": 2.642,
|
| 1366 |
+
"eval_steps_per_second": 0.346,
|
| 1367 |
+
"step": 485
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.26,
|
| 1371 |
+
"learning_rate": 3.701799485861183e-05,
|
| 1372 |
+
"loss": 1.631,
|
| 1373 |
+
"step": 490
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 1.26,
|
| 1377 |
+
"eval_loss": 1.6622774600982666,
|
| 1378 |
+
"eval_runtime": 31.7978,
|
| 1379 |
+
"eval_samples_per_second": 2.642,
|
| 1380 |
+
"eval_steps_per_second": 0.346,
|
| 1381 |
+
"step": 490
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.27,
|
| 1385 |
+
"learning_rate": 3.637532133676093e-05,
|
| 1386 |
+
"loss": 1.609,
|
| 1387 |
+
"step": 495
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 1.27,
|
| 1391 |
+
"eval_loss": 1.661568284034729,
|
| 1392 |
+
"eval_runtime": 31.8034,
|
| 1393 |
+
"eval_samples_per_second": 2.641,
|
| 1394 |
+
"eval_steps_per_second": 0.346,
|
| 1395 |
+
"step": 495
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.29,
|
| 1399 |
+
"learning_rate": 3.573264781491003e-05,
|
| 1400 |
+
"loss": 1.6444,
|
| 1401 |
+
"step": 500
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 1.29,
|
| 1405 |
+
"eval_loss": 1.6610949039459229,
|
| 1406 |
+
"eval_runtime": 31.8005,
|
| 1407 |
+
"eval_samples_per_second": 2.641,
|
| 1408 |
+
"eval_steps_per_second": 0.346,
|
| 1409 |
+
"step": 500
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.3,
|
| 1413 |
+
"learning_rate": 3.508997429305913e-05,
|
| 1414 |
+
"loss": 1.6387,
|
| 1415 |
+
"step": 505
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 1.3,
|
| 1419 |
+
"eval_loss": 1.6611486673355103,
|
| 1420 |
+
"eval_runtime": 31.8079,
|
| 1421 |
+
"eval_samples_per_second": 2.641,
|
| 1422 |
+
"eval_steps_per_second": 0.346,
|
| 1423 |
+
"step": 505
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.31,
|
| 1427 |
+
"learning_rate": 3.444730077120823e-05,
|
| 1428 |
+
"loss": 1.6507,
|
| 1429 |
+
"step": 510
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 1.31,
|
| 1433 |
+
"eval_loss": 1.661084532737732,
|
| 1434 |
+
"eval_runtime": 31.8028,
|
| 1435 |
+
"eval_samples_per_second": 2.641,
|
| 1436 |
+
"eval_steps_per_second": 0.346,
|
| 1437 |
+
"step": 510
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.32,
|
| 1441 |
+
"learning_rate": 3.380462724935733e-05,
|
| 1442 |
+
"loss": 1.6377,
|
| 1443 |
+
"step": 515
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.32,
|
| 1447 |
+
"eval_loss": 1.6610103845596313,
|
| 1448 |
+
"eval_runtime": 31.8101,
|
| 1449 |
+
"eval_samples_per_second": 2.641,
|
| 1450 |
+
"eval_steps_per_second": 0.346,
|
| 1451 |
+
"step": 515
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.34,
|
| 1455 |
+
"learning_rate": 3.316195372750643e-05,
|
| 1456 |
+
"loss": 1.6351,
|
| 1457 |
+
"step": 520
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.34,
|
| 1461 |
+
"eval_loss": 1.6608690023422241,
|
| 1462 |
+
"eval_runtime": 31.7986,
|
| 1463 |
+
"eval_samples_per_second": 2.642,
|
| 1464 |
+
"eval_steps_per_second": 0.346,
|
| 1465 |
+
"step": 520
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.35,
|
| 1469 |
+
"learning_rate": 3.251928020565553e-05,
|
| 1470 |
+
"loss": 1.6196,
|
| 1471 |
+
"step": 525
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 1.35,
|
| 1475 |
+
"eval_loss": 1.6606587171554565,
|
| 1476 |
+
"eval_runtime": 31.8015,
|
| 1477 |
+
"eval_samples_per_second": 2.641,
|
| 1478 |
+
"eval_steps_per_second": 0.346,
|
| 1479 |
+
"step": 525
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.36,
|
| 1483 |
+
"learning_rate": 3.1876606683804625e-05,
|
| 1484 |
+
"loss": 1.646,
|
| 1485 |
+
"step": 530
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.36,
|
| 1489 |
+
"eval_loss": 1.6605886220932007,
|
| 1490 |
+
"eval_runtime": 31.804,
|
| 1491 |
+
"eval_samples_per_second": 2.641,
|
| 1492 |
+
"eval_steps_per_second": 0.346,
|
| 1493 |
+
"step": 530
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.38,
|
| 1497 |
+
"learning_rate": 3.1233933161953726e-05,
|
| 1498 |
+
"loss": 1.6824,
|
| 1499 |
+
"step": 535
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.38,
|
| 1503 |
+
"eval_loss": 1.6603879928588867,
|
| 1504 |
+
"eval_runtime": 31.8111,
|
| 1505 |
+
"eval_samples_per_second": 2.641,
|
| 1506 |
+
"eval_steps_per_second": 0.346,
|
| 1507 |
+
"step": 535
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.39,
|
| 1511 |
+
"learning_rate": 3.059125964010283e-05,
|
| 1512 |
+
"loss": 1.6115,
|
| 1513 |
+
"step": 540
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 1.39,
|
| 1517 |
+
"eval_loss": 1.660337209701538,
|
| 1518 |
+
"eval_runtime": 31.805,
|
| 1519 |
+
"eval_samples_per_second": 2.641,
|
| 1520 |
+
"eval_steps_per_second": 0.346,
|
| 1521 |
+
"step": 540
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.4,
|
| 1525 |
+
"learning_rate": 2.994858611825193e-05,
|
| 1526 |
+
"loss": 1.6243,
|
| 1527 |
+
"step": 545
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 1.4,
|
| 1531 |
+
"eval_loss": 1.6606225967407227,
|
| 1532 |
+
"eval_runtime": 31.808,
|
| 1533 |
+
"eval_samples_per_second": 2.641,
|
| 1534 |
+
"eval_steps_per_second": 0.346,
|
| 1535 |
+
"step": 545
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.41,
|
| 1539 |
+
"learning_rate": 2.930591259640103e-05,
|
| 1540 |
+
"loss": 1.6486,
|
| 1541 |
+
"step": 550
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 1.41,
|
| 1545 |
+
"eval_loss": 1.6604374647140503,
|
| 1546 |
+
"eval_runtime": 31.8072,
|
| 1547 |
+
"eval_samples_per_second": 2.641,
|
| 1548 |
+
"eval_steps_per_second": 0.346,
|
| 1549 |
+
"step": 550
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.43,
|
| 1553 |
+
"learning_rate": 2.866323907455013e-05,
|
| 1554 |
+
"loss": 1.6865,
|
| 1555 |
+
"step": 555
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 1.43,
|
| 1559 |
+
"eval_loss": 1.6601544618606567,
|
| 1560 |
+
"eval_runtime": 31.8069,
|
| 1561 |
+
"eval_samples_per_second": 2.641,
|
| 1562 |
+
"eval_steps_per_second": 0.346,
|
| 1563 |
+
"step": 555
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.44,
|
| 1567 |
+
"learning_rate": 2.802056555269923e-05,
|
| 1568 |
+
"loss": 1.6616,
|
| 1569 |
+
"step": 560
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.44,
|
| 1573 |
+
"eval_loss": 1.660386562347412,
|
| 1574 |
+
"eval_runtime": 31.803,
|
| 1575 |
+
"eval_samples_per_second": 2.641,
|
| 1576 |
+
"eval_steps_per_second": 0.346,
|
| 1577 |
+
"step": 560
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.45,
|
| 1581 |
+
"learning_rate": 2.737789203084833e-05,
|
| 1582 |
+
"loss": 1.6336,
|
| 1583 |
+
"step": 565
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 1.45,
|
| 1587 |
+
"eval_loss": 1.660247802734375,
|
| 1588 |
+
"eval_runtime": 31.8084,
|
| 1589 |
+
"eval_samples_per_second": 2.641,
|
| 1590 |
+
"eval_steps_per_second": 0.346,
|
| 1591 |
+
"step": 565
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.47,
|
| 1595 |
+
"learning_rate": 2.673521850899743e-05,
|
| 1596 |
+
"loss": 1.6699,
|
| 1597 |
+
"step": 570
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 1.47,
|
| 1601 |
+
"eval_loss": 1.660292148590088,
|
| 1602 |
+
"eval_runtime": 31.8031,
|
| 1603 |
+
"eval_samples_per_second": 2.641,
|
| 1604 |
+
"eval_steps_per_second": 0.346,
|
| 1605 |
+
"step": 570
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.48,
|
| 1609 |
+
"learning_rate": 2.6092544987146534e-05,
|
| 1610 |
+
"loss": 1.6472,
|
| 1611 |
+
"step": 575
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 1.48,
|
| 1615 |
+
"eval_loss": 1.6598683595657349,
|
| 1616 |
+
"eval_runtime": 31.8181,
|
| 1617 |
+
"eval_samples_per_second": 2.64,
|
| 1618 |
+
"eval_steps_per_second": 0.346,
|
| 1619 |
+
"step": 575
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.49,
|
| 1623 |
+
"learning_rate": 2.5449871465295634e-05,
|
| 1624 |
+
"loss": 1.6723,
|
| 1625 |
+
"step": 580
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.49,
|
| 1629 |
+
"eval_loss": 1.6599065065383911,
|
| 1630 |
+
"eval_runtime": 31.8124,
|
| 1631 |
+
"eval_samples_per_second": 2.64,
|
| 1632 |
+
"eval_steps_per_second": 0.346,
|
| 1633 |
+
"step": 580
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.5,
|
| 1637 |
+
"learning_rate": 2.480719794344473e-05,
|
| 1638 |
+
"loss": 1.663,
|
| 1639 |
+
"step": 585
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 1.5,
|
| 1643 |
+
"eval_loss": 1.6599762439727783,
|
| 1644 |
+
"eval_runtime": 31.8175,
|
| 1645 |
+
"eval_samples_per_second": 2.64,
|
| 1646 |
+
"eval_steps_per_second": 0.346,
|
| 1647 |
+
"step": 585
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.52,
|
| 1651 |
+
"learning_rate": 2.4164524421593832e-05,
|
| 1652 |
+
"loss": 1.6519,
|
| 1653 |
+
"step": 590
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 1.52,
|
| 1657 |
+
"eval_loss": 1.6599925756454468,
|
| 1658 |
+
"eval_runtime": 31.8209,
|
| 1659 |
+
"eval_samples_per_second": 2.64,
|
| 1660 |
+
"eval_steps_per_second": 0.346,
|
| 1661 |
+
"step": 590
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.53,
|
| 1665 |
+
"learning_rate": 2.3521850899742933e-05,
|
| 1666 |
+
"loss": 1.6345,
|
| 1667 |
+
"step": 595
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 1.53,
|
| 1671 |
+
"eval_loss": 1.6600078344345093,
|
| 1672 |
+
"eval_runtime": 31.8031,
|
| 1673 |
+
"eval_samples_per_second": 2.641,
|
| 1674 |
+
"eval_steps_per_second": 0.346,
|
| 1675 |
+
"step": 595
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.54,
|
| 1679 |
+
"learning_rate": 2.2879177377892033e-05,
|
| 1680 |
+
"loss": 1.654,
|
| 1681 |
+
"step": 600
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 1.54,
|
| 1685 |
+
"eval_loss": 1.6599884033203125,
|
| 1686 |
+
"eval_runtime": 31.8281,
|
| 1687 |
+
"eval_samples_per_second": 2.639,
|
| 1688 |
+
"eval_steps_per_second": 0.346,
|
| 1689 |
+
"step": 600
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.56,
|
| 1693 |
+
"learning_rate": 2.2236503856041134e-05,
|
| 1694 |
+
"loss": 1.691,
|
| 1695 |
+
"step": 605
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 1.56,
|
| 1699 |
+
"eval_loss": 1.6599520444869995,
|
| 1700 |
+
"eval_runtime": 31.8168,
|
| 1701 |
+
"eval_samples_per_second": 2.64,
|
| 1702 |
+
"eval_steps_per_second": 0.346,
|
| 1703 |
+
"step": 605
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.57,
|
| 1707 |
+
"learning_rate": 2.159383033419023e-05,
|
| 1708 |
+
"loss": 1.6714,
|
| 1709 |
+
"step": 610
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 1.57,
|
| 1713 |
+
"eval_loss": 1.659857988357544,
|
| 1714 |
+
"eval_runtime": 31.8153,
|
| 1715 |
+
"eval_samples_per_second": 2.64,
|
| 1716 |
+
"eval_steps_per_second": 0.346,
|
| 1717 |
+
"step": 610
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.58,
|
| 1721 |
+
"learning_rate": 2.095115681233933e-05,
|
| 1722 |
+
"loss": 1.5977,
|
| 1723 |
+
"step": 615
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 1.58,
|
| 1727 |
+
"eval_loss": 1.6596992015838623,
|
| 1728 |
+
"eval_runtime": 31.8087,
|
| 1729 |
+
"eval_samples_per_second": 2.641,
|
| 1730 |
+
"eval_steps_per_second": 0.346,
|
| 1731 |
+
"step": 615
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.59,
|
| 1735 |
+
"learning_rate": 2.0308483290488432e-05,
|
| 1736 |
+
"loss": 1.6429,
|
| 1737 |
+
"step": 620
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.59,
|
| 1741 |
+
"eval_loss": 1.6595497131347656,
|
| 1742 |
+
"eval_runtime": 31.8151,
|
| 1743 |
+
"eval_samples_per_second": 2.64,
|
| 1744 |
+
"eval_steps_per_second": 0.346,
|
| 1745 |
+
"step": 620
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.61,
|
| 1749 |
+
"learning_rate": 1.9665809768637533e-05,
|
| 1750 |
+
"loss": 1.6091,
|
| 1751 |
+
"step": 625
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 1.61,
|
| 1755 |
+
"eval_loss": 1.6597559452056885,
|
| 1756 |
+
"eval_runtime": 31.8076,
|
| 1757 |
+
"eval_samples_per_second": 2.641,
|
| 1758 |
+
"eval_steps_per_second": 0.346,
|
| 1759 |
+
"step": 625
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.62,
|
| 1763 |
+
"learning_rate": 1.9023136246786633e-05,
|
| 1764 |
+
"loss": 1.5956,
|
| 1765 |
+
"step": 630
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 1.62,
|
| 1769 |
+
"eval_loss": 1.6593599319458008,
|
| 1770 |
+
"eval_runtime": 31.8058,
|
| 1771 |
+
"eval_samples_per_second": 2.641,
|
| 1772 |
+
"eval_steps_per_second": 0.346,
|
| 1773 |
+
"step": 630
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.63,
|
| 1777 |
+
"learning_rate": 1.8380462724935734e-05,
|
| 1778 |
+
"loss": 1.6697,
|
| 1779 |
+
"step": 635
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.63,
|
| 1783 |
+
"eval_loss": 1.6592466831207275,
|
| 1784 |
+
"eval_runtime": 31.8589,
|
| 1785 |
+
"eval_samples_per_second": 2.637,
|
| 1786 |
+
"eval_steps_per_second": 0.345,
|
| 1787 |
+
"step": 635
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.65,
|
| 1791 |
+
"learning_rate": 1.7737789203084834e-05,
|
| 1792 |
+
"loss": 1.6535,
|
| 1793 |
+
"step": 640
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.65,
|
| 1797 |
+
"eval_loss": 1.6592165231704712,
|
| 1798 |
+
"eval_runtime": 31.8225,
|
| 1799 |
+
"eval_samples_per_second": 2.64,
|
| 1800 |
+
"eval_steps_per_second": 0.346,
|
| 1801 |
+
"step": 640
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.66,
|
| 1805 |
+
"learning_rate": 1.7095115681233935e-05,
|
| 1806 |
+
"loss": 1.6722,
|
| 1807 |
+
"step": 645
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 1.66,
|
| 1811 |
+
"eval_loss": 1.659324049949646,
|
| 1812 |
+
"eval_runtime": 31.8388,
|
| 1813 |
+
"eval_samples_per_second": 2.638,
|
| 1814 |
+
"eval_steps_per_second": 0.345,
|
| 1815 |
+
"step": 645
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.67,
|
| 1819 |
+
"learning_rate": 1.6452442159383032e-05,
|
| 1820 |
+
"loss": 1.6347,
|
| 1821 |
+
"step": 650
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 1.67,
|
| 1825 |
+
"eval_loss": 1.6590396165847778,
|
| 1826 |
+
"eval_runtime": 31.8174,
|
| 1827 |
+
"eval_samples_per_second": 2.64,
|
| 1828 |
+
"eval_steps_per_second": 0.346,
|
| 1829 |
+
"step": 650
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.68,
|
| 1833 |
+
"learning_rate": 1.5809768637532136e-05,
|
| 1834 |
+
"loss": 1.6223,
|
| 1835 |
+
"step": 655
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.68,
|
| 1839 |
+
"eval_loss": 1.658969521522522,
|
| 1840 |
+
"eval_runtime": 31.8275,
|
| 1841 |
+
"eval_samples_per_second": 2.639,
|
| 1842 |
+
"eval_steps_per_second": 0.346,
|
| 1843 |
+
"step": 655
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.7,
|
| 1847 |
+
"learning_rate": 1.5167095115681235e-05,
|
| 1848 |
+
"loss": 1.6309,
|
| 1849 |
+
"step": 660
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.7,
|
| 1853 |
+
"eval_loss": 1.6587274074554443,
|
| 1854 |
+
"eval_runtime": 31.8146,
|
| 1855 |
+
"eval_samples_per_second": 2.64,
|
| 1856 |
+
"eval_steps_per_second": 0.346,
|
| 1857 |
+
"step": 660
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.71,
|
| 1861 |
+
"learning_rate": 1.4524421593830334e-05,
|
| 1862 |
+
"loss": 1.6499,
|
| 1863 |
+
"step": 665
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.71,
|
| 1867 |
+
"eval_loss": 1.65865957736969,
|
| 1868 |
+
"eval_runtime": 31.8091,
|
| 1869 |
+
"eval_samples_per_second": 2.641,
|
| 1870 |
+
"eval_steps_per_second": 0.346,
|
| 1871 |
+
"step": 665
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.72,
|
| 1875 |
+
"learning_rate": 1.3881748071979436e-05,
|
| 1876 |
+
"loss": 1.6713,
|
| 1877 |
+
"step": 670
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 1.72,
|
| 1881 |
+
"eval_loss": 1.6586016416549683,
|
| 1882 |
+
"eval_runtime": 31.8229,
|
| 1883 |
+
"eval_samples_per_second": 2.64,
|
| 1884 |
+
"eval_steps_per_second": 0.346,
|
| 1885 |
+
"step": 670
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.74,
|
| 1889 |
+
"learning_rate": 1.3239074550128535e-05,
|
| 1890 |
+
"loss": 1.6348,
|
| 1891 |
+
"step": 675
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.74,
|
| 1895 |
+
"eval_loss": 1.6584962606430054,
|
| 1896 |
+
"eval_runtime": 31.8035,
|
| 1897 |
+
"eval_samples_per_second": 2.641,
|
| 1898 |
+
"eval_steps_per_second": 0.346,
|
| 1899 |
+
"step": 675
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.75,
|
| 1903 |
+
"learning_rate": 1.2596401028277636e-05,
|
| 1904 |
+
"loss": 1.6447,
|
| 1905 |
+
"step": 680
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.75,
|
| 1909 |
+
"eval_loss": 1.6585614681243896,
|
| 1910 |
+
"eval_runtime": 31.8101,
|
| 1911 |
+
"eval_samples_per_second": 2.641,
|
| 1912 |
+
"eval_steps_per_second": 0.346,
|
| 1913 |
+
"step": 680
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.76,
|
| 1917 |
+
"learning_rate": 1.1953727506426736e-05,
|
| 1918 |
+
"loss": 1.6511,
|
| 1919 |
+
"step": 685
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.76,
|
| 1923 |
+
"eval_loss": 1.6583601236343384,
|
| 1924 |
+
"eval_runtime": 31.8125,
|
| 1925 |
+
"eval_samples_per_second": 2.64,
|
| 1926 |
+
"eval_steps_per_second": 0.346,
|
| 1927 |
+
"step": 685
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.77,
|
| 1931 |
+
"learning_rate": 1.1311053984575835e-05,
|
| 1932 |
+
"loss": 1.6496,
|
| 1933 |
+
"step": 690
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.77,
|
| 1937 |
+
"eval_loss": 1.6583328247070312,
|
| 1938 |
+
"eval_runtime": 31.8179,
|
| 1939 |
+
"eval_samples_per_second": 2.64,
|
| 1940 |
+
"eval_steps_per_second": 0.346,
|
| 1941 |
+
"step": 690
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.79,
|
| 1945 |
+
"learning_rate": 1.0668380462724936e-05,
|
| 1946 |
+
"loss": 1.6421,
|
| 1947 |
+
"step": 695
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 1.79,
|
| 1951 |
+
"eval_loss": 1.6583188772201538,
|
| 1952 |
+
"eval_runtime": 31.8165,
|
| 1953 |
+
"eval_samples_per_second": 2.64,
|
| 1954 |
+
"eval_steps_per_second": 0.346,
|
| 1955 |
+
"step": 695
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.8,
|
| 1959 |
+
"learning_rate": 1.0025706940874038e-05,
|
| 1960 |
+
"loss": 1.6126,
|
| 1961 |
+
"step": 700
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 1.8,
|
| 1965 |
+
"eval_loss": 1.6580705642700195,
|
| 1966 |
+
"eval_runtime": 31.8164,
|
| 1967 |
+
"eval_samples_per_second": 2.64,
|
| 1968 |
+
"eval_steps_per_second": 0.346,
|
| 1969 |
+
"step": 700
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.81,
|
| 1973 |
+
"learning_rate": 9.383033419023137e-06,
|
| 1974 |
+
"loss": 1.6226,
|
| 1975 |
+
"step": 705
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 1.81,
|
| 1979 |
+
"eval_loss": 1.6584465503692627,
|
| 1980 |
+
"eval_runtime": 31.816,
|
| 1981 |
+
"eval_samples_per_second": 2.64,
|
| 1982 |
+
"eval_steps_per_second": 0.346,
|
| 1983 |
+
"step": 705
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.83,
|
| 1987 |
+
"learning_rate": 8.740359897172237e-06,
|
| 1988 |
+
"loss": 1.6923,
|
| 1989 |
+
"step": 710
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.83,
|
| 1993 |
+
"eval_loss": 1.658342957496643,
|
| 1994 |
+
"eval_runtime": 31.8215,
|
| 1995 |
+
"eval_samples_per_second": 2.64,
|
| 1996 |
+
"eval_steps_per_second": 0.346,
|
| 1997 |
+
"step": 710
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.84,
|
| 2001 |
+
"learning_rate": 8.097686375321336e-06,
|
| 2002 |
+
"loss": 1.6224,
|
| 2003 |
+
"step": 715
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 1.84,
|
| 2007 |
+
"eval_loss": 1.6582502126693726,
|
| 2008 |
+
"eval_runtime": 31.812,
|
| 2009 |
+
"eval_samples_per_second": 2.641,
|
| 2010 |
+
"eval_steps_per_second": 0.346,
|
| 2011 |
+
"step": 715
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.85,
|
| 2015 |
+
"learning_rate": 7.4550128534704376e-06,
|
| 2016 |
+
"loss": 1.6587,
|
| 2017 |
+
"step": 720
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 1.85,
|
| 2021 |
+
"eval_loss": 1.658232569694519,
|
| 2022 |
+
"eval_runtime": 31.8059,
|
| 2023 |
+
"eval_samples_per_second": 2.641,
|
| 2024 |
+
"eval_steps_per_second": 0.346,
|
| 2025 |
+
"step": 720
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.86,
|
| 2029 |
+
"learning_rate": 6.812339331619537e-06,
|
| 2030 |
+
"loss": 1.6641,
|
| 2031 |
+
"step": 725
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 1.86,
|
| 2035 |
+
"eval_loss": 1.6582419872283936,
|
| 2036 |
+
"eval_runtime": 31.81,
|
| 2037 |
+
"eval_samples_per_second": 2.641,
|
| 2038 |
+
"eval_steps_per_second": 0.346,
|
| 2039 |
+
"step": 725
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.88,
|
| 2043 |
+
"learning_rate": 6.169665809768638e-06,
|
| 2044 |
+
"loss": 1.6419,
|
| 2045 |
+
"step": 730
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.88,
|
| 2049 |
+
"eval_loss": 1.6582107543945312,
|
| 2050 |
+
"eval_runtime": 31.833,
|
| 2051 |
+
"eval_samples_per_second": 2.639,
|
| 2052 |
+
"eval_steps_per_second": 0.346,
|
| 2053 |
+
"step": 730
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.89,
|
| 2057 |
+
"learning_rate": 5.526992287917738e-06,
|
| 2058 |
+
"loss": 1.652,
|
| 2059 |
+
"step": 735
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 1.89,
|
| 2063 |
+
"eval_loss": 1.6582270860671997,
|
| 2064 |
+
"eval_runtime": 31.8801,
|
| 2065 |
+
"eval_samples_per_second": 2.635,
|
| 2066 |
+
"eval_steps_per_second": 0.345,
|
| 2067 |
+
"step": 735
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.9,
|
| 2071 |
+
"learning_rate": 4.884318766066838e-06,
|
| 2072 |
+
"loss": 1.6487,
|
| 2073 |
+
"step": 740
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.9,
|
| 2077 |
+
"eval_loss": 1.6582915782928467,
|
| 2078 |
+
"eval_runtime": 31.8265,
|
| 2079 |
+
"eval_samples_per_second": 2.639,
|
| 2080 |
+
"eval_steps_per_second": 0.346,
|
| 2081 |
+
"step": 740
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.92,
|
| 2085 |
+
"learning_rate": 4.241645244215939e-06,
|
| 2086 |
+
"loss": 1.6245,
|
| 2087 |
+
"step": 745
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 1.92,
|
| 2091 |
+
"eval_loss": 1.658047080039978,
|
| 2092 |
+
"eval_runtime": 31.8109,
|
| 2093 |
+
"eval_samples_per_second": 2.641,
|
| 2094 |
+
"eval_steps_per_second": 0.346,
|
| 2095 |
+
"step": 745
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.93,
|
| 2099 |
+
"learning_rate": 3.598971722365039e-06,
|
| 2100 |
+
"loss": 1.6553,
|
| 2101 |
+
"step": 750
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 1.93,
|
| 2105 |
+
"eval_loss": 1.6578683853149414,
|
| 2106 |
+
"eval_runtime": 31.8025,
|
| 2107 |
+
"eval_samples_per_second": 2.641,
|
| 2108 |
+
"eval_steps_per_second": 0.346,
|
| 2109 |
+
"step": 750
|
| 2110 |
+
}
|
| 2111 |
+
],
|
| 2112 |
+
"logging_steps": 5,
|
| 2113 |
+
"max_steps": 778,
|
| 2114 |
+
"num_train_epochs": 2,
|
| 2115 |
+
"save_steps": 10,
|
| 2116 |
+
"total_flos": 2.4364649130491904e+17,
|
| 2117 |
+
"trial_name": null,
|
| 2118 |
+
"trial_params": null
|
| 2119 |
+
}
|
checkpoint-750/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc6a8542abd91027de58ebfccafdf919108680707834fe188d91cae077ef8e9
|
| 3 |
+
size 4600
|
checkpoint-760/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.5.0
|
checkpoint-760/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-760/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36e33012a5495bd07e00b9e59e90574c650664430061690402da200b176d8494
|
| 3 |
+
size 16794200
|
checkpoint-760/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86d459429a5d6f3262e6fbe255a2ee4932b6410a1a80593cdce61cd73243aef6
|
| 3 |
+
size 33663866
|
checkpoint-760/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6973cbf09e3463c2ccbdf4a6bd0f0551c3955052f339950757f1b93f508f887a
|
| 3 |
+
size 14244
|
checkpoint-760/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bf90aa5789bb0cee3a7c1f3d247be3d2ae5fb54b24e3bbd48be306d070a5211
|
| 3 |
+
size 1064
|
checkpoint-760/trainer_state.json
ADDED
|
@@ -0,0 +1,2147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.6578683853149414,
|
| 3 |
+
"best_model_checkpoint": "/scratch/kwamea/llama-output/checkpoint-750",
|
| 4 |
+
"epoch": 1.9537275064267352,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 760,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 9.93573264781491e-05,
|
| 14 |
+
"loss": 1.9824,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"eval_loss": 1.954728126525879,
|
| 20 |
+
"eval_runtime": 31.6803,
|
| 21 |
+
"eval_samples_per_second": 2.651,
|
| 22 |
+
"eval_steps_per_second": 0.347,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"learning_rate": 9.87146529562982e-05,
|
| 28 |
+
"loss": 1.9249,
|
| 29 |
+
"step": 10
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"eval_loss": 1.8934264183044434,
|
| 34 |
+
"eval_runtime": 31.7798,
|
| 35 |
+
"eval_samples_per_second": 2.643,
|
| 36 |
+
"eval_steps_per_second": 0.346,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04,
|
| 41 |
+
"learning_rate": 9.80719794344473e-05,
|
| 42 |
+
"loss": 1.8609,
|
| 43 |
+
"step": 15
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.04,
|
| 47 |
+
"eval_loss": 1.8421852588653564,
|
| 48 |
+
"eval_runtime": 31.7999,
|
| 49 |
+
"eval_samples_per_second": 2.642,
|
| 50 |
+
"eval_steps_per_second": 0.346,
|
| 51 |
+
"step": 15
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"learning_rate": 9.742930591259641e-05,
|
| 56 |
+
"loss": 1.8268,
|
| 57 |
+
"step": 20
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.05,
|
| 61 |
+
"eval_loss": 1.8279638290405273,
|
| 62 |
+
"eval_runtime": 31.8095,
|
| 63 |
+
"eval_samples_per_second": 2.641,
|
| 64 |
+
"eval_steps_per_second": 0.346,
|
| 65 |
+
"step": 20
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06,
|
| 69 |
+
"learning_rate": 9.67866323907455e-05,
|
| 70 |
+
"loss": 1.8349,
|
| 71 |
+
"step": 25
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.06,
|
| 75 |
+
"eval_loss": 1.813267469406128,
|
| 76 |
+
"eval_runtime": 31.8291,
|
| 77 |
+
"eval_samples_per_second": 2.639,
|
| 78 |
+
"eval_steps_per_second": 0.346,
|
| 79 |
+
"step": 25
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08,
|
| 83 |
+
"learning_rate": 9.61439588688946e-05,
|
| 84 |
+
"loss": 1.8239,
|
| 85 |
+
"step": 30
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.08,
|
| 89 |
+
"eval_loss": 1.8008779287338257,
|
| 90 |
+
"eval_runtime": 31.82,
|
| 91 |
+
"eval_samples_per_second": 2.64,
|
| 92 |
+
"eval_steps_per_second": 0.346,
|
| 93 |
+
"step": 30
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 9.550128534704372e-05,
|
| 98 |
+
"loss": 1.7177,
|
| 99 |
+
"step": 35
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.09,
|
| 103 |
+
"eval_loss": 1.789797067642212,
|
| 104 |
+
"eval_runtime": 31.8423,
|
| 105 |
+
"eval_samples_per_second": 2.638,
|
| 106 |
+
"eval_steps_per_second": 0.345,
|
| 107 |
+
"step": 35
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1,
|
| 111 |
+
"learning_rate": 9.485861182519281e-05,
|
| 112 |
+
"loss": 1.7962,
|
| 113 |
+
"step": 40
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.1,
|
| 117 |
+
"eval_loss": 1.7808287143707275,
|
| 118 |
+
"eval_runtime": 31.8387,
|
| 119 |
+
"eval_samples_per_second": 2.638,
|
| 120 |
+
"eval_steps_per_second": 0.345,
|
| 121 |
+
"step": 40
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.12,
|
| 125 |
+
"learning_rate": 9.421593830334192e-05,
|
| 126 |
+
"loss": 1.715,
|
| 127 |
+
"step": 45
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.12,
|
| 131 |
+
"eval_loss": 1.771236777305603,
|
| 132 |
+
"eval_runtime": 31.8526,
|
| 133 |
+
"eval_samples_per_second": 2.637,
|
| 134 |
+
"eval_steps_per_second": 0.345,
|
| 135 |
+
"step": 45
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13,
|
| 139 |
+
"learning_rate": 9.357326478149101e-05,
|
| 140 |
+
"loss": 1.7577,
|
| 141 |
+
"step": 50
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.13,
|
| 145 |
+
"eval_loss": 1.7619521617889404,
|
| 146 |
+
"eval_runtime": 31.828,
|
| 147 |
+
"eval_samples_per_second": 2.639,
|
| 148 |
+
"eval_steps_per_second": 0.346,
|
| 149 |
+
"step": 50
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.14,
|
| 153 |
+
"learning_rate": 9.29305912596401e-05,
|
| 154 |
+
"loss": 1.7323,
|
| 155 |
+
"step": 55
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.14,
|
| 159 |
+
"eval_loss": 1.7440986633300781,
|
| 160 |
+
"eval_runtime": 31.8301,
|
| 161 |
+
"eval_samples_per_second": 2.639,
|
| 162 |
+
"eval_steps_per_second": 0.346,
|
| 163 |
+
"step": 55
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.15,
|
| 167 |
+
"learning_rate": 9.228791773778921e-05,
|
| 168 |
+
"loss": 1.7122,
|
| 169 |
+
"step": 60
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.15,
|
| 173 |
+
"eval_loss": 1.712996006011963,
|
| 174 |
+
"eval_runtime": 31.8185,
|
| 175 |
+
"eval_samples_per_second": 2.64,
|
| 176 |
+
"eval_steps_per_second": 0.346,
|
| 177 |
+
"step": 60
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17,
|
| 181 |
+
"learning_rate": 9.16452442159383e-05,
|
| 182 |
+
"loss": 1.7042,
|
| 183 |
+
"step": 65
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.17,
|
| 187 |
+
"eval_loss": 1.7101707458496094,
|
| 188 |
+
"eval_runtime": 31.8153,
|
| 189 |
+
"eval_samples_per_second": 2.64,
|
| 190 |
+
"eval_steps_per_second": 0.346,
|
| 191 |
+
"step": 65
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.18,
|
| 195 |
+
"learning_rate": 9.100257069408741e-05,
|
| 196 |
+
"loss": 1.7242,
|
| 197 |
+
"step": 70
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.18,
|
| 201 |
+
"eval_loss": 1.7038702964782715,
|
| 202 |
+
"eval_runtime": 31.8191,
|
| 203 |
+
"eval_samples_per_second": 2.64,
|
| 204 |
+
"eval_steps_per_second": 0.346,
|
| 205 |
+
"step": 70
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19,
|
| 209 |
+
"learning_rate": 9.03598971722365e-05,
|
| 210 |
+
"loss": 1.7033,
|
| 211 |
+
"step": 75
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.19,
|
| 215 |
+
"eval_loss": 1.7004183530807495,
|
| 216 |
+
"eval_runtime": 31.811,
|
| 217 |
+
"eval_samples_per_second": 2.641,
|
| 218 |
+
"eval_steps_per_second": 0.346,
|
| 219 |
+
"step": 75
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21,
|
| 223 |
+
"learning_rate": 8.97172236503856e-05,
|
| 224 |
+
"loss": 1.6934,
|
| 225 |
+
"step": 80
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.21,
|
| 229 |
+
"eval_loss": 1.6985355615615845,
|
| 230 |
+
"eval_runtime": 31.8221,
|
| 231 |
+
"eval_samples_per_second": 2.64,
|
| 232 |
+
"eval_steps_per_second": 0.346,
|
| 233 |
+
"step": 80
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22,
|
| 237 |
+
"learning_rate": 8.907455012853471e-05,
|
| 238 |
+
"loss": 1.6443,
|
| 239 |
+
"step": 85
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.22,
|
| 243 |
+
"eval_loss": 1.696852684020996,
|
| 244 |
+
"eval_runtime": 31.8219,
|
| 245 |
+
"eval_samples_per_second": 2.64,
|
| 246 |
+
"eval_steps_per_second": 0.346,
|
| 247 |
+
"step": 85
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.23,
|
| 251 |
+
"learning_rate": 8.84318766066838e-05,
|
| 252 |
+
"loss": 1.7008,
|
| 253 |
+
"step": 90
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.23,
|
| 257 |
+
"eval_loss": 1.695594072341919,
|
| 258 |
+
"eval_runtime": 31.8205,
|
| 259 |
+
"eval_samples_per_second": 2.64,
|
| 260 |
+
"eval_steps_per_second": 0.346,
|
| 261 |
+
"step": 90
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.24,
|
| 265 |
+
"learning_rate": 8.778920308483291e-05,
|
| 266 |
+
"loss": 1.6873,
|
| 267 |
+
"step": 95
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.24,
|
| 271 |
+
"eval_loss": 1.6928850412368774,
|
| 272 |
+
"eval_runtime": 31.814,
|
| 273 |
+
"eval_samples_per_second": 2.64,
|
| 274 |
+
"eval_steps_per_second": 0.346,
|
| 275 |
+
"step": 95
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.26,
|
| 279 |
+
"learning_rate": 8.7146529562982e-05,
|
| 280 |
+
"loss": 1.6721,
|
| 281 |
+
"step": 100
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.26,
|
| 285 |
+
"eval_loss": 1.6919386386871338,
|
| 286 |
+
"eval_runtime": 31.8127,
|
| 287 |
+
"eval_samples_per_second": 2.64,
|
| 288 |
+
"eval_steps_per_second": 0.346,
|
| 289 |
+
"step": 100
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.27,
|
| 293 |
+
"learning_rate": 8.650385604113111e-05,
|
| 294 |
+
"loss": 1.6669,
|
| 295 |
+
"step": 105
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.27,
|
| 299 |
+
"eval_loss": 1.6905940771102905,
|
| 300 |
+
"eval_runtime": 31.8874,
|
| 301 |
+
"eval_samples_per_second": 2.634,
|
| 302 |
+
"eval_steps_per_second": 0.345,
|
| 303 |
+
"step": 105
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.28,
|
| 307 |
+
"learning_rate": 8.586118251928022e-05,
|
| 308 |
+
"loss": 1.7009,
|
| 309 |
+
"step": 110
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.28,
|
| 313 |
+
"eval_loss": 1.689422607421875,
|
| 314 |
+
"eval_runtime": 31.8489,
|
| 315 |
+
"eval_samples_per_second": 2.637,
|
| 316 |
+
"eval_steps_per_second": 0.345,
|
| 317 |
+
"step": 110
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.3,
|
| 321 |
+
"learning_rate": 8.521850899742931e-05,
|
| 322 |
+
"loss": 1.7151,
|
| 323 |
+
"step": 115
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.3,
|
| 327 |
+
"eval_loss": 1.688527226448059,
|
| 328 |
+
"eval_runtime": 31.8318,
|
| 329 |
+
"eval_samples_per_second": 2.639,
|
| 330 |
+
"eval_steps_per_second": 0.346,
|
| 331 |
+
"step": 115
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.31,
|
| 335 |
+
"learning_rate": 8.457583547557842e-05,
|
| 336 |
+
"loss": 1.7165,
|
| 337 |
+
"step": 120
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.31,
|
| 341 |
+
"eval_loss": 1.686748743057251,
|
| 342 |
+
"eval_runtime": 31.835,
|
| 343 |
+
"eval_samples_per_second": 2.639,
|
| 344 |
+
"eval_steps_per_second": 0.346,
|
| 345 |
+
"step": 120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.32,
|
| 349 |
+
"learning_rate": 8.393316195372751e-05,
|
| 350 |
+
"loss": 1.7015,
|
| 351 |
+
"step": 125
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.32,
|
| 355 |
+
"eval_loss": 1.6855812072753906,
|
| 356 |
+
"eval_runtime": 31.8269,
|
| 357 |
+
"eval_samples_per_second": 2.639,
|
| 358 |
+
"eval_steps_per_second": 0.346,
|
| 359 |
+
"step": 125
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.33,
|
| 363 |
+
"learning_rate": 8.32904884318766e-05,
|
| 364 |
+
"loss": 1.6818,
|
| 365 |
+
"step": 130
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.33,
|
| 369 |
+
"eval_loss": 1.6846078634262085,
|
| 370 |
+
"eval_runtime": 31.8617,
|
| 371 |
+
"eval_samples_per_second": 2.636,
|
| 372 |
+
"eval_steps_per_second": 0.345,
|
| 373 |
+
"step": 130
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.35,
|
| 377 |
+
"learning_rate": 8.264781491002571e-05,
|
| 378 |
+
"loss": 1.7151,
|
| 379 |
+
"step": 135
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.35,
|
| 383 |
+
"eval_loss": 1.6845166683197021,
|
| 384 |
+
"eval_runtime": 31.8631,
|
| 385 |
+
"eval_samples_per_second": 2.636,
|
| 386 |
+
"eval_steps_per_second": 0.345,
|
| 387 |
+
"step": 135
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.36,
|
| 391 |
+
"learning_rate": 8.200514138817481e-05,
|
| 392 |
+
"loss": 1.6667,
|
| 393 |
+
"step": 140
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.36,
|
| 397 |
+
"eval_loss": 1.6832246780395508,
|
| 398 |
+
"eval_runtime": 31.8276,
|
| 399 |
+
"eval_samples_per_second": 2.639,
|
| 400 |
+
"eval_steps_per_second": 0.346,
|
| 401 |
+
"step": 140
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.37,
|
| 405 |
+
"learning_rate": 8.136246786632391e-05,
|
| 406 |
+
"loss": 1.6586,
|
| 407 |
+
"step": 145
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.37,
|
| 411 |
+
"eval_loss": 1.6824573278427124,
|
| 412 |
+
"eval_runtime": 31.8115,
|
| 413 |
+
"eval_samples_per_second": 2.641,
|
| 414 |
+
"eval_steps_per_second": 0.346,
|
| 415 |
+
"step": 145
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.39,
|
| 419 |
+
"learning_rate": 8.071979434447301e-05,
|
| 420 |
+
"loss": 1.6999,
|
| 421 |
+
"step": 150
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.39,
|
| 425 |
+
"eval_loss": 1.681317687034607,
|
| 426 |
+
"eval_runtime": 31.805,
|
| 427 |
+
"eval_samples_per_second": 2.641,
|
| 428 |
+
"eval_steps_per_second": 0.346,
|
| 429 |
+
"step": 150
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4,
|
| 433 |
+
"learning_rate": 8.007712082262212e-05,
|
| 434 |
+
"loss": 1.6894,
|
| 435 |
+
"step": 155
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.4,
|
| 439 |
+
"eval_loss": 1.6812355518341064,
|
| 440 |
+
"eval_runtime": 31.8039,
|
| 441 |
+
"eval_samples_per_second": 2.641,
|
| 442 |
+
"eval_steps_per_second": 0.346,
|
| 443 |
+
"step": 155
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.41,
|
| 447 |
+
"learning_rate": 7.943444730077121e-05,
|
| 448 |
+
"loss": 1.6669,
|
| 449 |
+
"step": 160
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.41,
|
| 453 |
+
"eval_loss": 1.679802656173706,
|
| 454 |
+
"eval_runtime": 31.8021,
|
| 455 |
+
"eval_samples_per_second": 2.641,
|
| 456 |
+
"eval_steps_per_second": 0.346,
|
| 457 |
+
"step": 160
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.42,
|
| 461 |
+
"learning_rate": 7.87917737789203e-05,
|
| 462 |
+
"loss": 1.6481,
|
| 463 |
+
"step": 165
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.42,
|
| 467 |
+
"eval_loss": 1.679994821548462,
|
| 468 |
+
"eval_runtime": 31.8201,
|
| 469 |
+
"eval_samples_per_second": 2.64,
|
| 470 |
+
"eval_steps_per_second": 0.346,
|
| 471 |
+
"step": 165
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.44,
|
| 475 |
+
"learning_rate": 7.814910025706941e-05,
|
| 476 |
+
"loss": 1.7042,
|
| 477 |
+
"step": 170
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.44,
|
| 481 |
+
"eval_loss": 1.6786224842071533,
|
| 482 |
+
"eval_runtime": 31.8184,
|
| 483 |
+
"eval_samples_per_second": 2.64,
|
| 484 |
+
"eval_steps_per_second": 0.346,
|
| 485 |
+
"step": 170
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.45,
|
| 489 |
+
"learning_rate": 7.750642673521852e-05,
|
| 490 |
+
"loss": 1.6564,
|
| 491 |
+
"step": 175
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.45,
|
| 495 |
+
"eval_loss": 1.6783201694488525,
|
| 496 |
+
"eval_runtime": 31.8137,
|
| 497 |
+
"eval_samples_per_second": 2.64,
|
| 498 |
+
"eval_steps_per_second": 0.346,
|
| 499 |
+
"step": 175
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.46,
|
| 503 |
+
"learning_rate": 7.686375321336761e-05,
|
| 504 |
+
"loss": 1.6714,
|
| 505 |
+
"step": 180
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.46,
|
| 509 |
+
"eval_loss": 1.677714228630066,
|
| 510 |
+
"eval_runtime": 31.804,
|
| 511 |
+
"eval_samples_per_second": 2.641,
|
| 512 |
+
"eval_steps_per_second": 0.346,
|
| 513 |
+
"step": 180
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.48,
|
| 517 |
+
"learning_rate": 7.622107969151672e-05,
|
| 518 |
+
"loss": 1.6705,
|
| 519 |
+
"step": 185
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.48,
|
| 523 |
+
"eval_loss": 1.6772773265838623,
|
| 524 |
+
"eval_runtime": 31.8077,
|
| 525 |
+
"eval_samples_per_second": 2.641,
|
| 526 |
+
"eval_steps_per_second": 0.346,
|
| 527 |
+
"step": 185
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.49,
|
| 531 |
+
"learning_rate": 7.557840616966581e-05,
|
| 532 |
+
"loss": 1.6624,
|
| 533 |
+
"step": 190
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.49,
|
| 537 |
+
"eval_loss": 1.6766114234924316,
|
| 538 |
+
"eval_runtime": 31.8164,
|
| 539 |
+
"eval_samples_per_second": 2.64,
|
| 540 |
+
"eval_steps_per_second": 0.346,
|
| 541 |
+
"step": 190
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.5,
|
| 545 |
+
"learning_rate": 7.493573264781492e-05,
|
| 546 |
+
"loss": 1.6415,
|
| 547 |
+
"step": 195
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.5,
|
| 551 |
+
"eval_loss": 1.675940752029419,
|
| 552 |
+
"eval_runtime": 31.8124,
|
| 553 |
+
"eval_samples_per_second": 2.64,
|
| 554 |
+
"eval_steps_per_second": 0.346,
|
| 555 |
+
"step": 195
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.51,
|
| 559 |
+
"learning_rate": 7.429305912596401e-05,
|
| 560 |
+
"loss": 1.6633,
|
| 561 |
+
"step": 200
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.51,
|
| 565 |
+
"eval_loss": 1.6751865148544312,
|
| 566 |
+
"eval_runtime": 31.8123,
|
| 567 |
+
"eval_samples_per_second": 2.64,
|
| 568 |
+
"eval_steps_per_second": 0.346,
|
| 569 |
+
"step": 200
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.53,
|
| 573 |
+
"learning_rate": 7.365038560411311e-05,
|
| 574 |
+
"loss": 1.6142,
|
| 575 |
+
"step": 205
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.53,
|
| 579 |
+
"eval_loss": 1.6750575304031372,
|
| 580 |
+
"eval_runtime": 31.8049,
|
| 581 |
+
"eval_samples_per_second": 2.641,
|
| 582 |
+
"eval_steps_per_second": 0.346,
|
| 583 |
+
"step": 205
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.54,
|
| 587 |
+
"learning_rate": 7.300771208226222e-05,
|
| 588 |
+
"loss": 1.6736,
|
| 589 |
+
"step": 210
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.54,
|
| 593 |
+
"eval_loss": 1.6746423244476318,
|
| 594 |
+
"eval_runtime": 31.8111,
|
| 595 |
+
"eval_samples_per_second": 2.641,
|
| 596 |
+
"eval_steps_per_second": 0.346,
|
| 597 |
+
"step": 210
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.55,
|
| 601 |
+
"learning_rate": 7.236503856041131e-05,
|
| 602 |
+
"loss": 1.6414,
|
| 603 |
+
"step": 215
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.55,
|
| 607 |
+
"eval_loss": 1.6740491390228271,
|
| 608 |
+
"eval_runtime": 31.8083,
|
| 609 |
+
"eval_samples_per_second": 2.641,
|
| 610 |
+
"eval_steps_per_second": 0.346,
|
| 611 |
+
"step": 215
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.57,
|
| 615 |
+
"learning_rate": 7.172236503856042e-05,
|
| 616 |
+
"loss": 1.6725,
|
| 617 |
+
"step": 220
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.57,
|
| 621 |
+
"eval_loss": 1.673694372177124,
|
| 622 |
+
"eval_runtime": 31.8025,
|
| 623 |
+
"eval_samples_per_second": 2.641,
|
| 624 |
+
"eval_steps_per_second": 0.346,
|
| 625 |
+
"step": 220
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.58,
|
| 629 |
+
"learning_rate": 7.107969151670951e-05,
|
| 630 |
+
"loss": 1.679,
|
| 631 |
+
"step": 225
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.58,
|
| 635 |
+
"eval_loss": 1.6733818054199219,
|
| 636 |
+
"eval_runtime": 31.8077,
|
| 637 |
+
"eval_samples_per_second": 2.641,
|
| 638 |
+
"eval_steps_per_second": 0.346,
|
| 639 |
+
"step": 225
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.59,
|
| 643 |
+
"learning_rate": 7.043701799485862e-05,
|
| 644 |
+
"loss": 1.7204,
|
| 645 |
+
"step": 230
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.59,
|
| 649 |
+
"eval_loss": 1.6725033521652222,
|
| 650 |
+
"eval_runtime": 31.8079,
|
| 651 |
+
"eval_samples_per_second": 2.641,
|
| 652 |
+
"eval_steps_per_second": 0.346,
|
| 653 |
+
"step": 230
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.6,
|
| 657 |
+
"learning_rate": 6.979434447300771e-05,
|
| 658 |
+
"loss": 1.6816,
|
| 659 |
+
"step": 235
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.6,
|
| 663 |
+
"eval_loss": 1.67205011844635,
|
| 664 |
+
"eval_runtime": 31.809,
|
| 665 |
+
"eval_samples_per_second": 2.641,
|
| 666 |
+
"eval_steps_per_second": 0.346,
|
| 667 |
+
"step": 235
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.62,
|
| 671 |
+
"learning_rate": 6.91516709511568e-05,
|
| 672 |
+
"loss": 1.634,
|
| 673 |
+
"step": 240
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.62,
|
| 677 |
+
"eval_loss": 1.6717994213104248,
|
| 678 |
+
"eval_runtime": 31.8075,
|
| 679 |
+
"eval_samples_per_second": 2.641,
|
| 680 |
+
"eval_steps_per_second": 0.346,
|
| 681 |
+
"step": 240
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.63,
|
| 685 |
+
"learning_rate": 6.850899742930593e-05,
|
| 686 |
+
"loss": 1.6761,
|
| 687 |
+
"step": 245
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.63,
|
| 691 |
+
"eval_loss": 1.6714757680892944,
|
| 692 |
+
"eval_runtime": 31.8052,
|
| 693 |
+
"eval_samples_per_second": 2.641,
|
| 694 |
+
"eval_steps_per_second": 0.346,
|
| 695 |
+
"step": 245
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.64,
|
| 699 |
+
"learning_rate": 6.786632390745502e-05,
|
| 700 |
+
"loss": 1.6996,
|
| 701 |
+
"step": 250
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.64,
|
| 705 |
+
"eval_loss": 1.671559453010559,
|
| 706 |
+
"eval_runtime": 31.8089,
|
| 707 |
+
"eval_samples_per_second": 2.641,
|
| 708 |
+
"eval_steps_per_second": 0.346,
|
| 709 |
+
"step": 250
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.66,
|
| 713 |
+
"learning_rate": 6.722365038560411e-05,
|
| 714 |
+
"loss": 1.6302,
|
| 715 |
+
"step": 255
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.66,
|
| 719 |
+
"eval_loss": 1.6711652278900146,
|
| 720 |
+
"eval_runtime": 31.8105,
|
| 721 |
+
"eval_samples_per_second": 2.641,
|
| 722 |
+
"eval_steps_per_second": 0.346,
|
| 723 |
+
"step": 255
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.67,
|
| 727 |
+
"learning_rate": 6.658097686375322e-05,
|
| 728 |
+
"loss": 1.6611,
|
| 729 |
+
"step": 260
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.67,
|
| 733 |
+
"eval_loss": 1.6704061031341553,
|
| 734 |
+
"eval_runtime": 31.8135,
|
| 735 |
+
"eval_samples_per_second": 2.64,
|
| 736 |
+
"eval_steps_per_second": 0.346,
|
| 737 |
+
"step": 260
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.68,
|
| 741 |
+
"learning_rate": 6.593830334190231e-05,
|
| 742 |
+
"loss": 1.6586,
|
| 743 |
+
"step": 265
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.68,
|
| 747 |
+
"eval_loss": 1.6705658435821533,
|
| 748 |
+
"eval_runtime": 31.7998,
|
| 749 |
+
"eval_samples_per_second": 2.642,
|
| 750 |
+
"eval_steps_per_second": 0.346,
|
| 751 |
+
"step": 265
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.69,
|
| 755 |
+
"learning_rate": 6.529562982005142e-05,
|
| 756 |
+
"loss": 1.6838,
|
| 757 |
+
"step": 270
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.69,
|
| 761 |
+
"eval_loss": 1.6697953939437866,
|
| 762 |
+
"eval_runtime": 31.7994,
|
| 763 |
+
"eval_samples_per_second": 2.642,
|
| 764 |
+
"eval_steps_per_second": 0.346,
|
| 765 |
+
"step": 270
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.71,
|
| 769 |
+
"learning_rate": 6.465295629820052e-05,
|
| 770 |
+
"loss": 1.6499,
|
| 771 |
+
"step": 275
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.71,
|
| 775 |
+
"eval_loss": 1.669343113899231,
|
| 776 |
+
"eval_runtime": 31.8147,
|
| 777 |
+
"eval_samples_per_second": 2.64,
|
| 778 |
+
"eval_steps_per_second": 0.346,
|
| 779 |
+
"step": 275
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.72,
|
| 783 |
+
"learning_rate": 6.401028277634962e-05,
|
| 784 |
+
"loss": 1.6424,
|
| 785 |
+
"step": 280
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.72,
|
| 789 |
+
"eval_loss": 1.6693596839904785,
|
| 790 |
+
"eval_runtime": 31.8155,
|
| 791 |
+
"eval_samples_per_second": 2.64,
|
| 792 |
+
"eval_steps_per_second": 0.346,
|
| 793 |
+
"step": 280
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.73,
|
| 797 |
+
"learning_rate": 6.336760925449872e-05,
|
| 798 |
+
"loss": 1.6238,
|
| 799 |
+
"step": 285
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.73,
|
| 803 |
+
"eval_loss": 1.669128179550171,
|
| 804 |
+
"eval_runtime": 31.8219,
|
| 805 |
+
"eval_samples_per_second": 2.64,
|
| 806 |
+
"eval_steps_per_second": 0.346,
|
| 807 |
+
"step": 285
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.75,
|
| 811 |
+
"learning_rate": 6.272493573264781e-05,
|
| 812 |
+
"loss": 1.6538,
|
| 813 |
+
"step": 290
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.75,
|
| 817 |
+
"eval_loss": 1.6691263914108276,
|
| 818 |
+
"eval_runtime": 31.81,
|
| 819 |
+
"eval_samples_per_second": 2.641,
|
| 820 |
+
"eval_steps_per_second": 0.346,
|
| 821 |
+
"step": 290
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.76,
|
| 825 |
+
"learning_rate": 6.208226221079692e-05,
|
| 826 |
+
"loss": 1.656,
|
| 827 |
+
"step": 295
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.76,
|
| 831 |
+
"eval_loss": 1.66847825050354,
|
| 832 |
+
"eval_runtime": 31.7918,
|
| 833 |
+
"eval_samples_per_second": 2.642,
|
| 834 |
+
"eval_steps_per_second": 0.346,
|
| 835 |
+
"step": 295
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.77,
|
| 839 |
+
"learning_rate": 6.143958868894601e-05,
|
| 840 |
+
"loss": 1.6407,
|
| 841 |
+
"step": 300
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.77,
|
| 845 |
+
"eval_loss": 1.6683858633041382,
|
| 846 |
+
"eval_runtime": 31.8114,
|
| 847 |
+
"eval_samples_per_second": 2.641,
|
| 848 |
+
"eval_steps_per_second": 0.346,
|
| 849 |
+
"step": 300
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.78,
|
| 853 |
+
"learning_rate": 6.079691516709511e-05,
|
| 854 |
+
"loss": 1.6468,
|
| 855 |
+
"step": 305
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.78,
|
| 859 |
+
"eval_loss": 1.6678352355957031,
|
| 860 |
+
"eval_runtime": 31.7975,
|
| 861 |
+
"eval_samples_per_second": 2.642,
|
| 862 |
+
"eval_steps_per_second": 0.346,
|
| 863 |
+
"step": 305
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.8,
|
| 867 |
+
"learning_rate": 6.015424164524421e-05,
|
| 868 |
+
"loss": 1.6579,
|
| 869 |
+
"step": 310
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.8,
|
| 873 |
+
"eval_loss": 1.6675294637680054,
|
| 874 |
+
"eval_runtime": 31.8059,
|
| 875 |
+
"eval_samples_per_second": 2.641,
|
| 876 |
+
"eval_steps_per_second": 0.346,
|
| 877 |
+
"step": 310
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.81,
|
| 881 |
+
"learning_rate": 5.951156812339333e-05,
|
| 882 |
+
"loss": 1.6331,
|
| 883 |
+
"step": 315
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.81,
|
| 887 |
+
"eval_loss": 1.6670397520065308,
|
| 888 |
+
"eval_runtime": 31.7994,
|
| 889 |
+
"eval_samples_per_second": 2.642,
|
| 890 |
+
"eval_steps_per_second": 0.346,
|
| 891 |
+
"step": 315
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.82,
|
| 895 |
+
"learning_rate": 5.886889460154242e-05,
|
| 896 |
+
"loss": 1.6634,
|
| 897 |
+
"step": 320
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.82,
|
| 901 |
+
"eval_loss": 1.6668330430984497,
|
| 902 |
+
"eval_runtime": 31.807,
|
| 903 |
+
"eval_samples_per_second": 2.641,
|
| 904 |
+
"eval_steps_per_second": 0.346,
|
| 905 |
+
"step": 320
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.84,
|
| 909 |
+
"learning_rate": 5.822622107969152e-05,
|
| 910 |
+
"loss": 1.6406,
|
| 911 |
+
"step": 325
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.84,
|
| 915 |
+
"eval_loss": 1.6668546199798584,
|
| 916 |
+
"eval_runtime": 31.8004,
|
| 917 |
+
"eval_samples_per_second": 2.641,
|
| 918 |
+
"eval_steps_per_second": 0.346,
|
| 919 |
+
"step": 325
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.85,
|
| 923 |
+
"learning_rate": 5.758354755784062e-05,
|
| 924 |
+
"loss": 1.6614,
|
| 925 |
+
"step": 330
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.85,
|
| 929 |
+
"eval_loss": 1.666812539100647,
|
| 930 |
+
"eval_runtime": 31.8023,
|
| 931 |
+
"eval_samples_per_second": 2.641,
|
| 932 |
+
"eval_steps_per_second": 0.346,
|
| 933 |
+
"step": 330
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.86,
|
| 937 |
+
"learning_rate": 5.694087403598972e-05,
|
| 938 |
+
"loss": 1.6598,
|
| 939 |
+
"step": 335
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.86,
|
| 943 |
+
"eval_loss": 1.666398048400879,
|
| 944 |
+
"eval_runtime": 31.8087,
|
| 945 |
+
"eval_samples_per_second": 2.641,
|
| 946 |
+
"eval_steps_per_second": 0.346,
|
| 947 |
+
"step": 335
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.87,
|
| 951 |
+
"learning_rate": 5.6298200514138824e-05,
|
| 952 |
+
"loss": 1.6698,
|
| 953 |
+
"step": 340
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.87,
|
| 957 |
+
"eval_loss": 1.6660391092300415,
|
| 958 |
+
"eval_runtime": 31.8016,
|
| 959 |
+
"eval_samples_per_second": 2.641,
|
| 960 |
+
"eval_steps_per_second": 0.346,
|
| 961 |
+
"step": 340
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.89,
|
| 965 |
+
"learning_rate": 5.5655526992287924e-05,
|
| 966 |
+
"loss": 1.6346,
|
| 967 |
+
"step": 345
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.89,
|
| 971 |
+
"eval_loss": 1.665901780128479,
|
| 972 |
+
"eval_runtime": 31.7878,
|
| 973 |
+
"eval_samples_per_second": 2.643,
|
| 974 |
+
"eval_steps_per_second": 0.346,
|
| 975 |
+
"step": 345
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.9,
|
| 979 |
+
"learning_rate": 5.501285347043702e-05,
|
| 980 |
+
"loss": 1.6617,
|
| 981 |
+
"step": 350
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.9,
|
| 985 |
+
"eval_loss": 1.666027307510376,
|
| 986 |
+
"eval_runtime": 31.7999,
|
| 987 |
+
"eval_samples_per_second": 2.642,
|
| 988 |
+
"eval_steps_per_second": 0.346,
|
| 989 |
+
"step": 350
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.91,
|
| 993 |
+
"learning_rate": 5.437017994858612e-05,
|
| 994 |
+
"loss": 1.6623,
|
| 995 |
+
"step": 355
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.91,
|
| 999 |
+
"eval_loss": 1.6658612489700317,
|
| 1000 |
+
"eval_runtime": 31.8128,
|
| 1001 |
+
"eval_samples_per_second": 2.64,
|
| 1002 |
+
"eval_steps_per_second": 0.346,
|
| 1003 |
+
"step": 355
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.93,
|
| 1007 |
+
"learning_rate": 5.372750642673522e-05,
|
| 1008 |
+
"loss": 1.6737,
|
| 1009 |
+
"step": 360
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.93,
|
| 1013 |
+
"eval_loss": 1.6656837463378906,
|
| 1014 |
+
"eval_runtime": 31.8094,
|
| 1015 |
+
"eval_samples_per_second": 2.641,
|
| 1016 |
+
"eval_steps_per_second": 0.346,
|
| 1017 |
+
"step": 360
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.94,
|
| 1021 |
+
"learning_rate": 5.308483290488432e-05,
|
| 1022 |
+
"loss": 1.6981,
|
| 1023 |
+
"step": 365
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.94,
|
| 1027 |
+
"eval_loss": 1.6653661727905273,
|
| 1028 |
+
"eval_runtime": 31.8031,
|
| 1029 |
+
"eval_samples_per_second": 2.641,
|
| 1030 |
+
"eval_steps_per_second": 0.346,
|
| 1031 |
+
"step": 365
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.95,
|
| 1035 |
+
"learning_rate": 5.244215938303342e-05,
|
| 1036 |
+
"loss": 1.6832,
|
| 1037 |
+
"step": 370
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.95,
|
| 1041 |
+
"eval_loss": 1.6652257442474365,
|
| 1042 |
+
"eval_runtime": 31.8077,
|
| 1043 |
+
"eval_samples_per_second": 2.641,
|
| 1044 |
+
"eval_steps_per_second": 0.346,
|
| 1045 |
+
"step": 370
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.96,
|
| 1049 |
+
"learning_rate": 5.1799485861182514e-05,
|
| 1050 |
+
"loss": 1.6925,
|
| 1051 |
+
"step": 375
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.96,
|
| 1055 |
+
"eval_loss": 1.664839267730713,
|
| 1056 |
+
"eval_runtime": 31.8082,
|
| 1057 |
+
"eval_samples_per_second": 2.641,
|
| 1058 |
+
"eval_steps_per_second": 0.346,
|
| 1059 |
+
"step": 375
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.98,
|
| 1063 |
+
"learning_rate": 5.1156812339331615e-05,
|
| 1064 |
+
"loss": 1.6721,
|
| 1065 |
+
"step": 380
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.98,
|
| 1069 |
+
"eval_loss": 1.6642415523529053,
|
| 1070 |
+
"eval_runtime": 31.7927,
|
| 1071 |
+
"eval_samples_per_second": 2.642,
|
| 1072 |
+
"eval_steps_per_second": 0.346,
|
| 1073 |
+
"step": 380
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.99,
|
| 1077 |
+
"learning_rate": 5.051413881748073e-05,
|
| 1078 |
+
"loss": 1.6208,
|
| 1079 |
+
"step": 385
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.99,
|
| 1083 |
+
"eval_loss": 1.6641273498535156,
|
| 1084 |
+
"eval_runtime": 31.8006,
|
| 1085 |
+
"eval_samples_per_second": 2.641,
|
| 1086 |
+
"eval_steps_per_second": 0.346,
|
| 1087 |
+
"step": 385
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.0,
|
| 1091 |
+
"learning_rate": 4.987146529562982e-05,
|
| 1092 |
+
"loss": 1.6519,
|
| 1093 |
+
"step": 390
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.0,
|
| 1097 |
+
"eval_loss": 1.6645455360412598,
|
| 1098 |
+
"eval_runtime": 31.8026,
|
| 1099 |
+
"eval_samples_per_second": 2.641,
|
| 1100 |
+
"eval_steps_per_second": 0.346,
|
| 1101 |
+
"step": 390
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.02,
|
| 1105 |
+
"learning_rate": 4.922879177377892e-05,
|
| 1106 |
+
"loss": 1.6581,
|
| 1107 |
+
"step": 395
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.02,
|
| 1111 |
+
"eval_loss": 1.6641591787338257,
|
| 1112 |
+
"eval_runtime": 31.8025,
|
| 1113 |
+
"eval_samples_per_second": 2.641,
|
| 1114 |
+
"eval_steps_per_second": 0.346,
|
| 1115 |
+
"step": 395
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.03,
|
| 1119 |
+
"learning_rate": 4.8586118251928024e-05,
|
| 1120 |
+
"loss": 1.6768,
|
| 1121 |
+
"step": 400
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.03,
|
| 1125 |
+
"eval_loss": 1.6637850999832153,
|
| 1126 |
+
"eval_runtime": 31.806,
|
| 1127 |
+
"eval_samples_per_second": 2.641,
|
| 1128 |
+
"eval_steps_per_second": 0.346,
|
| 1129 |
+
"step": 400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.04,
|
| 1133 |
+
"learning_rate": 4.7943444730077124e-05,
|
| 1134 |
+
"loss": 1.6257,
|
| 1135 |
+
"step": 405
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 1.04,
|
| 1139 |
+
"eval_loss": 1.6636526584625244,
|
| 1140 |
+
"eval_runtime": 31.8116,
|
| 1141 |
+
"eval_samples_per_second": 2.641,
|
| 1142 |
+
"eval_steps_per_second": 0.346,
|
| 1143 |
+
"step": 405
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.05,
|
| 1147 |
+
"learning_rate": 4.7300771208226225e-05,
|
| 1148 |
+
"loss": 1.6522,
|
| 1149 |
+
"step": 410
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.05,
|
| 1153 |
+
"eval_loss": 1.6634690761566162,
|
| 1154 |
+
"eval_runtime": 31.8063,
|
| 1155 |
+
"eval_samples_per_second": 2.641,
|
| 1156 |
+
"eval_steps_per_second": 0.346,
|
| 1157 |
+
"step": 410
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.07,
|
| 1161 |
+
"learning_rate": 4.6658097686375325e-05,
|
| 1162 |
+
"loss": 1.615,
|
| 1163 |
+
"step": 415
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 1.07,
|
| 1167 |
+
"eval_loss": 1.6637413501739502,
|
| 1168 |
+
"eval_runtime": 31.8115,
|
| 1169 |
+
"eval_samples_per_second": 2.641,
|
| 1170 |
+
"eval_steps_per_second": 0.346,
|
| 1171 |
+
"step": 415
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.08,
|
| 1175 |
+
"learning_rate": 4.6015424164524426e-05,
|
| 1176 |
+
"loss": 1.5967,
|
| 1177 |
+
"step": 420
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.08,
|
| 1181 |
+
"eval_loss": 1.6633188724517822,
|
| 1182 |
+
"eval_runtime": 31.8016,
|
| 1183 |
+
"eval_samples_per_second": 2.641,
|
| 1184 |
+
"eval_steps_per_second": 0.346,
|
| 1185 |
+
"step": 420
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.09,
|
| 1189 |
+
"learning_rate": 4.537275064267352e-05,
|
| 1190 |
+
"loss": 1.6708,
|
| 1191 |
+
"step": 425
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.09,
|
| 1195 |
+
"eval_loss": 1.6634286642074585,
|
| 1196 |
+
"eval_runtime": 31.8074,
|
| 1197 |
+
"eval_samples_per_second": 2.641,
|
| 1198 |
+
"eval_steps_per_second": 0.346,
|
| 1199 |
+
"step": 425
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.11,
|
| 1203 |
+
"learning_rate": 4.473007712082262e-05,
|
| 1204 |
+
"loss": 1.6696,
|
| 1205 |
+
"step": 430
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.11,
|
| 1209 |
+
"eval_loss": 1.663163661956787,
|
| 1210 |
+
"eval_runtime": 31.799,
|
| 1211 |
+
"eval_samples_per_second": 2.642,
|
| 1212 |
+
"eval_steps_per_second": 0.346,
|
| 1213 |
+
"step": 430
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.12,
|
| 1217 |
+
"learning_rate": 4.408740359897173e-05,
|
| 1218 |
+
"loss": 1.6344,
|
| 1219 |
+
"step": 435
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.12,
|
| 1223 |
+
"eval_loss": 1.6632493734359741,
|
| 1224 |
+
"eval_runtime": 31.8032,
|
| 1225 |
+
"eval_samples_per_second": 2.641,
|
| 1226 |
+
"eval_steps_per_second": 0.346,
|
| 1227 |
+
"step": 435
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.13,
|
| 1231 |
+
"learning_rate": 4.344473007712083e-05,
|
| 1232 |
+
"loss": 1.5922,
|
| 1233 |
+
"step": 440
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.13,
|
| 1237 |
+
"eval_loss": 1.6627737283706665,
|
| 1238 |
+
"eval_runtime": 31.8064,
|
| 1239 |
+
"eval_samples_per_second": 2.641,
|
| 1240 |
+
"eval_steps_per_second": 0.346,
|
| 1241 |
+
"step": 440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.14,
|
| 1245 |
+
"learning_rate": 4.280205655526993e-05,
|
| 1246 |
+
"loss": 1.6541,
|
| 1247 |
+
"step": 445
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.14,
|
| 1251 |
+
"eval_loss": 1.6630815267562866,
|
| 1252 |
+
"eval_runtime": 31.8083,
|
| 1253 |
+
"eval_samples_per_second": 2.641,
|
| 1254 |
+
"eval_steps_per_second": 0.346,
|
| 1255 |
+
"step": 445
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.16,
|
| 1259 |
+
"learning_rate": 4.215938303341902e-05,
|
| 1260 |
+
"loss": 1.6348,
|
| 1261 |
+
"step": 450
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.16,
|
| 1265 |
+
"eval_loss": 1.662713885307312,
|
| 1266 |
+
"eval_runtime": 31.7977,
|
| 1267 |
+
"eval_samples_per_second": 2.642,
|
| 1268 |
+
"eval_steps_per_second": 0.346,
|
| 1269 |
+
"step": 450
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.17,
|
| 1273 |
+
"learning_rate": 4.151670951156812e-05,
|
| 1274 |
+
"loss": 1.6444,
|
| 1275 |
+
"step": 455
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.17,
|
| 1279 |
+
"eval_loss": 1.6629937887191772,
|
| 1280 |
+
"eval_runtime": 31.799,
|
| 1281 |
+
"eval_samples_per_second": 2.642,
|
| 1282 |
+
"eval_steps_per_second": 0.346,
|
| 1283 |
+
"step": 455
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.18,
|
| 1287 |
+
"learning_rate": 4.0874035989717224e-05,
|
| 1288 |
+
"loss": 1.6629,
|
| 1289 |
+
"step": 460
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 1.18,
|
| 1293 |
+
"eval_loss": 1.6626592874526978,
|
| 1294 |
+
"eval_runtime": 31.8136,
|
| 1295 |
+
"eval_samples_per_second": 2.64,
|
| 1296 |
+
"eval_steps_per_second": 0.346,
|
| 1297 |
+
"step": 460
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.2,
|
| 1301 |
+
"learning_rate": 4.0231362467866324e-05,
|
| 1302 |
+
"loss": 1.6327,
|
| 1303 |
+
"step": 465
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 1.2,
|
| 1307 |
+
"eval_loss": 1.6625391244888306,
|
| 1308 |
+
"eval_runtime": 31.802,
|
| 1309 |
+
"eval_samples_per_second": 2.641,
|
| 1310 |
+
"eval_steps_per_second": 0.346,
|
| 1311 |
+
"step": 465
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.21,
|
| 1315 |
+
"learning_rate": 3.958868894601543e-05,
|
| 1316 |
+
"loss": 1.6236,
|
| 1317 |
+
"step": 470
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 1.21,
|
| 1321 |
+
"eval_loss": 1.6622934341430664,
|
| 1322 |
+
"eval_runtime": 31.8055,
|
| 1323 |
+
"eval_samples_per_second": 2.641,
|
| 1324 |
+
"eval_steps_per_second": 0.346,
|
| 1325 |
+
"step": 470
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.22,
|
| 1329 |
+
"learning_rate": 3.8946015424164526e-05,
|
| 1330 |
+
"loss": 1.6232,
|
| 1331 |
+
"step": 475
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 1.22,
|
| 1335 |
+
"eval_loss": 1.661791443824768,
|
| 1336 |
+
"eval_runtime": 31.8035,
|
| 1337 |
+
"eval_samples_per_second": 2.641,
|
| 1338 |
+
"eval_steps_per_second": 0.346,
|
| 1339 |
+
"step": 475
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.23,
|
| 1343 |
+
"learning_rate": 3.8303341902313626e-05,
|
| 1344 |
+
"loss": 1.6374,
|
| 1345 |
+
"step": 480
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 1.23,
|
| 1349 |
+
"eval_loss": 1.6618887186050415,
|
| 1350 |
+
"eval_runtime": 31.7892,
|
| 1351 |
+
"eval_samples_per_second": 2.642,
|
| 1352 |
+
"eval_steps_per_second": 0.346,
|
| 1353 |
+
"step": 480
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.25,
|
| 1357 |
+
"learning_rate": 3.766066838046273e-05,
|
| 1358 |
+
"loss": 1.6422,
|
| 1359 |
+
"step": 485
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 1.25,
|
| 1363 |
+
"eval_loss": 1.6620476245880127,
|
| 1364 |
+
"eval_runtime": 31.7974,
|
| 1365 |
+
"eval_samples_per_second": 2.642,
|
| 1366 |
+
"eval_steps_per_second": 0.346,
|
| 1367 |
+
"step": 485
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.26,
|
| 1371 |
+
"learning_rate": 3.701799485861183e-05,
|
| 1372 |
+
"loss": 1.631,
|
| 1373 |
+
"step": 490
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 1.26,
|
| 1377 |
+
"eval_loss": 1.6622774600982666,
|
| 1378 |
+
"eval_runtime": 31.7978,
|
| 1379 |
+
"eval_samples_per_second": 2.642,
|
| 1380 |
+
"eval_steps_per_second": 0.346,
|
| 1381 |
+
"step": 490
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.27,
|
| 1385 |
+
"learning_rate": 3.637532133676093e-05,
|
| 1386 |
+
"loss": 1.609,
|
| 1387 |
+
"step": 495
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 1.27,
|
| 1391 |
+
"eval_loss": 1.661568284034729,
|
| 1392 |
+
"eval_runtime": 31.8034,
|
| 1393 |
+
"eval_samples_per_second": 2.641,
|
| 1394 |
+
"eval_steps_per_second": 0.346,
|
| 1395 |
+
"step": 495
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.29,
|
| 1399 |
+
"learning_rate": 3.573264781491003e-05,
|
| 1400 |
+
"loss": 1.6444,
|
| 1401 |
+
"step": 500
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 1.29,
|
| 1405 |
+
"eval_loss": 1.6610949039459229,
|
| 1406 |
+
"eval_runtime": 31.8005,
|
| 1407 |
+
"eval_samples_per_second": 2.641,
|
| 1408 |
+
"eval_steps_per_second": 0.346,
|
| 1409 |
+
"step": 500
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.3,
|
| 1413 |
+
"learning_rate": 3.508997429305913e-05,
|
| 1414 |
+
"loss": 1.6387,
|
| 1415 |
+
"step": 505
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 1.3,
|
| 1419 |
+
"eval_loss": 1.6611486673355103,
|
| 1420 |
+
"eval_runtime": 31.8079,
|
| 1421 |
+
"eval_samples_per_second": 2.641,
|
| 1422 |
+
"eval_steps_per_second": 0.346,
|
| 1423 |
+
"step": 505
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.31,
|
| 1427 |
+
"learning_rate": 3.444730077120823e-05,
|
| 1428 |
+
"loss": 1.6507,
|
| 1429 |
+
"step": 510
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 1.31,
|
| 1433 |
+
"eval_loss": 1.661084532737732,
|
| 1434 |
+
"eval_runtime": 31.8028,
|
| 1435 |
+
"eval_samples_per_second": 2.641,
|
| 1436 |
+
"eval_steps_per_second": 0.346,
|
| 1437 |
+
"step": 510
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.32,
|
| 1441 |
+
"learning_rate": 3.380462724935733e-05,
|
| 1442 |
+
"loss": 1.6377,
|
| 1443 |
+
"step": 515
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.32,
|
| 1447 |
+
"eval_loss": 1.6610103845596313,
|
| 1448 |
+
"eval_runtime": 31.8101,
|
| 1449 |
+
"eval_samples_per_second": 2.641,
|
| 1450 |
+
"eval_steps_per_second": 0.346,
|
| 1451 |
+
"step": 515
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.34,
|
| 1455 |
+
"learning_rate": 3.316195372750643e-05,
|
| 1456 |
+
"loss": 1.6351,
|
| 1457 |
+
"step": 520
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.34,
|
| 1461 |
+
"eval_loss": 1.6608690023422241,
|
| 1462 |
+
"eval_runtime": 31.7986,
|
| 1463 |
+
"eval_samples_per_second": 2.642,
|
| 1464 |
+
"eval_steps_per_second": 0.346,
|
| 1465 |
+
"step": 520
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.35,
|
| 1469 |
+
"learning_rate": 3.251928020565553e-05,
|
| 1470 |
+
"loss": 1.6196,
|
| 1471 |
+
"step": 525
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 1.35,
|
| 1475 |
+
"eval_loss": 1.6606587171554565,
|
| 1476 |
+
"eval_runtime": 31.8015,
|
| 1477 |
+
"eval_samples_per_second": 2.641,
|
| 1478 |
+
"eval_steps_per_second": 0.346,
|
| 1479 |
+
"step": 525
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.36,
|
| 1483 |
+
"learning_rate": 3.1876606683804625e-05,
|
| 1484 |
+
"loss": 1.646,
|
| 1485 |
+
"step": 530
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.36,
|
| 1489 |
+
"eval_loss": 1.6605886220932007,
|
| 1490 |
+
"eval_runtime": 31.804,
|
| 1491 |
+
"eval_samples_per_second": 2.641,
|
| 1492 |
+
"eval_steps_per_second": 0.346,
|
| 1493 |
+
"step": 530
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.38,
|
| 1497 |
+
"learning_rate": 3.1233933161953726e-05,
|
| 1498 |
+
"loss": 1.6824,
|
| 1499 |
+
"step": 535
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.38,
|
| 1503 |
+
"eval_loss": 1.6603879928588867,
|
| 1504 |
+
"eval_runtime": 31.8111,
|
| 1505 |
+
"eval_samples_per_second": 2.641,
|
| 1506 |
+
"eval_steps_per_second": 0.346,
|
| 1507 |
+
"step": 535
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.39,
|
| 1511 |
+
"learning_rate": 3.059125964010283e-05,
|
| 1512 |
+
"loss": 1.6115,
|
| 1513 |
+
"step": 540
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 1.39,
|
| 1517 |
+
"eval_loss": 1.660337209701538,
|
| 1518 |
+
"eval_runtime": 31.805,
|
| 1519 |
+
"eval_samples_per_second": 2.641,
|
| 1520 |
+
"eval_steps_per_second": 0.346,
|
| 1521 |
+
"step": 540
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.4,
|
| 1525 |
+
"learning_rate": 2.994858611825193e-05,
|
| 1526 |
+
"loss": 1.6243,
|
| 1527 |
+
"step": 545
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 1.4,
|
| 1531 |
+
"eval_loss": 1.6606225967407227,
|
| 1532 |
+
"eval_runtime": 31.808,
|
| 1533 |
+
"eval_samples_per_second": 2.641,
|
| 1534 |
+
"eval_steps_per_second": 0.346,
|
| 1535 |
+
"step": 545
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.41,
|
| 1539 |
+
"learning_rate": 2.930591259640103e-05,
|
| 1540 |
+
"loss": 1.6486,
|
| 1541 |
+
"step": 550
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 1.41,
|
| 1545 |
+
"eval_loss": 1.6604374647140503,
|
| 1546 |
+
"eval_runtime": 31.8072,
|
| 1547 |
+
"eval_samples_per_second": 2.641,
|
| 1548 |
+
"eval_steps_per_second": 0.346,
|
| 1549 |
+
"step": 550
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.43,
|
| 1553 |
+
"learning_rate": 2.866323907455013e-05,
|
| 1554 |
+
"loss": 1.6865,
|
| 1555 |
+
"step": 555
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 1.43,
|
| 1559 |
+
"eval_loss": 1.6601544618606567,
|
| 1560 |
+
"eval_runtime": 31.8069,
|
| 1561 |
+
"eval_samples_per_second": 2.641,
|
| 1562 |
+
"eval_steps_per_second": 0.346,
|
| 1563 |
+
"step": 555
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.44,
|
| 1567 |
+
"learning_rate": 2.802056555269923e-05,
|
| 1568 |
+
"loss": 1.6616,
|
| 1569 |
+
"step": 560
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.44,
|
| 1573 |
+
"eval_loss": 1.660386562347412,
|
| 1574 |
+
"eval_runtime": 31.803,
|
| 1575 |
+
"eval_samples_per_second": 2.641,
|
| 1576 |
+
"eval_steps_per_second": 0.346,
|
| 1577 |
+
"step": 560
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.45,
|
| 1581 |
+
"learning_rate": 2.737789203084833e-05,
|
| 1582 |
+
"loss": 1.6336,
|
| 1583 |
+
"step": 565
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 1.45,
|
| 1587 |
+
"eval_loss": 1.660247802734375,
|
| 1588 |
+
"eval_runtime": 31.8084,
|
| 1589 |
+
"eval_samples_per_second": 2.641,
|
| 1590 |
+
"eval_steps_per_second": 0.346,
|
| 1591 |
+
"step": 565
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.47,
|
| 1595 |
+
"learning_rate": 2.673521850899743e-05,
|
| 1596 |
+
"loss": 1.6699,
|
| 1597 |
+
"step": 570
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 1.47,
|
| 1601 |
+
"eval_loss": 1.660292148590088,
|
| 1602 |
+
"eval_runtime": 31.8031,
|
| 1603 |
+
"eval_samples_per_second": 2.641,
|
| 1604 |
+
"eval_steps_per_second": 0.346,
|
| 1605 |
+
"step": 570
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.48,
|
| 1609 |
+
"learning_rate": 2.6092544987146534e-05,
|
| 1610 |
+
"loss": 1.6472,
|
| 1611 |
+
"step": 575
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 1.48,
|
| 1615 |
+
"eval_loss": 1.6598683595657349,
|
| 1616 |
+
"eval_runtime": 31.8181,
|
| 1617 |
+
"eval_samples_per_second": 2.64,
|
| 1618 |
+
"eval_steps_per_second": 0.346,
|
| 1619 |
+
"step": 575
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.49,
|
| 1623 |
+
"learning_rate": 2.5449871465295634e-05,
|
| 1624 |
+
"loss": 1.6723,
|
| 1625 |
+
"step": 580
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.49,
|
| 1629 |
+
"eval_loss": 1.6599065065383911,
|
| 1630 |
+
"eval_runtime": 31.8124,
|
| 1631 |
+
"eval_samples_per_second": 2.64,
|
| 1632 |
+
"eval_steps_per_second": 0.346,
|
| 1633 |
+
"step": 580
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.5,
|
| 1637 |
+
"learning_rate": 2.480719794344473e-05,
|
| 1638 |
+
"loss": 1.663,
|
| 1639 |
+
"step": 585
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 1.5,
|
| 1643 |
+
"eval_loss": 1.6599762439727783,
|
| 1644 |
+
"eval_runtime": 31.8175,
|
| 1645 |
+
"eval_samples_per_second": 2.64,
|
| 1646 |
+
"eval_steps_per_second": 0.346,
|
| 1647 |
+
"step": 585
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.52,
|
| 1651 |
+
"learning_rate": 2.4164524421593832e-05,
|
| 1652 |
+
"loss": 1.6519,
|
| 1653 |
+
"step": 590
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 1.52,
|
| 1657 |
+
"eval_loss": 1.6599925756454468,
|
| 1658 |
+
"eval_runtime": 31.8209,
|
| 1659 |
+
"eval_samples_per_second": 2.64,
|
| 1660 |
+
"eval_steps_per_second": 0.346,
|
| 1661 |
+
"step": 590
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.53,
|
| 1665 |
+
"learning_rate": 2.3521850899742933e-05,
|
| 1666 |
+
"loss": 1.6345,
|
| 1667 |
+
"step": 595
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 1.53,
|
| 1671 |
+
"eval_loss": 1.6600078344345093,
|
| 1672 |
+
"eval_runtime": 31.8031,
|
| 1673 |
+
"eval_samples_per_second": 2.641,
|
| 1674 |
+
"eval_steps_per_second": 0.346,
|
| 1675 |
+
"step": 595
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.54,
|
| 1679 |
+
"learning_rate": 2.2879177377892033e-05,
|
| 1680 |
+
"loss": 1.654,
|
| 1681 |
+
"step": 600
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 1.54,
|
| 1685 |
+
"eval_loss": 1.6599884033203125,
|
| 1686 |
+
"eval_runtime": 31.8281,
|
| 1687 |
+
"eval_samples_per_second": 2.639,
|
| 1688 |
+
"eval_steps_per_second": 0.346,
|
| 1689 |
+
"step": 600
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.56,
|
| 1693 |
+
"learning_rate": 2.2236503856041134e-05,
|
| 1694 |
+
"loss": 1.691,
|
| 1695 |
+
"step": 605
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 1.56,
|
| 1699 |
+
"eval_loss": 1.6599520444869995,
|
| 1700 |
+
"eval_runtime": 31.8168,
|
| 1701 |
+
"eval_samples_per_second": 2.64,
|
| 1702 |
+
"eval_steps_per_second": 0.346,
|
| 1703 |
+
"step": 605
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.57,
|
| 1707 |
+
"learning_rate": 2.159383033419023e-05,
|
| 1708 |
+
"loss": 1.6714,
|
| 1709 |
+
"step": 610
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 1.57,
|
| 1713 |
+
"eval_loss": 1.659857988357544,
|
| 1714 |
+
"eval_runtime": 31.8153,
|
| 1715 |
+
"eval_samples_per_second": 2.64,
|
| 1716 |
+
"eval_steps_per_second": 0.346,
|
| 1717 |
+
"step": 610
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.58,
|
| 1721 |
+
"learning_rate": 2.095115681233933e-05,
|
| 1722 |
+
"loss": 1.5977,
|
| 1723 |
+
"step": 615
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 1.58,
|
| 1727 |
+
"eval_loss": 1.6596992015838623,
|
| 1728 |
+
"eval_runtime": 31.8087,
|
| 1729 |
+
"eval_samples_per_second": 2.641,
|
| 1730 |
+
"eval_steps_per_second": 0.346,
|
| 1731 |
+
"step": 615
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.59,
|
| 1735 |
+
"learning_rate": 2.0308483290488432e-05,
|
| 1736 |
+
"loss": 1.6429,
|
| 1737 |
+
"step": 620
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.59,
|
| 1741 |
+
"eval_loss": 1.6595497131347656,
|
| 1742 |
+
"eval_runtime": 31.8151,
|
| 1743 |
+
"eval_samples_per_second": 2.64,
|
| 1744 |
+
"eval_steps_per_second": 0.346,
|
| 1745 |
+
"step": 620
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.61,
|
| 1749 |
+
"learning_rate": 1.9665809768637533e-05,
|
| 1750 |
+
"loss": 1.6091,
|
| 1751 |
+
"step": 625
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 1.61,
|
| 1755 |
+
"eval_loss": 1.6597559452056885,
|
| 1756 |
+
"eval_runtime": 31.8076,
|
| 1757 |
+
"eval_samples_per_second": 2.641,
|
| 1758 |
+
"eval_steps_per_second": 0.346,
|
| 1759 |
+
"step": 625
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.62,
|
| 1763 |
+
"learning_rate": 1.9023136246786633e-05,
|
| 1764 |
+
"loss": 1.5956,
|
| 1765 |
+
"step": 630
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 1.62,
|
| 1769 |
+
"eval_loss": 1.6593599319458008,
|
| 1770 |
+
"eval_runtime": 31.8058,
|
| 1771 |
+
"eval_samples_per_second": 2.641,
|
| 1772 |
+
"eval_steps_per_second": 0.346,
|
| 1773 |
+
"step": 630
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.63,
|
| 1777 |
+
"learning_rate": 1.8380462724935734e-05,
|
| 1778 |
+
"loss": 1.6697,
|
| 1779 |
+
"step": 635
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.63,
|
| 1783 |
+
"eval_loss": 1.6592466831207275,
|
| 1784 |
+
"eval_runtime": 31.8589,
|
| 1785 |
+
"eval_samples_per_second": 2.637,
|
| 1786 |
+
"eval_steps_per_second": 0.345,
|
| 1787 |
+
"step": 635
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.65,
|
| 1791 |
+
"learning_rate": 1.7737789203084834e-05,
|
| 1792 |
+
"loss": 1.6535,
|
| 1793 |
+
"step": 640
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.65,
|
| 1797 |
+
"eval_loss": 1.6592165231704712,
|
| 1798 |
+
"eval_runtime": 31.8225,
|
| 1799 |
+
"eval_samples_per_second": 2.64,
|
| 1800 |
+
"eval_steps_per_second": 0.346,
|
| 1801 |
+
"step": 640
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.66,
|
| 1805 |
+
"learning_rate": 1.7095115681233935e-05,
|
| 1806 |
+
"loss": 1.6722,
|
| 1807 |
+
"step": 645
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 1.66,
|
| 1811 |
+
"eval_loss": 1.659324049949646,
|
| 1812 |
+
"eval_runtime": 31.8388,
|
| 1813 |
+
"eval_samples_per_second": 2.638,
|
| 1814 |
+
"eval_steps_per_second": 0.345,
|
| 1815 |
+
"step": 645
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.67,
|
| 1819 |
+
"learning_rate": 1.6452442159383032e-05,
|
| 1820 |
+
"loss": 1.6347,
|
| 1821 |
+
"step": 650
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 1.67,
|
| 1825 |
+
"eval_loss": 1.6590396165847778,
|
| 1826 |
+
"eval_runtime": 31.8174,
|
| 1827 |
+
"eval_samples_per_second": 2.64,
|
| 1828 |
+
"eval_steps_per_second": 0.346,
|
| 1829 |
+
"step": 650
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.68,
|
| 1833 |
+
"learning_rate": 1.5809768637532136e-05,
|
| 1834 |
+
"loss": 1.6223,
|
| 1835 |
+
"step": 655
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.68,
|
| 1839 |
+
"eval_loss": 1.658969521522522,
|
| 1840 |
+
"eval_runtime": 31.8275,
|
| 1841 |
+
"eval_samples_per_second": 2.639,
|
| 1842 |
+
"eval_steps_per_second": 0.346,
|
| 1843 |
+
"step": 655
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.7,
|
| 1847 |
+
"learning_rate": 1.5167095115681235e-05,
|
| 1848 |
+
"loss": 1.6309,
|
| 1849 |
+
"step": 660
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.7,
|
| 1853 |
+
"eval_loss": 1.6587274074554443,
|
| 1854 |
+
"eval_runtime": 31.8146,
|
| 1855 |
+
"eval_samples_per_second": 2.64,
|
| 1856 |
+
"eval_steps_per_second": 0.346,
|
| 1857 |
+
"step": 660
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.71,
|
| 1861 |
+
"learning_rate": 1.4524421593830334e-05,
|
| 1862 |
+
"loss": 1.6499,
|
| 1863 |
+
"step": 665
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.71,
|
| 1867 |
+
"eval_loss": 1.65865957736969,
|
| 1868 |
+
"eval_runtime": 31.8091,
|
| 1869 |
+
"eval_samples_per_second": 2.641,
|
| 1870 |
+
"eval_steps_per_second": 0.346,
|
| 1871 |
+
"step": 665
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.72,
|
| 1875 |
+
"learning_rate": 1.3881748071979436e-05,
|
| 1876 |
+
"loss": 1.6713,
|
| 1877 |
+
"step": 670
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 1.72,
|
| 1881 |
+
"eval_loss": 1.6586016416549683,
|
| 1882 |
+
"eval_runtime": 31.8229,
|
| 1883 |
+
"eval_samples_per_second": 2.64,
|
| 1884 |
+
"eval_steps_per_second": 0.346,
|
| 1885 |
+
"step": 670
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.74,
|
| 1889 |
+
"learning_rate": 1.3239074550128535e-05,
|
| 1890 |
+
"loss": 1.6348,
|
| 1891 |
+
"step": 675
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.74,
|
| 1895 |
+
"eval_loss": 1.6584962606430054,
|
| 1896 |
+
"eval_runtime": 31.8035,
|
| 1897 |
+
"eval_samples_per_second": 2.641,
|
| 1898 |
+
"eval_steps_per_second": 0.346,
|
| 1899 |
+
"step": 675
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.75,
|
| 1903 |
+
"learning_rate": 1.2596401028277636e-05,
|
| 1904 |
+
"loss": 1.6447,
|
| 1905 |
+
"step": 680
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.75,
|
| 1909 |
+
"eval_loss": 1.6585614681243896,
|
| 1910 |
+
"eval_runtime": 31.8101,
|
| 1911 |
+
"eval_samples_per_second": 2.641,
|
| 1912 |
+
"eval_steps_per_second": 0.346,
|
| 1913 |
+
"step": 680
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.76,
|
| 1917 |
+
"learning_rate": 1.1953727506426736e-05,
|
| 1918 |
+
"loss": 1.6511,
|
| 1919 |
+
"step": 685
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.76,
|
| 1923 |
+
"eval_loss": 1.6583601236343384,
|
| 1924 |
+
"eval_runtime": 31.8125,
|
| 1925 |
+
"eval_samples_per_second": 2.64,
|
| 1926 |
+
"eval_steps_per_second": 0.346,
|
| 1927 |
+
"step": 685
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.77,
|
| 1931 |
+
"learning_rate": 1.1311053984575835e-05,
|
| 1932 |
+
"loss": 1.6496,
|
| 1933 |
+
"step": 690
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.77,
|
| 1937 |
+
"eval_loss": 1.6583328247070312,
|
| 1938 |
+
"eval_runtime": 31.8179,
|
| 1939 |
+
"eval_samples_per_second": 2.64,
|
| 1940 |
+
"eval_steps_per_second": 0.346,
|
| 1941 |
+
"step": 690
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.79,
|
| 1945 |
+
"learning_rate": 1.0668380462724936e-05,
|
| 1946 |
+
"loss": 1.6421,
|
| 1947 |
+
"step": 695
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 1.79,
|
| 1951 |
+
"eval_loss": 1.6583188772201538,
|
| 1952 |
+
"eval_runtime": 31.8165,
|
| 1953 |
+
"eval_samples_per_second": 2.64,
|
| 1954 |
+
"eval_steps_per_second": 0.346,
|
| 1955 |
+
"step": 695
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.8,
|
| 1959 |
+
"learning_rate": 1.0025706940874038e-05,
|
| 1960 |
+
"loss": 1.6126,
|
| 1961 |
+
"step": 700
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 1.8,
|
| 1965 |
+
"eval_loss": 1.6580705642700195,
|
| 1966 |
+
"eval_runtime": 31.8164,
|
| 1967 |
+
"eval_samples_per_second": 2.64,
|
| 1968 |
+
"eval_steps_per_second": 0.346,
|
| 1969 |
+
"step": 700
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.81,
|
| 1973 |
+
"learning_rate": 9.383033419023137e-06,
|
| 1974 |
+
"loss": 1.6226,
|
| 1975 |
+
"step": 705
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 1.81,
|
| 1979 |
+
"eval_loss": 1.6584465503692627,
|
| 1980 |
+
"eval_runtime": 31.816,
|
| 1981 |
+
"eval_samples_per_second": 2.64,
|
| 1982 |
+
"eval_steps_per_second": 0.346,
|
| 1983 |
+
"step": 705
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.83,
|
| 1987 |
+
"learning_rate": 8.740359897172237e-06,
|
| 1988 |
+
"loss": 1.6923,
|
| 1989 |
+
"step": 710
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.83,
|
| 1993 |
+
"eval_loss": 1.658342957496643,
|
| 1994 |
+
"eval_runtime": 31.8215,
|
| 1995 |
+
"eval_samples_per_second": 2.64,
|
| 1996 |
+
"eval_steps_per_second": 0.346,
|
| 1997 |
+
"step": 710
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.84,
|
| 2001 |
+
"learning_rate": 8.097686375321336e-06,
|
| 2002 |
+
"loss": 1.6224,
|
| 2003 |
+
"step": 715
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 1.84,
|
| 2007 |
+
"eval_loss": 1.6582502126693726,
|
| 2008 |
+
"eval_runtime": 31.812,
|
| 2009 |
+
"eval_samples_per_second": 2.641,
|
| 2010 |
+
"eval_steps_per_second": 0.346,
|
| 2011 |
+
"step": 715
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.85,
|
| 2015 |
+
"learning_rate": 7.4550128534704376e-06,
|
| 2016 |
+
"loss": 1.6587,
|
| 2017 |
+
"step": 720
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 1.85,
|
| 2021 |
+
"eval_loss": 1.658232569694519,
|
| 2022 |
+
"eval_runtime": 31.8059,
|
| 2023 |
+
"eval_samples_per_second": 2.641,
|
| 2024 |
+
"eval_steps_per_second": 0.346,
|
| 2025 |
+
"step": 720
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.86,
|
| 2029 |
+
"learning_rate": 6.812339331619537e-06,
|
| 2030 |
+
"loss": 1.6641,
|
| 2031 |
+
"step": 725
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 1.86,
|
| 2035 |
+
"eval_loss": 1.6582419872283936,
|
| 2036 |
+
"eval_runtime": 31.81,
|
| 2037 |
+
"eval_samples_per_second": 2.641,
|
| 2038 |
+
"eval_steps_per_second": 0.346,
|
| 2039 |
+
"step": 725
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.88,
|
| 2043 |
+
"learning_rate": 6.169665809768638e-06,
|
| 2044 |
+
"loss": 1.6419,
|
| 2045 |
+
"step": 730
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.88,
|
| 2049 |
+
"eval_loss": 1.6582107543945312,
|
| 2050 |
+
"eval_runtime": 31.833,
|
| 2051 |
+
"eval_samples_per_second": 2.639,
|
| 2052 |
+
"eval_steps_per_second": 0.346,
|
| 2053 |
+
"step": 730
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.89,
|
| 2057 |
+
"learning_rate": 5.526992287917738e-06,
|
| 2058 |
+
"loss": 1.652,
|
| 2059 |
+
"step": 735
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 1.89,
|
| 2063 |
+
"eval_loss": 1.6582270860671997,
|
| 2064 |
+
"eval_runtime": 31.8801,
|
| 2065 |
+
"eval_samples_per_second": 2.635,
|
| 2066 |
+
"eval_steps_per_second": 0.345,
|
| 2067 |
+
"step": 735
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.9,
|
| 2071 |
+
"learning_rate": 4.884318766066838e-06,
|
| 2072 |
+
"loss": 1.6487,
|
| 2073 |
+
"step": 740
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.9,
|
| 2077 |
+
"eval_loss": 1.6582915782928467,
|
| 2078 |
+
"eval_runtime": 31.8265,
|
| 2079 |
+
"eval_samples_per_second": 2.639,
|
| 2080 |
+
"eval_steps_per_second": 0.346,
|
| 2081 |
+
"step": 740
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.92,
|
| 2085 |
+
"learning_rate": 4.241645244215939e-06,
|
| 2086 |
+
"loss": 1.6245,
|
| 2087 |
+
"step": 745
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 1.92,
|
| 2091 |
+
"eval_loss": 1.658047080039978,
|
| 2092 |
+
"eval_runtime": 31.8109,
|
| 2093 |
+
"eval_samples_per_second": 2.641,
|
| 2094 |
+
"eval_steps_per_second": 0.346,
|
| 2095 |
+
"step": 745
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.93,
|
| 2099 |
+
"learning_rate": 3.598971722365039e-06,
|
| 2100 |
+
"loss": 1.6553,
|
| 2101 |
+
"step": 750
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 1.93,
|
| 2105 |
+
"eval_loss": 1.6578683853149414,
|
| 2106 |
+
"eval_runtime": 31.8025,
|
| 2107 |
+
"eval_samples_per_second": 2.641,
|
| 2108 |
+
"eval_steps_per_second": 0.346,
|
| 2109 |
+
"step": 750
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.94,
|
| 2113 |
+
"learning_rate": 2.956298200514139e-06,
|
| 2114 |
+
"loss": 1.653,
|
| 2115 |
+
"step": 755
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 1.94,
|
| 2119 |
+
"eval_loss": 1.6578799486160278,
|
| 2120 |
+
"eval_runtime": 31.8005,
|
| 2121 |
+
"eval_samples_per_second": 2.641,
|
| 2122 |
+
"eval_steps_per_second": 0.346,
|
| 2123 |
+
"step": 755
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.95,
|
| 2127 |
+
"learning_rate": 2.313624678663239e-06,
|
| 2128 |
+
"loss": 1.6519,
|
| 2129 |
+
"step": 760
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 1.95,
|
| 2133 |
+
"eval_loss": 1.657995343208313,
|
| 2134 |
+
"eval_runtime": 31.8085,
|
| 2135 |
+
"eval_samples_per_second": 2.641,
|
| 2136 |
+
"eval_steps_per_second": 0.346,
|
| 2137 |
+
"step": 760
|
| 2138 |
+
}
|
| 2139 |
+
],
|
| 2140 |
+
"logging_steps": 5,
|
| 2141 |
+
"max_steps": 778,
|
| 2142 |
+
"num_train_epochs": 2,
|
| 2143 |
+
"save_steps": 10,
|
| 2144 |
+
"total_flos": 2.4689619442335744e+17,
|
| 2145 |
+
"trial_name": null,
|
| 2146 |
+
"trial_params": null
|
| 2147 |
+
}
|
checkpoint-760/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc6a8542abd91027de58ebfccafdf919108680707834fe188d91cae077ef8e9
|
| 3 |
+
size 4600
|
checkpoint-770/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.5.0
|
checkpoint-770/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-770/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f53f206e0cb885454f819ae3409abc106eeba62514646529f6f9e4bbb61ba4bb
|
| 3 |
+
size 16794200
|
checkpoint-770/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79d8992ce3454e6f5b2392b746972be89665bcb4818ce6f2e23af544ed03c810
|
| 3 |
+
size 33663866
|
checkpoint-770/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c5f9ad2e286a1e70aa146089c04236927b587bd36b55c15839ea4c0e9f97abe
|
| 3 |
+
size 14244
|
checkpoint-770/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20a2696e9318ad2bf716807b888007e1a89e6c3dfb2d5365a6d1bd45f962d7a5
|
| 3 |
+
size 1064
|
checkpoint-770/trainer_state.json
ADDED
|
@@ -0,0 +1,2175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.6578683853149414,
|
| 3 |
+
"best_model_checkpoint": "/scratch/kwamea/llama-output/checkpoint-750",
|
| 4 |
+
"epoch": 1.9794344473007712,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 770,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 9.93573264781491e-05,
|
| 14 |
+
"loss": 1.9824,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"eval_loss": 1.954728126525879,
|
| 20 |
+
"eval_runtime": 31.6803,
|
| 21 |
+
"eval_samples_per_second": 2.651,
|
| 22 |
+
"eval_steps_per_second": 0.347,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"learning_rate": 9.87146529562982e-05,
|
| 28 |
+
"loss": 1.9249,
|
| 29 |
+
"step": 10
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"eval_loss": 1.8934264183044434,
|
| 34 |
+
"eval_runtime": 31.7798,
|
| 35 |
+
"eval_samples_per_second": 2.643,
|
| 36 |
+
"eval_steps_per_second": 0.346,
|
| 37 |
+
"step": 10
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04,
|
| 41 |
+
"learning_rate": 9.80719794344473e-05,
|
| 42 |
+
"loss": 1.8609,
|
| 43 |
+
"step": 15
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.04,
|
| 47 |
+
"eval_loss": 1.8421852588653564,
|
| 48 |
+
"eval_runtime": 31.7999,
|
| 49 |
+
"eval_samples_per_second": 2.642,
|
| 50 |
+
"eval_steps_per_second": 0.346,
|
| 51 |
+
"step": 15
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"learning_rate": 9.742930591259641e-05,
|
| 56 |
+
"loss": 1.8268,
|
| 57 |
+
"step": 20
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.05,
|
| 61 |
+
"eval_loss": 1.8279638290405273,
|
| 62 |
+
"eval_runtime": 31.8095,
|
| 63 |
+
"eval_samples_per_second": 2.641,
|
| 64 |
+
"eval_steps_per_second": 0.346,
|
| 65 |
+
"step": 20
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06,
|
| 69 |
+
"learning_rate": 9.67866323907455e-05,
|
| 70 |
+
"loss": 1.8349,
|
| 71 |
+
"step": 25
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.06,
|
| 75 |
+
"eval_loss": 1.813267469406128,
|
| 76 |
+
"eval_runtime": 31.8291,
|
| 77 |
+
"eval_samples_per_second": 2.639,
|
| 78 |
+
"eval_steps_per_second": 0.346,
|
| 79 |
+
"step": 25
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.08,
|
| 83 |
+
"learning_rate": 9.61439588688946e-05,
|
| 84 |
+
"loss": 1.8239,
|
| 85 |
+
"step": 30
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.08,
|
| 89 |
+
"eval_loss": 1.8008779287338257,
|
| 90 |
+
"eval_runtime": 31.82,
|
| 91 |
+
"eval_samples_per_second": 2.64,
|
| 92 |
+
"eval_steps_per_second": 0.346,
|
| 93 |
+
"step": 30
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 9.550128534704372e-05,
|
| 98 |
+
"loss": 1.7177,
|
| 99 |
+
"step": 35
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.09,
|
| 103 |
+
"eval_loss": 1.789797067642212,
|
| 104 |
+
"eval_runtime": 31.8423,
|
| 105 |
+
"eval_samples_per_second": 2.638,
|
| 106 |
+
"eval_steps_per_second": 0.345,
|
| 107 |
+
"step": 35
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1,
|
| 111 |
+
"learning_rate": 9.485861182519281e-05,
|
| 112 |
+
"loss": 1.7962,
|
| 113 |
+
"step": 40
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.1,
|
| 117 |
+
"eval_loss": 1.7808287143707275,
|
| 118 |
+
"eval_runtime": 31.8387,
|
| 119 |
+
"eval_samples_per_second": 2.638,
|
| 120 |
+
"eval_steps_per_second": 0.345,
|
| 121 |
+
"step": 40
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.12,
|
| 125 |
+
"learning_rate": 9.421593830334192e-05,
|
| 126 |
+
"loss": 1.715,
|
| 127 |
+
"step": 45
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.12,
|
| 131 |
+
"eval_loss": 1.771236777305603,
|
| 132 |
+
"eval_runtime": 31.8526,
|
| 133 |
+
"eval_samples_per_second": 2.637,
|
| 134 |
+
"eval_steps_per_second": 0.345,
|
| 135 |
+
"step": 45
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13,
|
| 139 |
+
"learning_rate": 9.357326478149101e-05,
|
| 140 |
+
"loss": 1.7577,
|
| 141 |
+
"step": 50
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.13,
|
| 145 |
+
"eval_loss": 1.7619521617889404,
|
| 146 |
+
"eval_runtime": 31.828,
|
| 147 |
+
"eval_samples_per_second": 2.639,
|
| 148 |
+
"eval_steps_per_second": 0.346,
|
| 149 |
+
"step": 50
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.14,
|
| 153 |
+
"learning_rate": 9.29305912596401e-05,
|
| 154 |
+
"loss": 1.7323,
|
| 155 |
+
"step": 55
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.14,
|
| 159 |
+
"eval_loss": 1.7440986633300781,
|
| 160 |
+
"eval_runtime": 31.8301,
|
| 161 |
+
"eval_samples_per_second": 2.639,
|
| 162 |
+
"eval_steps_per_second": 0.346,
|
| 163 |
+
"step": 55
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.15,
|
| 167 |
+
"learning_rate": 9.228791773778921e-05,
|
| 168 |
+
"loss": 1.7122,
|
| 169 |
+
"step": 60
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.15,
|
| 173 |
+
"eval_loss": 1.712996006011963,
|
| 174 |
+
"eval_runtime": 31.8185,
|
| 175 |
+
"eval_samples_per_second": 2.64,
|
| 176 |
+
"eval_steps_per_second": 0.346,
|
| 177 |
+
"step": 60
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17,
|
| 181 |
+
"learning_rate": 9.16452442159383e-05,
|
| 182 |
+
"loss": 1.7042,
|
| 183 |
+
"step": 65
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.17,
|
| 187 |
+
"eval_loss": 1.7101707458496094,
|
| 188 |
+
"eval_runtime": 31.8153,
|
| 189 |
+
"eval_samples_per_second": 2.64,
|
| 190 |
+
"eval_steps_per_second": 0.346,
|
| 191 |
+
"step": 65
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.18,
|
| 195 |
+
"learning_rate": 9.100257069408741e-05,
|
| 196 |
+
"loss": 1.7242,
|
| 197 |
+
"step": 70
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.18,
|
| 201 |
+
"eval_loss": 1.7038702964782715,
|
| 202 |
+
"eval_runtime": 31.8191,
|
| 203 |
+
"eval_samples_per_second": 2.64,
|
| 204 |
+
"eval_steps_per_second": 0.346,
|
| 205 |
+
"step": 70
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19,
|
| 209 |
+
"learning_rate": 9.03598971722365e-05,
|
| 210 |
+
"loss": 1.7033,
|
| 211 |
+
"step": 75
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.19,
|
| 215 |
+
"eval_loss": 1.7004183530807495,
|
| 216 |
+
"eval_runtime": 31.811,
|
| 217 |
+
"eval_samples_per_second": 2.641,
|
| 218 |
+
"eval_steps_per_second": 0.346,
|
| 219 |
+
"step": 75
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21,
|
| 223 |
+
"learning_rate": 8.97172236503856e-05,
|
| 224 |
+
"loss": 1.6934,
|
| 225 |
+
"step": 80
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.21,
|
| 229 |
+
"eval_loss": 1.6985355615615845,
|
| 230 |
+
"eval_runtime": 31.8221,
|
| 231 |
+
"eval_samples_per_second": 2.64,
|
| 232 |
+
"eval_steps_per_second": 0.346,
|
| 233 |
+
"step": 80
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22,
|
| 237 |
+
"learning_rate": 8.907455012853471e-05,
|
| 238 |
+
"loss": 1.6443,
|
| 239 |
+
"step": 85
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.22,
|
| 243 |
+
"eval_loss": 1.696852684020996,
|
| 244 |
+
"eval_runtime": 31.8219,
|
| 245 |
+
"eval_samples_per_second": 2.64,
|
| 246 |
+
"eval_steps_per_second": 0.346,
|
| 247 |
+
"step": 85
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.23,
|
| 251 |
+
"learning_rate": 8.84318766066838e-05,
|
| 252 |
+
"loss": 1.7008,
|
| 253 |
+
"step": 90
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.23,
|
| 257 |
+
"eval_loss": 1.695594072341919,
|
| 258 |
+
"eval_runtime": 31.8205,
|
| 259 |
+
"eval_samples_per_second": 2.64,
|
| 260 |
+
"eval_steps_per_second": 0.346,
|
| 261 |
+
"step": 90
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.24,
|
| 265 |
+
"learning_rate": 8.778920308483291e-05,
|
| 266 |
+
"loss": 1.6873,
|
| 267 |
+
"step": 95
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.24,
|
| 271 |
+
"eval_loss": 1.6928850412368774,
|
| 272 |
+
"eval_runtime": 31.814,
|
| 273 |
+
"eval_samples_per_second": 2.64,
|
| 274 |
+
"eval_steps_per_second": 0.346,
|
| 275 |
+
"step": 95
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.26,
|
| 279 |
+
"learning_rate": 8.7146529562982e-05,
|
| 280 |
+
"loss": 1.6721,
|
| 281 |
+
"step": 100
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.26,
|
| 285 |
+
"eval_loss": 1.6919386386871338,
|
| 286 |
+
"eval_runtime": 31.8127,
|
| 287 |
+
"eval_samples_per_second": 2.64,
|
| 288 |
+
"eval_steps_per_second": 0.346,
|
| 289 |
+
"step": 100
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.27,
|
| 293 |
+
"learning_rate": 8.650385604113111e-05,
|
| 294 |
+
"loss": 1.6669,
|
| 295 |
+
"step": 105
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.27,
|
| 299 |
+
"eval_loss": 1.6905940771102905,
|
| 300 |
+
"eval_runtime": 31.8874,
|
| 301 |
+
"eval_samples_per_second": 2.634,
|
| 302 |
+
"eval_steps_per_second": 0.345,
|
| 303 |
+
"step": 105
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.28,
|
| 307 |
+
"learning_rate": 8.586118251928022e-05,
|
| 308 |
+
"loss": 1.7009,
|
| 309 |
+
"step": 110
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.28,
|
| 313 |
+
"eval_loss": 1.689422607421875,
|
| 314 |
+
"eval_runtime": 31.8489,
|
| 315 |
+
"eval_samples_per_second": 2.637,
|
| 316 |
+
"eval_steps_per_second": 0.345,
|
| 317 |
+
"step": 110
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.3,
|
| 321 |
+
"learning_rate": 8.521850899742931e-05,
|
| 322 |
+
"loss": 1.7151,
|
| 323 |
+
"step": 115
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.3,
|
| 327 |
+
"eval_loss": 1.688527226448059,
|
| 328 |
+
"eval_runtime": 31.8318,
|
| 329 |
+
"eval_samples_per_second": 2.639,
|
| 330 |
+
"eval_steps_per_second": 0.346,
|
| 331 |
+
"step": 115
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.31,
|
| 335 |
+
"learning_rate": 8.457583547557842e-05,
|
| 336 |
+
"loss": 1.7165,
|
| 337 |
+
"step": 120
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.31,
|
| 341 |
+
"eval_loss": 1.686748743057251,
|
| 342 |
+
"eval_runtime": 31.835,
|
| 343 |
+
"eval_samples_per_second": 2.639,
|
| 344 |
+
"eval_steps_per_second": 0.346,
|
| 345 |
+
"step": 120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.32,
|
| 349 |
+
"learning_rate": 8.393316195372751e-05,
|
| 350 |
+
"loss": 1.7015,
|
| 351 |
+
"step": 125
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.32,
|
| 355 |
+
"eval_loss": 1.6855812072753906,
|
| 356 |
+
"eval_runtime": 31.8269,
|
| 357 |
+
"eval_samples_per_second": 2.639,
|
| 358 |
+
"eval_steps_per_second": 0.346,
|
| 359 |
+
"step": 125
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.33,
|
| 363 |
+
"learning_rate": 8.32904884318766e-05,
|
| 364 |
+
"loss": 1.6818,
|
| 365 |
+
"step": 130
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.33,
|
| 369 |
+
"eval_loss": 1.6846078634262085,
|
| 370 |
+
"eval_runtime": 31.8617,
|
| 371 |
+
"eval_samples_per_second": 2.636,
|
| 372 |
+
"eval_steps_per_second": 0.345,
|
| 373 |
+
"step": 130
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.35,
|
| 377 |
+
"learning_rate": 8.264781491002571e-05,
|
| 378 |
+
"loss": 1.7151,
|
| 379 |
+
"step": 135
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.35,
|
| 383 |
+
"eval_loss": 1.6845166683197021,
|
| 384 |
+
"eval_runtime": 31.8631,
|
| 385 |
+
"eval_samples_per_second": 2.636,
|
| 386 |
+
"eval_steps_per_second": 0.345,
|
| 387 |
+
"step": 135
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.36,
|
| 391 |
+
"learning_rate": 8.200514138817481e-05,
|
| 392 |
+
"loss": 1.6667,
|
| 393 |
+
"step": 140
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.36,
|
| 397 |
+
"eval_loss": 1.6832246780395508,
|
| 398 |
+
"eval_runtime": 31.8276,
|
| 399 |
+
"eval_samples_per_second": 2.639,
|
| 400 |
+
"eval_steps_per_second": 0.346,
|
| 401 |
+
"step": 140
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.37,
|
| 405 |
+
"learning_rate": 8.136246786632391e-05,
|
| 406 |
+
"loss": 1.6586,
|
| 407 |
+
"step": 145
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.37,
|
| 411 |
+
"eval_loss": 1.6824573278427124,
|
| 412 |
+
"eval_runtime": 31.8115,
|
| 413 |
+
"eval_samples_per_second": 2.641,
|
| 414 |
+
"eval_steps_per_second": 0.346,
|
| 415 |
+
"step": 145
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.39,
|
| 419 |
+
"learning_rate": 8.071979434447301e-05,
|
| 420 |
+
"loss": 1.6999,
|
| 421 |
+
"step": 150
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.39,
|
| 425 |
+
"eval_loss": 1.681317687034607,
|
| 426 |
+
"eval_runtime": 31.805,
|
| 427 |
+
"eval_samples_per_second": 2.641,
|
| 428 |
+
"eval_steps_per_second": 0.346,
|
| 429 |
+
"step": 150
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4,
|
| 433 |
+
"learning_rate": 8.007712082262212e-05,
|
| 434 |
+
"loss": 1.6894,
|
| 435 |
+
"step": 155
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.4,
|
| 439 |
+
"eval_loss": 1.6812355518341064,
|
| 440 |
+
"eval_runtime": 31.8039,
|
| 441 |
+
"eval_samples_per_second": 2.641,
|
| 442 |
+
"eval_steps_per_second": 0.346,
|
| 443 |
+
"step": 155
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.41,
|
| 447 |
+
"learning_rate": 7.943444730077121e-05,
|
| 448 |
+
"loss": 1.6669,
|
| 449 |
+
"step": 160
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.41,
|
| 453 |
+
"eval_loss": 1.679802656173706,
|
| 454 |
+
"eval_runtime": 31.8021,
|
| 455 |
+
"eval_samples_per_second": 2.641,
|
| 456 |
+
"eval_steps_per_second": 0.346,
|
| 457 |
+
"step": 160
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.42,
|
| 461 |
+
"learning_rate": 7.87917737789203e-05,
|
| 462 |
+
"loss": 1.6481,
|
| 463 |
+
"step": 165
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.42,
|
| 467 |
+
"eval_loss": 1.679994821548462,
|
| 468 |
+
"eval_runtime": 31.8201,
|
| 469 |
+
"eval_samples_per_second": 2.64,
|
| 470 |
+
"eval_steps_per_second": 0.346,
|
| 471 |
+
"step": 165
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.44,
|
| 475 |
+
"learning_rate": 7.814910025706941e-05,
|
| 476 |
+
"loss": 1.7042,
|
| 477 |
+
"step": 170
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.44,
|
| 481 |
+
"eval_loss": 1.6786224842071533,
|
| 482 |
+
"eval_runtime": 31.8184,
|
| 483 |
+
"eval_samples_per_second": 2.64,
|
| 484 |
+
"eval_steps_per_second": 0.346,
|
| 485 |
+
"step": 170
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.45,
|
| 489 |
+
"learning_rate": 7.750642673521852e-05,
|
| 490 |
+
"loss": 1.6564,
|
| 491 |
+
"step": 175
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.45,
|
| 495 |
+
"eval_loss": 1.6783201694488525,
|
| 496 |
+
"eval_runtime": 31.8137,
|
| 497 |
+
"eval_samples_per_second": 2.64,
|
| 498 |
+
"eval_steps_per_second": 0.346,
|
| 499 |
+
"step": 175
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.46,
|
| 503 |
+
"learning_rate": 7.686375321336761e-05,
|
| 504 |
+
"loss": 1.6714,
|
| 505 |
+
"step": 180
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.46,
|
| 509 |
+
"eval_loss": 1.677714228630066,
|
| 510 |
+
"eval_runtime": 31.804,
|
| 511 |
+
"eval_samples_per_second": 2.641,
|
| 512 |
+
"eval_steps_per_second": 0.346,
|
| 513 |
+
"step": 180
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.48,
|
| 517 |
+
"learning_rate": 7.622107969151672e-05,
|
| 518 |
+
"loss": 1.6705,
|
| 519 |
+
"step": 185
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.48,
|
| 523 |
+
"eval_loss": 1.6772773265838623,
|
| 524 |
+
"eval_runtime": 31.8077,
|
| 525 |
+
"eval_samples_per_second": 2.641,
|
| 526 |
+
"eval_steps_per_second": 0.346,
|
| 527 |
+
"step": 185
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.49,
|
| 531 |
+
"learning_rate": 7.557840616966581e-05,
|
| 532 |
+
"loss": 1.6624,
|
| 533 |
+
"step": 190
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.49,
|
| 537 |
+
"eval_loss": 1.6766114234924316,
|
| 538 |
+
"eval_runtime": 31.8164,
|
| 539 |
+
"eval_samples_per_second": 2.64,
|
| 540 |
+
"eval_steps_per_second": 0.346,
|
| 541 |
+
"step": 190
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.5,
|
| 545 |
+
"learning_rate": 7.493573264781492e-05,
|
| 546 |
+
"loss": 1.6415,
|
| 547 |
+
"step": 195
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.5,
|
| 551 |
+
"eval_loss": 1.675940752029419,
|
| 552 |
+
"eval_runtime": 31.8124,
|
| 553 |
+
"eval_samples_per_second": 2.64,
|
| 554 |
+
"eval_steps_per_second": 0.346,
|
| 555 |
+
"step": 195
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.51,
|
| 559 |
+
"learning_rate": 7.429305912596401e-05,
|
| 560 |
+
"loss": 1.6633,
|
| 561 |
+
"step": 200
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.51,
|
| 565 |
+
"eval_loss": 1.6751865148544312,
|
| 566 |
+
"eval_runtime": 31.8123,
|
| 567 |
+
"eval_samples_per_second": 2.64,
|
| 568 |
+
"eval_steps_per_second": 0.346,
|
| 569 |
+
"step": 200
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.53,
|
| 573 |
+
"learning_rate": 7.365038560411311e-05,
|
| 574 |
+
"loss": 1.6142,
|
| 575 |
+
"step": 205
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.53,
|
| 579 |
+
"eval_loss": 1.6750575304031372,
|
| 580 |
+
"eval_runtime": 31.8049,
|
| 581 |
+
"eval_samples_per_second": 2.641,
|
| 582 |
+
"eval_steps_per_second": 0.346,
|
| 583 |
+
"step": 205
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.54,
|
| 587 |
+
"learning_rate": 7.300771208226222e-05,
|
| 588 |
+
"loss": 1.6736,
|
| 589 |
+
"step": 210
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.54,
|
| 593 |
+
"eval_loss": 1.6746423244476318,
|
| 594 |
+
"eval_runtime": 31.8111,
|
| 595 |
+
"eval_samples_per_second": 2.641,
|
| 596 |
+
"eval_steps_per_second": 0.346,
|
| 597 |
+
"step": 210
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.55,
|
| 601 |
+
"learning_rate": 7.236503856041131e-05,
|
| 602 |
+
"loss": 1.6414,
|
| 603 |
+
"step": 215
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.55,
|
| 607 |
+
"eval_loss": 1.6740491390228271,
|
| 608 |
+
"eval_runtime": 31.8083,
|
| 609 |
+
"eval_samples_per_second": 2.641,
|
| 610 |
+
"eval_steps_per_second": 0.346,
|
| 611 |
+
"step": 215
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.57,
|
| 615 |
+
"learning_rate": 7.172236503856042e-05,
|
| 616 |
+
"loss": 1.6725,
|
| 617 |
+
"step": 220
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.57,
|
| 621 |
+
"eval_loss": 1.673694372177124,
|
| 622 |
+
"eval_runtime": 31.8025,
|
| 623 |
+
"eval_samples_per_second": 2.641,
|
| 624 |
+
"eval_steps_per_second": 0.346,
|
| 625 |
+
"step": 220
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.58,
|
| 629 |
+
"learning_rate": 7.107969151670951e-05,
|
| 630 |
+
"loss": 1.679,
|
| 631 |
+
"step": 225
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.58,
|
| 635 |
+
"eval_loss": 1.6733818054199219,
|
| 636 |
+
"eval_runtime": 31.8077,
|
| 637 |
+
"eval_samples_per_second": 2.641,
|
| 638 |
+
"eval_steps_per_second": 0.346,
|
| 639 |
+
"step": 225
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.59,
|
| 643 |
+
"learning_rate": 7.043701799485862e-05,
|
| 644 |
+
"loss": 1.7204,
|
| 645 |
+
"step": 230
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.59,
|
| 649 |
+
"eval_loss": 1.6725033521652222,
|
| 650 |
+
"eval_runtime": 31.8079,
|
| 651 |
+
"eval_samples_per_second": 2.641,
|
| 652 |
+
"eval_steps_per_second": 0.346,
|
| 653 |
+
"step": 230
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.6,
|
| 657 |
+
"learning_rate": 6.979434447300771e-05,
|
| 658 |
+
"loss": 1.6816,
|
| 659 |
+
"step": 235
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.6,
|
| 663 |
+
"eval_loss": 1.67205011844635,
|
| 664 |
+
"eval_runtime": 31.809,
|
| 665 |
+
"eval_samples_per_second": 2.641,
|
| 666 |
+
"eval_steps_per_second": 0.346,
|
| 667 |
+
"step": 235
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.62,
|
| 671 |
+
"learning_rate": 6.91516709511568e-05,
|
| 672 |
+
"loss": 1.634,
|
| 673 |
+
"step": 240
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.62,
|
| 677 |
+
"eval_loss": 1.6717994213104248,
|
| 678 |
+
"eval_runtime": 31.8075,
|
| 679 |
+
"eval_samples_per_second": 2.641,
|
| 680 |
+
"eval_steps_per_second": 0.346,
|
| 681 |
+
"step": 240
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.63,
|
| 685 |
+
"learning_rate": 6.850899742930593e-05,
|
| 686 |
+
"loss": 1.6761,
|
| 687 |
+
"step": 245
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.63,
|
| 691 |
+
"eval_loss": 1.6714757680892944,
|
| 692 |
+
"eval_runtime": 31.8052,
|
| 693 |
+
"eval_samples_per_second": 2.641,
|
| 694 |
+
"eval_steps_per_second": 0.346,
|
| 695 |
+
"step": 245
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.64,
|
| 699 |
+
"learning_rate": 6.786632390745502e-05,
|
| 700 |
+
"loss": 1.6996,
|
| 701 |
+
"step": 250
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.64,
|
| 705 |
+
"eval_loss": 1.671559453010559,
|
| 706 |
+
"eval_runtime": 31.8089,
|
| 707 |
+
"eval_samples_per_second": 2.641,
|
| 708 |
+
"eval_steps_per_second": 0.346,
|
| 709 |
+
"step": 250
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.66,
|
| 713 |
+
"learning_rate": 6.722365038560411e-05,
|
| 714 |
+
"loss": 1.6302,
|
| 715 |
+
"step": 255
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.66,
|
| 719 |
+
"eval_loss": 1.6711652278900146,
|
| 720 |
+
"eval_runtime": 31.8105,
|
| 721 |
+
"eval_samples_per_second": 2.641,
|
| 722 |
+
"eval_steps_per_second": 0.346,
|
| 723 |
+
"step": 255
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.67,
|
| 727 |
+
"learning_rate": 6.658097686375322e-05,
|
| 728 |
+
"loss": 1.6611,
|
| 729 |
+
"step": 260
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.67,
|
| 733 |
+
"eval_loss": 1.6704061031341553,
|
| 734 |
+
"eval_runtime": 31.8135,
|
| 735 |
+
"eval_samples_per_second": 2.64,
|
| 736 |
+
"eval_steps_per_second": 0.346,
|
| 737 |
+
"step": 260
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.68,
|
| 741 |
+
"learning_rate": 6.593830334190231e-05,
|
| 742 |
+
"loss": 1.6586,
|
| 743 |
+
"step": 265
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.68,
|
| 747 |
+
"eval_loss": 1.6705658435821533,
|
| 748 |
+
"eval_runtime": 31.7998,
|
| 749 |
+
"eval_samples_per_second": 2.642,
|
| 750 |
+
"eval_steps_per_second": 0.346,
|
| 751 |
+
"step": 265
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.69,
|
| 755 |
+
"learning_rate": 6.529562982005142e-05,
|
| 756 |
+
"loss": 1.6838,
|
| 757 |
+
"step": 270
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.69,
|
| 761 |
+
"eval_loss": 1.6697953939437866,
|
| 762 |
+
"eval_runtime": 31.7994,
|
| 763 |
+
"eval_samples_per_second": 2.642,
|
| 764 |
+
"eval_steps_per_second": 0.346,
|
| 765 |
+
"step": 270
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.71,
|
| 769 |
+
"learning_rate": 6.465295629820052e-05,
|
| 770 |
+
"loss": 1.6499,
|
| 771 |
+
"step": 275
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.71,
|
| 775 |
+
"eval_loss": 1.669343113899231,
|
| 776 |
+
"eval_runtime": 31.8147,
|
| 777 |
+
"eval_samples_per_second": 2.64,
|
| 778 |
+
"eval_steps_per_second": 0.346,
|
| 779 |
+
"step": 275
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.72,
|
| 783 |
+
"learning_rate": 6.401028277634962e-05,
|
| 784 |
+
"loss": 1.6424,
|
| 785 |
+
"step": 280
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.72,
|
| 789 |
+
"eval_loss": 1.6693596839904785,
|
| 790 |
+
"eval_runtime": 31.8155,
|
| 791 |
+
"eval_samples_per_second": 2.64,
|
| 792 |
+
"eval_steps_per_second": 0.346,
|
| 793 |
+
"step": 280
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.73,
|
| 797 |
+
"learning_rate": 6.336760925449872e-05,
|
| 798 |
+
"loss": 1.6238,
|
| 799 |
+
"step": 285
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.73,
|
| 803 |
+
"eval_loss": 1.669128179550171,
|
| 804 |
+
"eval_runtime": 31.8219,
|
| 805 |
+
"eval_samples_per_second": 2.64,
|
| 806 |
+
"eval_steps_per_second": 0.346,
|
| 807 |
+
"step": 285
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.75,
|
| 811 |
+
"learning_rate": 6.272493573264781e-05,
|
| 812 |
+
"loss": 1.6538,
|
| 813 |
+
"step": 290
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.75,
|
| 817 |
+
"eval_loss": 1.6691263914108276,
|
| 818 |
+
"eval_runtime": 31.81,
|
| 819 |
+
"eval_samples_per_second": 2.641,
|
| 820 |
+
"eval_steps_per_second": 0.346,
|
| 821 |
+
"step": 290
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.76,
|
| 825 |
+
"learning_rate": 6.208226221079692e-05,
|
| 826 |
+
"loss": 1.656,
|
| 827 |
+
"step": 295
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.76,
|
| 831 |
+
"eval_loss": 1.66847825050354,
|
| 832 |
+
"eval_runtime": 31.7918,
|
| 833 |
+
"eval_samples_per_second": 2.642,
|
| 834 |
+
"eval_steps_per_second": 0.346,
|
| 835 |
+
"step": 295
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.77,
|
| 839 |
+
"learning_rate": 6.143958868894601e-05,
|
| 840 |
+
"loss": 1.6407,
|
| 841 |
+
"step": 300
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.77,
|
| 845 |
+
"eval_loss": 1.6683858633041382,
|
| 846 |
+
"eval_runtime": 31.8114,
|
| 847 |
+
"eval_samples_per_second": 2.641,
|
| 848 |
+
"eval_steps_per_second": 0.346,
|
| 849 |
+
"step": 300
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.78,
|
| 853 |
+
"learning_rate": 6.079691516709511e-05,
|
| 854 |
+
"loss": 1.6468,
|
| 855 |
+
"step": 305
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.78,
|
| 859 |
+
"eval_loss": 1.6678352355957031,
|
| 860 |
+
"eval_runtime": 31.7975,
|
| 861 |
+
"eval_samples_per_second": 2.642,
|
| 862 |
+
"eval_steps_per_second": 0.346,
|
| 863 |
+
"step": 305
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.8,
|
| 867 |
+
"learning_rate": 6.015424164524421e-05,
|
| 868 |
+
"loss": 1.6579,
|
| 869 |
+
"step": 310
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.8,
|
| 873 |
+
"eval_loss": 1.6675294637680054,
|
| 874 |
+
"eval_runtime": 31.8059,
|
| 875 |
+
"eval_samples_per_second": 2.641,
|
| 876 |
+
"eval_steps_per_second": 0.346,
|
| 877 |
+
"step": 310
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.81,
|
| 881 |
+
"learning_rate": 5.951156812339333e-05,
|
| 882 |
+
"loss": 1.6331,
|
| 883 |
+
"step": 315
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.81,
|
| 887 |
+
"eval_loss": 1.6670397520065308,
|
| 888 |
+
"eval_runtime": 31.7994,
|
| 889 |
+
"eval_samples_per_second": 2.642,
|
| 890 |
+
"eval_steps_per_second": 0.346,
|
| 891 |
+
"step": 315
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.82,
|
| 895 |
+
"learning_rate": 5.886889460154242e-05,
|
| 896 |
+
"loss": 1.6634,
|
| 897 |
+
"step": 320
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.82,
|
| 901 |
+
"eval_loss": 1.6668330430984497,
|
| 902 |
+
"eval_runtime": 31.807,
|
| 903 |
+
"eval_samples_per_second": 2.641,
|
| 904 |
+
"eval_steps_per_second": 0.346,
|
| 905 |
+
"step": 320
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.84,
|
| 909 |
+
"learning_rate": 5.822622107969152e-05,
|
| 910 |
+
"loss": 1.6406,
|
| 911 |
+
"step": 325
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.84,
|
| 915 |
+
"eval_loss": 1.6668546199798584,
|
| 916 |
+
"eval_runtime": 31.8004,
|
| 917 |
+
"eval_samples_per_second": 2.641,
|
| 918 |
+
"eval_steps_per_second": 0.346,
|
| 919 |
+
"step": 325
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.85,
|
| 923 |
+
"learning_rate": 5.758354755784062e-05,
|
| 924 |
+
"loss": 1.6614,
|
| 925 |
+
"step": 330
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.85,
|
| 929 |
+
"eval_loss": 1.666812539100647,
|
| 930 |
+
"eval_runtime": 31.8023,
|
| 931 |
+
"eval_samples_per_second": 2.641,
|
| 932 |
+
"eval_steps_per_second": 0.346,
|
| 933 |
+
"step": 330
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.86,
|
| 937 |
+
"learning_rate": 5.694087403598972e-05,
|
| 938 |
+
"loss": 1.6598,
|
| 939 |
+
"step": 335
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.86,
|
| 943 |
+
"eval_loss": 1.666398048400879,
|
| 944 |
+
"eval_runtime": 31.8087,
|
| 945 |
+
"eval_samples_per_second": 2.641,
|
| 946 |
+
"eval_steps_per_second": 0.346,
|
| 947 |
+
"step": 335
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.87,
|
| 951 |
+
"learning_rate": 5.6298200514138824e-05,
|
| 952 |
+
"loss": 1.6698,
|
| 953 |
+
"step": 340
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.87,
|
| 957 |
+
"eval_loss": 1.6660391092300415,
|
| 958 |
+
"eval_runtime": 31.8016,
|
| 959 |
+
"eval_samples_per_second": 2.641,
|
| 960 |
+
"eval_steps_per_second": 0.346,
|
| 961 |
+
"step": 340
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.89,
|
| 965 |
+
"learning_rate": 5.5655526992287924e-05,
|
| 966 |
+
"loss": 1.6346,
|
| 967 |
+
"step": 345
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.89,
|
| 971 |
+
"eval_loss": 1.665901780128479,
|
| 972 |
+
"eval_runtime": 31.7878,
|
| 973 |
+
"eval_samples_per_second": 2.643,
|
| 974 |
+
"eval_steps_per_second": 0.346,
|
| 975 |
+
"step": 345
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.9,
|
| 979 |
+
"learning_rate": 5.501285347043702e-05,
|
| 980 |
+
"loss": 1.6617,
|
| 981 |
+
"step": 350
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.9,
|
| 985 |
+
"eval_loss": 1.666027307510376,
|
| 986 |
+
"eval_runtime": 31.7999,
|
| 987 |
+
"eval_samples_per_second": 2.642,
|
| 988 |
+
"eval_steps_per_second": 0.346,
|
| 989 |
+
"step": 350
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.91,
|
| 993 |
+
"learning_rate": 5.437017994858612e-05,
|
| 994 |
+
"loss": 1.6623,
|
| 995 |
+
"step": 355
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.91,
|
| 999 |
+
"eval_loss": 1.6658612489700317,
|
| 1000 |
+
"eval_runtime": 31.8128,
|
| 1001 |
+
"eval_samples_per_second": 2.64,
|
| 1002 |
+
"eval_steps_per_second": 0.346,
|
| 1003 |
+
"step": 355
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.93,
|
| 1007 |
+
"learning_rate": 5.372750642673522e-05,
|
| 1008 |
+
"loss": 1.6737,
|
| 1009 |
+
"step": 360
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.93,
|
| 1013 |
+
"eval_loss": 1.6656837463378906,
|
| 1014 |
+
"eval_runtime": 31.8094,
|
| 1015 |
+
"eval_samples_per_second": 2.641,
|
| 1016 |
+
"eval_steps_per_second": 0.346,
|
| 1017 |
+
"step": 360
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.94,
|
| 1021 |
+
"learning_rate": 5.308483290488432e-05,
|
| 1022 |
+
"loss": 1.6981,
|
| 1023 |
+
"step": 365
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.94,
|
| 1027 |
+
"eval_loss": 1.6653661727905273,
|
| 1028 |
+
"eval_runtime": 31.8031,
|
| 1029 |
+
"eval_samples_per_second": 2.641,
|
| 1030 |
+
"eval_steps_per_second": 0.346,
|
| 1031 |
+
"step": 365
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.95,
|
| 1035 |
+
"learning_rate": 5.244215938303342e-05,
|
| 1036 |
+
"loss": 1.6832,
|
| 1037 |
+
"step": 370
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.95,
|
| 1041 |
+
"eval_loss": 1.6652257442474365,
|
| 1042 |
+
"eval_runtime": 31.8077,
|
| 1043 |
+
"eval_samples_per_second": 2.641,
|
| 1044 |
+
"eval_steps_per_second": 0.346,
|
| 1045 |
+
"step": 370
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.96,
|
| 1049 |
+
"learning_rate": 5.1799485861182514e-05,
|
| 1050 |
+
"loss": 1.6925,
|
| 1051 |
+
"step": 375
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.96,
|
| 1055 |
+
"eval_loss": 1.664839267730713,
|
| 1056 |
+
"eval_runtime": 31.8082,
|
| 1057 |
+
"eval_samples_per_second": 2.641,
|
| 1058 |
+
"eval_steps_per_second": 0.346,
|
| 1059 |
+
"step": 375
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.98,
|
| 1063 |
+
"learning_rate": 5.1156812339331615e-05,
|
| 1064 |
+
"loss": 1.6721,
|
| 1065 |
+
"step": 380
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.98,
|
| 1069 |
+
"eval_loss": 1.6642415523529053,
|
| 1070 |
+
"eval_runtime": 31.7927,
|
| 1071 |
+
"eval_samples_per_second": 2.642,
|
| 1072 |
+
"eval_steps_per_second": 0.346,
|
| 1073 |
+
"step": 380
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.99,
|
| 1077 |
+
"learning_rate": 5.051413881748073e-05,
|
| 1078 |
+
"loss": 1.6208,
|
| 1079 |
+
"step": 385
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.99,
|
| 1083 |
+
"eval_loss": 1.6641273498535156,
|
| 1084 |
+
"eval_runtime": 31.8006,
|
| 1085 |
+
"eval_samples_per_second": 2.641,
|
| 1086 |
+
"eval_steps_per_second": 0.346,
|
| 1087 |
+
"step": 385
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 1.0,
|
| 1091 |
+
"learning_rate": 4.987146529562982e-05,
|
| 1092 |
+
"loss": 1.6519,
|
| 1093 |
+
"step": 390
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.0,
|
| 1097 |
+
"eval_loss": 1.6645455360412598,
|
| 1098 |
+
"eval_runtime": 31.8026,
|
| 1099 |
+
"eval_samples_per_second": 2.641,
|
| 1100 |
+
"eval_steps_per_second": 0.346,
|
| 1101 |
+
"step": 390
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 1.02,
|
| 1105 |
+
"learning_rate": 4.922879177377892e-05,
|
| 1106 |
+
"loss": 1.6581,
|
| 1107 |
+
"step": 395
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 1.02,
|
| 1111 |
+
"eval_loss": 1.6641591787338257,
|
| 1112 |
+
"eval_runtime": 31.8025,
|
| 1113 |
+
"eval_samples_per_second": 2.641,
|
| 1114 |
+
"eval_steps_per_second": 0.346,
|
| 1115 |
+
"step": 395
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.03,
|
| 1119 |
+
"learning_rate": 4.8586118251928024e-05,
|
| 1120 |
+
"loss": 1.6768,
|
| 1121 |
+
"step": 400
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.03,
|
| 1125 |
+
"eval_loss": 1.6637850999832153,
|
| 1126 |
+
"eval_runtime": 31.806,
|
| 1127 |
+
"eval_samples_per_second": 2.641,
|
| 1128 |
+
"eval_steps_per_second": 0.346,
|
| 1129 |
+
"step": 400
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.04,
|
| 1133 |
+
"learning_rate": 4.7943444730077124e-05,
|
| 1134 |
+
"loss": 1.6257,
|
| 1135 |
+
"step": 405
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 1.04,
|
| 1139 |
+
"eval_loss": 1.6636526584625244,
|
| 1140 |
+
"eval_runtime": 31.8116,
|
| 1141 |
+
"eval_samples_per_second": 2.641,
|
| 1142 |
+
"eval_steps_per_second": 0.346,
|
| 1143 |
+
"step": 405
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.05,
|
| 1147 |
+
"learning_rate": 4.7300771208226225e-05,
|
| 1148 |
+
"loss": 1.6522,
|
| 1149 |
+
"step": 410
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 1.05,
|
| 1153 |
+
"eval_loss": 1.6634690761566162,
|
| 1154 |
+
"eval_runtime": 31.8063,
|
| 1155 |
+
"eval_samples_per_second": 2.641,
|
| 1156 |
+
"eval_steps_per_second": 0.346,
|
| 1157 |
+
"step": 410
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.07,
|
| 1161 |
+
"learning_rate": 4.6658097686375325e-05,
|
| 1162 |
+
"loss": 1.615,
|
| 1163 |
+
"step": 415
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 1.07,
|
| 1167 |
+
"eval_loss": 1.6637413501739502,
|
| 1168 |
+
"eval_runtime": 31.8115,
|
| 1169 |
+
"eval_samples_per_second": 2.641,
|
| 1170 |
+
"eval_steps_per_second": 0.346,
|
| 1171 |
+
"step": 415
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.08,
|
| 1175 |
+
"learning_rate": 4.6015424164524426e-05,
|
| 1176 |
+
"loss": 1.5967,
|
| 1177 |
+
"step": 420
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 1.08,
|
| 1181 |
+
"eval_loss": 1.6633188724517822,
|
| 1182 |
+
"eval_runtime": 31.8016,
|
| 1183 |
+
"eval_samples_per_second": 2.641,
|
| 1184 |
+
"eval_steps_per_second": 0.346,
|
| 1185 |
+
"step": 420
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.09,
|
| 1189 |
+
"learning_rate": 4.537275064267352e-05,
|
| 1190 |
+
"loss": 1.6708,
|
| 1191 |
+
"step": 425
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.09,
|
| 1195 |
+
"eval_loss": 1.6634286642074585,
|
| 1196 |
+
"eval_runtime": 31.8074,
|
| 1197 |
+
"eval_samples_per_second": 2.641,
|
| 1198 |
+
"eval_steps_per_second": 0.346,
|
| 1199 |
+
"step": 425
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.11,
|
| 1203 |
+
"learning_rate": 4.473007712082262e-05,
|
| 1204 |
+
"loss": 1.6696,
|
| 1205 |
+
"step": 430
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.11,
|
| 1209 |
+
"eval_loss": 1.663163661956787,
|
| 1210 |
+
"eval_runtime": 31.799,
|
| 1211 |
+
"eval_samples_per_second": 2.642,
|
| 1212 |
+
"eval_steps_per_second": 0.346,
|
| 1213 |
+
"step": 430
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.12,
|
| 1217 |
+
"learning_rate": 4.408740359897173e-05,
|
| 1218 |
+
"loss": 1.6344,
|
| 1219 |
+
"step": 435
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.12,
|
| 1223 |
+
"eval_loss": 1.6632493734359741,
|
| 1224 |
+
"eval_runtime": 31.8032,
|
| 1225 |
+
"eval_samples_per_second": 2.641,
|
| 1226 |
+
"eval_steps_per_second": 0.346,
|
| 1227 |
+
"step": 435
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.13,
|
| 1231 |
+
"learning_rate": 4.344473007712083e-05,
|
| 1232 |
+
"loss": 1.5922,
|
| 1233 |
+
"step": 440
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 1.13,
|
| 1237 |
+
"eval_loss": 1.6627737283706665,
|
| 1238 |
+
"eval_runtime": 31.8064,
|
| 1239 |
+
"eval_samples_per_second": 2.641,
|
| 1240 |
+
"eval_steps_per_second": 0.346,
|
| 1241 |
+
"step": 440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.14,
|
| 1245 |
+
"learning_rate": 4.280205655526993e-05,
|
| 1246 |
+
"loss": 1.6541,
|
| 1247 |
+
"step": 445
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.14,
|
| 1251 |
+
"eval_loss": 1.6630815267562866,
|
| 1252 |
+
"eval_runtime": 31.8083,
|
| 1253 |
+
"eval_samples_per_second": 2.641,
|
| 1254 |
+
"eval_steps_per_second": 0.346,
|
| 1255 |
+
"step": 445
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.16,
|
| 1259 |
+
"learning_rate": 4.215938303341902e-05,
|
| 1260 |
+
"loss": 1.6348,
|
| 1261 |
+
"step": 450
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 1.16,
|
| 1265 |
+
"eval_loss": 1.662713885307312,
|
| 1266 |
+
"eval_runtime": 31.7977,
|
| 1267 |
+
"eval_samples_per_second": 2.642,
|
| 1268 |
+
"eval_steps_per_second": 0.346,
|
| 1269 |
+
"step": 450
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.17,
|
| 1273 |
+
"learning_rate": 4.151670951156812e-05,
|
| 1274 |
+
"loss": 1.6444,
|
| 1275 |
+
"step": 455
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.17,
|
| 1279 |
+
"eval_loss": 1.6629937887191772,
|
| 1280 |
+
"eval_runtime": 31.799,
|
| 1281 |
+
"eval_samples_per_second": 2.642,
|
| 1282 |
+
"eval_steps_per_second": 0.346,
|
| 1283 |
+
"step": 455
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.18,
|
| 1287 |
+
"learning_rate": 4.0874035989717224e-05,
|
| 1288 |
+
"loss": 1.6629,
|
| 1289 |
+
"step": 460
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 1.18,
|
| 1293 |
+
"eval_loss": 1.6626592874526978,
|
| 1294 |
+
"eval_runtime": 31.8136,
|
| 1295 |
+
"eval_samples_per_second": 2.64,
|
| 1296 |
+
"eval_steps_per_second": 0.346,
|
| 1297 |
+
"step": 460
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.2,
|
| 1301 |
+
"learning_rate": 4.0231362467866324e-05,
|
| 1302 |
+
"loss": 1.6327,
|
| 1303 |
+
"step": 465
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 1.2,
|
| 1307 |
+
"eval_loss": 1.6625391244888306,
|
| 1308 |
+
"eval_runtime": 31.802,
|
| 1309 |
+
"eval_samples_per_second": 2.641,
|
| 1310 |
+
"eval_steps_per_second": 0.346,
|
| 1311 |
+
"step": 465
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.21,
|
| 1315 |
+
"learning_rate": 3.958868894601543e-05,
|
| 1316 |
+
"loss": 1.6236,
|
| 1317 |
+
"step": 470
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 1.21,
|
| 1321 |
+
"eval_loss": 1.6622934341430664,
|
| 1322 |
+
"eval_runtime": 31.8055,
|
| 1323 |
+
"eval_samples_per_second": 2.641,
|
| 1324 |
+
"eval_steps_per_second": 0.346,
|
| 1325 |
+
"step": 470
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.22,
|
| 1329 |
+
"learning_rate": 3.8946015424164526e-05,
|
| 1330 |
+
"loss": 1.6232,
|
| 1331 |
+
"step": 475
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 1.22,
|
| 1335 |
+
"eval_loss": 1.661791443824768,
|
| 1336 |
+
"eval_runtime": 31.8035,
|
| 1337 |
+
"eval_samples_per_second": 2.641,
|
| 1338 |
+
"eval_steps_per_second": 0.346,
|
| 1339 |
+
"step": 475
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 1.23,
|
| 1343 |
+
"learning_rate": 3.8303341902313626e-05,
|
| 1344 |
+
"loss": 1.6374,
|
| 1345 |
+
"step": 480
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 1.23,
|
| 1349 |
+
"eval_loss": 1.6618887186050415,
|
| 1350 |
+
"eval_runtime": 31.7892,
|
| 1351 |
+
"eval_samples_per_second": 2.642,
|
| 1352 |
+
"eval_steps_per_second": 0.346,
|
| 1353 |
+
"step": 480
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 1.25,
|
| 1357 |
+
"learning_rate": 3.766066838046273e-05,
|
| 1358 |
+
"loss": 1.6422,
|
| 1359 |
+
"step": 485
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 1.25,
|
| 1363 |
+
"eval_loss": 1.6620476245880127,
|
| 1364 |
+
"eval_runtime": 31.7974,
|
| 1365 |
+
"eval_samples_per_second": 2.642,
|
| 1366 |
+
"eval_steps_per_second": 0.346,
|
| 1367 |
+
"step": 485
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.26,
|
| 1371 |
+
"learning_rate": 3.701799485861183e-05,
|
| 1372 |
+
"loss": 1.631,
|
| 1373 |
+
"step": 490
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 1.26,
|
| 1377 |
+
"eval_loss": 1.6622774600982666,
|
| 1378 |
+
"eval_runtime": 31.7978,
|
| 1379 |
+
"eval_samples_per_second": 2.642,
|
| 1380 |
+
"eval_steps_per_second": 0.346,
|
| 1381 |
+
"step": 490
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.27,
|
| 1385 |
+
"learning_rate": 3.637532133676093e-05,
|
| 1386 |
+
"loss": 1.609,
|
| 1387 |
+
"step": 495
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 1.27,
|
| 1391 |
+
"eval_loss": 1.661568284034729,
|
| 1392 |
+
"eval_runtime": 31.8034,
|
| 1393 |
+
"eval_samples_per_second": 2.641,
|
| 1394 |
+
"eval_steps_per_second": 0.346,
|
| 1395 |
+
"step": 495
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 1.29,
|
| 1399 |
+
"learning_rate": 3.573264781491003e-05,
|
| 1400 |
+
"loss": 1.6444,
|
| 1401 |
+
"step": 500
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 1.29,
|
| 1405 |
+
"eval_loss": 1.6610949039459229,
|
| 1406 |
+
"eval_runtime": 31.8005,
|
| 1407 |
+
"eval_samples_per_second": 2.641,
|
| 1408 |
+
"eval_steps_per_second": 0.346,
|
| 1409 |
+
"step": 500
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.3,
|
| 1413 |
+
"learning_rate": 3.508997429305913e-05,
|
| 1414 |
+
"loss": 1.6387,
|
| 1415 |
+
"step": 505
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 1.3,
|
| 1419 |
+
"eval_loss": 1.6611486673355103,
|
| 1420 |
+
"eval_runtime": 31.8079,
|
| 1421 |
+
"eval_samples_per_second": 2.641,
|
| 1422 |
+
"eval_steps_per_second": 0.346,
|
| 1423 |
+
"step": 505
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 1.31,
|
| 1427 |
+
"learning_rate": 3.444730077120823e-05,
|
| 1428 |
+
"loss": 1.6507,
|
| 1429 |
+
"step": 510
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 1.31,
|
| 1433 |
+
"eval_loss": 1.661084532737732,
|
| 1434 |
+
"eval_runtime": 31.8028,
|
| 1435 |
+
"eval_samples_per_second": 2.641,
|
| 1436 |
+
"eval_steps_per_second": 0.346,
|
| 1437 |
+
"step": 510
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 1.32,
|
| 1441 |
+
"learning_rate": 3.380462724935733e-05,
|
| 1442 |
+
"loss": 1.6377,
|
| 1443 |
+
"step": 515
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.32,
|
| 1447 |
+
"eval_loss": 1.6610103845596313,
|
| 1448 |
+
"eval_runtime": 31.8101,
|
| 1449 |
+
"eval_samples_per_second": 2.641,
|
| 1450 |
+
"eval_steps_per_second": 0.346,
|
| 1451 |
+
"step": 515
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.34,
|
| 1455 |
+
"learning_rate": 3.316195372750643e-05,
|
| 1456 |
+
"loss": 1.6351,
|
| 1457 |
+
"step": 520
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.34,
|
| 1461 |
+
"eval_loss": 1.6608690023422241,
|
| 1462 |
+
"eval_runtime": 31.7986,
|
| 1463 |
+
"eval_samples_per_second": 2.642,
|
| 1464 |
+
"eval_steps_per_second": 0.346,
|
| 1465 |
+
"step": 520
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 1.35,
|
| 1469 |
+
"learning_rate": 3.251928020565553e-05,
|
| 1470 |
+
"loss": 1.6196,
|
| 1471 |
+
"step": 525
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 1.35,
|
| 1475 |
+
"eval_loss": 1.6606587171554565,
|
| 1476 |
+
"eval_runtime": 31.8015,
|
| 1477 |
+
"eval_samples_per_second": 2.641,
|
| 1478 |
+
"eval_steps_per_second": 0.346,
|
| 1479 |
+
"step": 525
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 1.36,
|
| 1483 |
+
"learning_rate": 3.1876606683804625e-05,
|
| 1484 |
+
"loss": 1.646,
|
| 1485 |
+
"step": 530
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 1.36,
|
| 1489 |
+
"eval_loss": 1.6605886220932007,
|
| 1490 |
+
"eval_runtime": 31.804,
|
| 1491 |
+
"eval_samples_per_second": 2.641,
|
| 1492 |
+
"eval_steps_per_second": 0.346,
|
| 1493 |
+
"step": 530
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.38,
|
| 1497 |
+
"learning_rate": 3.1233933161953726e-05,
|
| 1498 |
+
"loss": 1.6824,
|
| 1499 |
+
"step": 535
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.38,
|
| 1503 |
+
"eval_loss": 1.6603879928588867,
|
| 1504 |
+
"eval_runtime": 31.8111,
|
| 1505 |
+
"eval_samples_per_second": 2.641,
|
| 1506 |
+
"eval_steps_per_second": 0.346,
|
| 1507 |
+
"step": 535
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 1.39,
|
| 1511 |
+
"learning_rate": 3.059125964010283e-05,
|
| 1512 |
+
"loss": 1.6115,
|
| 1513 |
+
"step": 540
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 1.39,
|
| 1517 |
+
"eval_loss": 1.660337209701538,
|
| 1518 |
+
"eval_runtime": 31.805,
|
| 1519 |
+
"eval_samples_per_second": 2.641,
|
| 1520 |
+
"eval_steps_per_second": 0.346,
|
| 1521 |
+
"step": 540
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 1.4,
|
| 1525 |
+
"learning_rate": 2.994858611825193e-05,
|
| 1526 |
+
"loss": 1.6243,
|
| 1527 |
+
"step": 545
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 1.4,
|
| 1531 |
+
"eval_loss": 1.6606225967407227,
|
| 1532 |
+
"eval_runtime": 31.808,
|
| 1533 |
+
"eval_samples_per_second": 2.641,
|
| 1534 |
+
"eval_steps_per_second": 0.346,
|
| 1535 |
+
"step": 545
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 1.41,
|
| 1539 |
+
"learning_rate": 2.930591259640103e-05,
|
| 1540 |
+
"loss": 1.6486,
|
| 1541 |
+
"step": 550
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 1.41,
|
| 1545 |
+
"eval_loss": 1.6604374647140503,
|
| 1546 |
+
"eval_runtime": 31.8072,
|
| 1547 |
+
"eval_samples_per_second": 2.641,
|
| 1548 |
+
"eval_steps_per_second": 0.346,
|
| 1549 |
+
"step": 550
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 1.43,
|
| 1553 |
+
"learning_rate": 2.866323907455013e-05,
|
| 1554 |
+
"loss": 1.6865,
|
| 1555 |
+
"step": 555
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 1.43,
|
| 1559 |
+
"eval_loss": 1.6601544618606567,
|
| 1560 |
+
"eval_runtime": 31.8069,
|
| 1561 |
+
"eval_samples_per_second": 2.641,
|
| 1562 |
+
"eval_steps_per_second": 0.346,
|
| 1563 |
+
"step": 555
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 1.44,
|
| 1567 |
+
"learning_rate": 2.802056555269923e-05,
|
| 1568 |
+
"loss": 1.6616,
|
| 1569 |
+
"step": 560
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 1.44,
|
| 1573 |
+
"eval_loss": 1.660386562347412,
|
| 1574 |
+
"eval_runtime": 31.803,
|
| 1575 |
+
"eval_samples_per_second": 2.641,
|
| 1576 |
+
"eval_steps_per_second": 0.346,
|
| 1577 |
+
"step": 560
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 1.45,
|
| 1581 |
+
"learning_rate": 2.737789203084833e-05,
|
| 1582 |
+
"loss": 1.6336,
|
| 1583 |
+
"step": 565
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 1.45,
|
| 1587 |
+
"eval_loss": 1.660247802734375,
|
| 1588 |
+
"eval_runtime": 31.8084,
|
| 1589 |
+
"eval_samples_per_second": 2.641,
|
| 1590 |
+
"eval_steps_per_second": 0.346,
|
| 1591 |
+
"step": 565
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 1.47,
|
| 1595 |
+
"learning_rate": 2.673521850899743e-05,
|
| 1596 |
+
"loss": 1.6699,
|
| 1597 |
+
"step": 570
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 1.47,
|
| 1601 |
+
"eval_loss": 1.660292148590088,
|
| 1602 |
+
"eval_runtime": 31.8031,
|
| 1603 |
+
"eval_samples_per_second": 2.641,
|
| 1604 |
+
"eval_steps_per_second": 0.346,
|
| 1605 |
+
"step": 570
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 1.48,
|
| 1609 |
+
"learning_rate": 2.6092544987146534e-05,
|
| 1610 |
+
"loss": 1.6472,
|
| 1611 |
+
"step": 575
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 1.48,
|
| 1615 |
+
"eval_loss": 1.6598683595657349,
|
| 1616 |
+
"eval_runtime": 31.8181,
|
| 1617 |
+
"eval_samples_per_second": 2.64,
|
| 1618 |
+
"eval_steps_per_second": 0.346,
|
| 1619 |
+
"step": 575
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 1.49,
|
| 1623 |
+
"learning_rate": 2.5449871465295634e-05,
|
| 1624 |
+
"loss": 1.6723,
|
| 1625 |
+
"step": 580
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 1.49,
|
| 1629 |
+
"eval_loss": 1.6599065065383911,
|
| 1630 |
+
"eval_runtime": 31.8124,
|
| 1631 |
+
"eval_samples_per_second": 2.64,
|
| 1632 |
+
"eval_steps_per_second": 0.346,
|
| 1633 |
+
"step": 580
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 1.5,
|
| 1637 |
+
"learning_rate": 2.480719794344473e-05,
|
| 1638 |
+
"loss": 1.663,
|
| 1639 |
+
"step": 585
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 1.5,
|
| 1643 |
+
"eval_loss": 1.6599762439727783,
|
| 1644 |
+
"eval_runtime": 31.8175,
|
| 1645 |
+
"eval_samples_per_second": 2.64,
|
| 1646 |
+
"eval_steps_per_second": 0.346,
|
| 1647 |
+
"step": 585
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 1.52,
|
| 1651 |
+
"learning_rate": 2.4164524421593832e-05,
|
| 1652 |
+
"loss": 1.6519,
|
| 1653 |
+
"step": 590
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 1.52,
|
| 1657 |
+
"eval_loss": 1.6599925756454468,
|
| 1658 |
+
"eval_runtime": 31.8209,
|
| 1659 |
+
"eval_samples_per_second": 2.64,
|
| 1660 |
+
"eval_steps_per_second": 0.346,
|
| 1661 |
+
"step": 590
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 1.53,
|
| 1665 |
+
"learning_rate": 2.3521850899742933e-05,
|
| 1666 |
+
"loss": 1.6345,
|
| 1667 |
+
"step": 595
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 1.53,
|
| 1671 |
+
"eval_loss": 1.6600078344345093,
|
| 1672 |
+
"eval_runtime": 31.8031,
|
| 1673 |
+
"eval_samples_per_second": 2.641,
|
| 1674 |
+
"eval_steps_per_second": 0.346,
|
| 1675 |
+
"step": 595
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 1.54,
|
| 1679 |
+
"learning_rate": 2.2879177377892033e-05,
|
| 1680 |
+
"loss": 1.654,
|
| 1681 |
+
"step": 600
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 1.54,
|
| 1685 |
+
"eval_loss": 1.6599884033203125,
|
| 1686 |
+
"eval_runtime": 31.8281,
|
| 1687 |
+
"eval_samples_per_second": 2.639,
|
| 1688 |
+
"eval_steps_per_second": 0.346,
|
| 1689 |
+
"step": 600
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 1.56,
|
| 1693 |
+
"learning_rate": 2.2236503856041134e-05,
|
| 1694 |
+
"loss": 1.691,
|
| 1695 |
+
"step": 605
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 1.56,
|
| 1699 |
+
"eval_loss": 1.6599520444869995,
|
| 1700 |
+
"eval_runtime": 31.8168,
|
| 1701 |
+
"eval_samples_per_second": 2.64,
|
| 1702 |
+
"eval_steps_per_second": 0.346,
|
| 1703 |
+
"step": 605
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 1.57,
|
| 1707 |
+
"learning_rate": 2.159383033419023e-05,
|
| 1708 |
+
"loss": 1.6714,
|
| 1709 |
+
"step": 610
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 1.57,
|
| 1713 |
+
"eval_loss": 1.659857988357544,
|
| 1714 |
+
"eval_runtime": 31.8153,
|
| 1715 |
+
"eval_samples_per_second": 2.64,
|
| 1716 |
+
"eval_steps_per_second": 0.346,
|
| 1717 |
+
"step": 610
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 1.58,
|
| 1721 |
+
"learning_rate": 2.095115681233933e-05,
|
| 1722 |
+
"loss": 1.5977,
|
| 1723 |
+
"step": 615
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 1.58,
|
| 1727 |
+
"eval_loss": 1.6596992015838623,
|
| 1728 |
+
"eval_runtime": 31.8087,
|
| 1729 |
+
"eval_samples_per_second": 2.641,
|
| 1730 |
+
"eval_steps_per_second": 0.346,
|
| 1731 |
+
"step": 615
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 1.59,
|
| 1735 |
+
"learning_rate": 2.0308483290488432e-05,
|
| 1736 |
+
"loss": 1.6429,
|
| 1737 |
+
"step": 620
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 1.59,
|
| 1741 |
+
"eval_loss": 1.6595497131347656,
|
| 1742 |
+
"eval_runtime": 31.8151,
|
| 1743 |
+
"eval_samples_per_second": 2.64,
|
| 1744 |
+
"eval_steps_per_second": 0.346,
|
| 1745 |
+
"step": 620
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 1.61,
|
| 1749 |
+
"learning_rate": 1.9665809768637533e-05,
|
| 1750 |
+
"loss": 1.6091,
|
| 1751 |
+
"step": 625
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 1.61,
|
| 1755 |
+
"eval_loss": 1.6597559452056885,
|
| 1756 |
+
"eval_runtime": 31.8076,
|
| 1757 |
+
"eval_samples_per_second": 2.641,
|
| 1758 |
+
"eval_steps_per_second": 0.346,
|
| 1759 |
+
"step": 625
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 1.62,
|
| 1763 |
+
"learning_rate": 1.9023136246786633e-05,
|
| 1764 |
+
"loss": 1.5956,
|
| 1765 |
+
"step": 630
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 1.62,
|
| 1769 |
+
"eval_loss": 1.6593599319458008,
|
| 1770 |
+
"eval_runtime": 31.8058,
|
| 1771 |
+
"eval_samples_per_second": 2.641,
|
| 1772 |
+
"eval_steps_per_second": 0.346,
|
| 1773 |
+
"step": 630
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 1.63,
|
| 1777 |
+
"learning_rate": 1.8380462724935734e-05,
|
| 1778 |
+
"loss": 1.6697,
|
| 1779 |
+
"step": 635
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 1.63,
|
| 1783 |
+
"eval_loss": 1.6592466831207275,
|
| 1784 |
+
"eval_runtime": 31.8589,
|
| 1785 |
+
"eval_samples_per_second": 2.637,
|
| 1786 |
+
"eval_steps_per_second": 0.345,
|
| 1787 |
+
"step": 635
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 1.65,
|
| 1791 |
+
"learning_rate": 1.7737789203084834e-05,
|
| 1792 |
+
"loss": 1.6535,
|
| 1793 |
+
"step": 640
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 1.65,
|
| 1797 |
+
"eval_loss": 1.6592165231704712,
|
| 1798 |
+
"eval_runtime": 31.8225,
|
| 1799 |
+
"eval_samples_per_second": 2.64,
|
| 1800 |
+
"eval_steps_per_second": 0.346,
|
| 1801 |
+
"step": 640
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 1.66,
|
| 1805 |
+
"learning_rate": 1.7095115681233935e-05,
|
| 1806 |
+
"loss": 1.6722,
|
| 1807 |
+
"step": 645
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 1.66,
|
| 1811 |
+
"eval_loss": 1.659324049949646,
|
| 1812 |
+
"eval_runtime": 31.8388,
|
| 1813 |
+
"eval_samples_per_second": 2.638,
|
| 1814 |
+
"eval_steps_per_second": 0.345,
|
| 1815 |
+
"step": 645
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 1.67,
|
| 1819 |
+
"learning_rate": 1.6452442159383032e-05,
|
| 1820 |
+
"loss": 1.6347,
|
| 1821 |
+
"step": 650
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 1.67,
|
| 1825 |
+
"eval_loss": 1.6590396165847778,
|
| 1826 |
+
"eval_runtime": 31.8174,
|
| 1827 |
+
"eval_samples_per_second": 2.64,
|
| 1828 |
+
"eval_steps_per_second": 0.346,
|
| 1829 |
+
"step": 650
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 1.68,
|
| 1833 |
+
"learning_rate": 1.5809768637532136e-05,
|
| 1834 |
+
"loss": 1.6223,
|
| 1835 |
+
"step": 655
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 1.68,
|
| 1839 |
+
"eval_loss": 1.658969521522522,
|
| 1840 |
+
"eval_runtime": 31.8275,
|
| 1841 |
+
"eval_samples_per_second": 2.639,
|
| 1842 |
+
"eval_steps_per_second": 0.346,
|
| 1843 |
+
"step": 655
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 1.7,
|
| 1847 |
+
"learning_rate": 1.5167095115681235e-05,
|
| 1848 |
+
"loss": 1.6309,
|
| 1849 |
+
"step": 660
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 1.7,
|
| 1853 |
+
"eval_loss": 1.6587274074554443,
|
| 1854 |
+
"eval_runtime": 31.8146,
|
| 1855 |
+
"eval_samples_per_second": 2.64,
|
| 1856 |
+
"eval_steps_per_second": 0.346,
|
| 1857 |
+
"step": 660
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 1.71,
|
| 1861 |
+
"learning_rate": 1.4524421593830334e-05,
|
| 1862 |
+
"loss": 1.6499,
|
| 1863 |
+
"step": 665
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 1.71,
|
| 1867 |
+
"eval_loss": 1.65865957736969,
|
| 1868 |
+
"eval_runtime": 31.8091,
|
| 1869 |
+
"eval_samples_per_second": 2.641,
|
| 1870 |
+
"eval_steps_per_second": 0.346,
|
| 1871 |
+
"step": 665
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 1.72,
|
| 1875 |
+
"learning_rate": 1.3881748071979436e-05,
|
| 1876 |
+
"loss": 1.6713,
|
| 1877 |
+
"step": 670
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 1.72,
|
| 1881 |
+
"eval_loss": 1.6586016416549683,
|
| 1882 |
+
"eval_runtime": 31.8229,
|
| 1883 |
+
"eval_samples_per_second": 2.64,
|
| 1884 |
+
"eval_steps_per_second": 0.346,
|
| 1885 |
+
"step": 670
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 1.74,
|
| 1889 |
+
"learning_rate": 1.3239074550128535e-05,
|
| 1890 |
+
"loss": 1.6348,
|
| 1891 |
+
"step": 675
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 1.74,
|
| 1895 |
+
"eval_loss": 1.6584962606430054,
|
| 1896 |
+
"eval_runtime": 31.8035,
|
| 1897 |
+
"eval_samples_per_second": 2.641,
|
| 1898 |
+
"eval_steps_per_second": 0.346,
|
| 1899 |
+
"step": 675
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 1.75,
|
| 1903 |
+
"learning_rate": 1.2596401028277636e-05,
|
| 1904 |
+
"loss": 1.6447,
|
| 1905 |
+
"step": 680
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 1.75,
|
| 1909 |
+
"eval_loss": 1.6585614681243896,
|
| 1910 |
+
"eval_runtime": 31.8101,
|
| 1911 |
+
"eval_samples_per_second": 2.641,
|
| 1912 |
+
"eval_steps_per_second": 0.346,
|
| 1913 |
+
"step": 680
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 1.76,
|
| 1917 |
+
"learning_rate": 1.1953727506426736e-05,
|
| 1918 |
+
"loss": 1.6511,
|
| 1919 |
+
"step": 685
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 1.76,
|
| 1923 |
+
"eval_loss": 1.6583601236343384,
|
| 1924 |
+
"eval_runtime": 31.8125,
|
| 1925 |
+
"eval_samples_per_second": 2.64,
|
| 1926 |
+
"eval_steps_per_second": 0.346,
|
| 1927 |
+
"step": 685
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 1.77,
|
| 1931 |
+
"learning_rate": 1.1311053984575835e-05,
|
| 1932 |
+
"loss": 1.6496,
|
| 1933 |
+
"step": 690
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 1.77,
|
| 1937 |
+
"eval_loss": 1.6583328247070312,
|
| 1938 |
+
"eval_runtime": 31.8179,
|
| 1939 |
+
"eval_samples_per_second": 2.64,
|
| 1940 |
+
"eval_steps_per_second": 0.346,
|
| 1941 |
+
"step": 690
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 1.79,
|
| 1945 |
+
"learning_rate": 1.0668380462724936e-05,
|
| 1946 |
+
"loss": 1.6421,
|
| 1947 |
+
"step": 695
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 1.79,
|
| 1951 |
+
"eval_loss": 1.6583188772201538,
|
| 1952 |
+
"eval_runtime": 31.8165,
|
| 1953 |
+
"eval_samples_per_second": 2.64,
|
| 1954 |
+
"eval_steps_per_second": 0.346,
|
| 1955 |
+
"step": 695
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 1.8,
|
| 1959 |
+
"learning_rate": 1.0025706940874038e-05,
|
| 1960 |
+
"loss": 1.6126,
|
| 1961 |
+
"step": 700
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 1.8,
|
| 1965 |
+
"eval_loss": 1.6580705642700195,
|
| 1966 |
+
"eval_runtime": 31.8164,
|
| 1967 |
+
"eval_samples_per_second": 2.64,
|
| 1968 |
+
"eval_steps_per_second": 0.346,
|
| 1969 |
+
"step": 700
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 1.81,
|
| 1973 |
+
"learning_rate": 9.383033419023137e-06,
|
| 1974 |
+
"loss": 1.6226,
|
| 1975 |
+
"step": 705
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 1.81,
|
| 1979 |
+
"eval_loss": 1.6584465503692627,
|
| 1980 |
+
"eval_runtime": 31.816,
|
| 1981 |
+
"eval_samples_per_second": 2.64,
|
| 1982 |
+
"eval_steps_per_second": 0.346,
|
| 1983 |
+
"step": 705
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 1.83,
|
| 1987 |
+
"learning_rate": 8.740359897172237e-06,
|
| 1988 |
+
"loss": 1.6923,
|
| 1989 |
+
"step": 710
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 1.83,
|
| 1993 |
+
"eval_loss": 1.658342957496643,
|
| 1994 |
+
"eval_runtime": 31.8215,
|
| 1995 |
+
"eval_samples_per_second": 2.64,
|
| 1996 |
+
"eval_steps_per_second": 0.346,
|
| 1997 |
+
"step": 710
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 1.84,
|
| 2001 |
+
"learning_rate": 8.097686375321336e-06,
|
| 2002 |
+
"loss": 1.6224,
|
| 2003 |
+
"step": 715
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 1.84,
|
| 2007 |
+
"eval_loss": 1.6582502126693726,
|
| 2008 |
+
"eval_runtime": 31.812,
|
| 2009 |
+
"eval_samples_per_second": 2.641,
|
| 2010 |
+
"eval_steps_per_second": 0.346,
|
| 2011 |
+
"step": 715
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 1.85,
|
| 2015 |
+
"learning_rate": 7.4550128534704376e-06,
|
| 2016 |
+
"loss": 1.6587,
|
| 2017 |
+
"step": 720
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 1.85,
|
| 2021 |
+
"eval_loss": 1.658232569694519,
|
| 2022 |
+
"eval_runtime": 31.8059,
|
| 2023 |
+
"eval_samples_per_second": 2.641,
|
| 2024 |
+
"eval_steps_per_second": 0.346,
|
| 2025 |
+
"step": 720
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 1.86,
|
| 2029 |
+
"learning_rate": 6.812339331619537e-06,
|
| 2030 |
+
"loss": 1.6641,
|
| 2031 |
+
"step": 725
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 1.86,
|
| 2035 |
+
"eval_loss": 1.6582419872283936,
|
| 2036 |
+
"eval_runtime": 31.81,
|
| 2037 |
+
"eval_samples_per_second": 2.641,
|
| 2038 |
+
"eval_steps_per_second": 0.346,
|
| 2039 |
+
"step": 725
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 1.88,
|
| 2043 |
+
"learning_rate": 6.169665809768638e-06,
|
| 2044 |
+
"loss": 1.6419,
|
| 2045 |
+
"step": 730
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 1.88,
|
| 2049 |
+
"eval_loss": 1.6582107543945312,
|
| 2050 |
+
"eval_runtime": 31.833,
|
| 2051 |
+
"eval_samples_per_second": 2.639,
|
| 2052 |
+
"eval_steps_per_second": 0.346,
|
| 2053 |
+
"step": 730
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 1.89,
|
| 2057 |
+
"learning_rate": 5.526992287917738e-06,
|
| 2058 |
+
"loss": 1.652,
|
| 2059 |
+
"step": 735
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 1.89,
|
| 2063 |
+
"eval_loss": 1.6582270860671997,
|
| 2064 |
+
"eval_runtime": 31.8801,
|
| 2065 |
+
"eval_samples_per_second": 2.635,
|
| 2066 |
+
"eval_steps_per_second": 0.345,
|
| 2067 |
+
"step": 735
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 1.9,
|
| 2071 |
+
"learning_rate": 4.884318766066838e-06,
|
| 2072 |
+
"loss": 1.6487,
|
| 2073 |
+
"step": 740
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 1.9,
|
| 2077 |
+
"eval_loss": 1.6582915782928467,
|
| 2078 |
+
"eval_runtime": 31.8265,
|
| 2079 |
+
"eval_samples_per_second": 2.639,
|
| 2080 |
+
"eval_steps_per_second": 0.346,
|
| 2081 |
+
"step": 740
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 1.92,
|
| 2085 |
+
"learning_rate": 4.241645244215939e-06,
|
| 2086 |
+
"loss": 1.6245,
|
| 2087 |
+
"step": 745
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 1.92,
|
| 2091 |
+
"eval_loss": 1.658047080039978,
|
| 2092 |
+
"eval_runtime": 31.8109,
|
| 2093 |
+
"eval_samples_per_second": 2.641,
|
| 2094 |
+
"eval_steps_per_second": 0.346,
|
| 2095 |
+
"step": 745
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 1.93,
|
| 2099 |
+
"learning_rate": 3.598971722365039e-06,
|
| 2100 |
+
"loss": 1.6553,
|
| 2101 |
+
"step": 750
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 1.93,
|
| 2105 |
+
"eval_loss": 1.6578683853149414,
|
| 2106 |
+
"eval_runtime": 31.8025,
|
| 2107 |
+
"eval_samples_per_second": 2.641,
|
| 2108 |
+
"eval_steps_per_second": 0.346,
|
| 2109 |
+
"step": 750
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 1.94,
|
| 2113 |
+
"learning_rate": 2.956298200514139e-06,
|
| 2114 |
+
"loss": 1.653,
|
| 2115 |
+
"step": 755
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 1.94,
|
| 2119 |
+
"eval_loss": 1.6578799486160278,
|
| 2120 |
+
"eval_runtime": 31.8005,
|
| 2121 |
+
"eval_samples_per_second": 2.641,
|
| 2122 |
+
"eval_steps_per_second": 0.346,
|
| 2123 |
+
"step": 755
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 1.95,
|
| 2127 |
+
"learning_rate": 2.313624678663239e-06,
|
| 2128 |
+
"loss": 1.6519,
|
| 2129 |
+
"step": 760
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 1.95,
|
| 2133 |
+
"eval_loss": 1.657995343208313,
|
| 2134 |
+
"eval_runtime": 31.8085,
|
| 2135 |
+
"eval_samples_per_second": 2.641,
|
| 2136 |
+
"eval_steps_per_second": 0.346,
|
| 2137 |
+
"step": 760
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 1.97,
|
| 2141 |
+
"learning_rate": 1.6709511568123394e-06,
|
| 2142 |
+
"loss": 1.6955,
|
| 2143 |
+
"step": 765
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 1.97,
|
| 2147 |
+
"eval_loss": 1.6578824520111084,
|
| 2148 |
+
"eval_runtime": 31.8128,
|
| 2149 |
+
"eval_samples_per_second": 2.64,
|
| 2150 |
+
"eval_steps_per_second": 0.346,
|
| 2151 |
+
"step": 765
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 1.98,
|
| 2155 |
+
"learning_rate": 1.0282776349614395e-06,
|
| 2156 |
+
"loss": 1.6327,
|
| 2157 |
+
"step": 770
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 1.98,
|
| 2161 |
+
"eval_loss": 1.6581860780715942,
|
| 2162 |
+
"eval_runtime": 31.8501,
|
| 2163 |
+
"eval_samples_per_second": 2.637,
|
| 2164 |
+
"eval_steps_per_second": 0.345,
|
| 2165 |
+
"step": 770
|
| 2166 |
+
}
|
| 2167 |
+
],
|
| 2168 |
+
"logging_steps": 5,
|
| 2169 |
+
"max_steps": 778,
|
| 2170 |
+
"num_train_epochs": 2,
|
| 2171 |
+
"save_steps": 10,
|
| 2172 |
+
"total_flos": 2.5014589754179584e+17,
|
| 2173 |
+
"trial_name": null,
|
| 2174 |
+
"trial_params": null
|
| 2175 |
+
}
|
checkpoint-770/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc6a8542abd91027de58ebfccafdf919108680707834fe188d91cae077ef8e9
|
| 3 |
+
size 4600
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 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": 11008,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"num_key_value_heads": 32,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"quantization_config": {
|
| 20 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 21 |
+
"bnb_4bit_quant_type": "fp4",
|
| 22 |
+
"bnb_4bit_use_double_quant": false,
|
| 23 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 24 |
+
"llm_int8_has_fp16_weight": false,
|
| 25 |
+
"llm_int8_skip_modules": null,
|
| 26 |
+
"llm_int8_threshold": 6.0,
|
| 27 |
+
"load_in_4bit": false,
|
| 28 |
+
"load_in_8bit": true,
|
| 29 |
+
"quant_method": "bitsandbytes"
|
| 30 |
+
},
|
| 31 |
+
"rms_norm_eps": 1e-05,
|
| 32 |
+
"rope_scaling": null,
|
| 33 |
+
"rope_theta": 10000.0,
|
| 34 |
+
"tie_word_embeddings": false,
|
| 35 |
+
"torch_dtype": "float16",
|
| 36 |
+
"transformers_version": "4.35.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 32000
|
| 39 |
+
}
|
logs/events.out.tfevents.1699989718.node0370.palmetto.clemson.edu.1119956.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8338f7ab492bb36430b90fde21a7822be3a5f94276aa93f72ad83aeaf872e40
|
| 3 |
+
size 4868
|
logs/events.out.tfevents.1699989813.node0370.palmetto.clemson.edu.1119956.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4773b11c0e593bac1fe819e5c6324bb2a3542c475a7d375bb608e46408b2b009
|
| 3 |
+
size 4602
|
logs/events.out.tfevents.1699994287.node0370.palmetto.clemson.edu.1126403.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edff87033b1a80ab70d0a0af49d7943790a698e659a0875f929d78a3299c699d
|
| 3 |
+
size 7962
|
logs/events.out.tfevents.1699995040.node0370.palmetto.clemson.edu.1127435.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f054998bd37e1977597fdb66e495fb58c70a3b0042fa2ef4428756252ee49a4c
|
| 3 |
+
size 33937
|
logs/events.out.tfevents.1700064888.node0277.palmetto.clemson.edu.1971495.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:587a2145d6c92f9cbc7c114d9b2d452e13239b0a925f3bdcaa5631c48bdca19a
|
| 3 |
+
size 9908
|
logs/events.out.tfevents.1700066157.node0277.palmetto.clemson.edu.1973537.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fcffea7a0e86207d5c20daaabb71040aa71cb529a4bbddc4a309e37d9666f12
|
| 3 |
+
size 14528
|