Upload folder using huggingface_hub
Browse files- checkpoint-1000/config.json +28 -0
- checkpoint-1000/generation_config.json +7 -0
- checkpoint-1000/model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +3520 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1500/config.json +28 -0
- checkpoint-1500/generation_config.json +7 -0
- checkpoint-1500/model.safetensors +3 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/trainer_state.json +0 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/config.json +28 -0
- checkpoint-2000/generation_config.json +7 -0
- checkpoint-2000/model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +0 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2500/config.json +28 -0
- checkpoint-2500/generation_config.json +7 -0
- checkpoint-2500/model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/trainer_state.json +0 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-500/config.json +28 -0
- checkpoint-500/generation_config.json +7 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +1770 -0
- checkpoint-500/training_args.bin +3 -0
checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "jeff31415/TinyLlama-1.1B-1T-OpenOrca",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 22,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float16",
|
| 25 |
+
"transformers_version": "4.36.0.dev0",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32000
|
| 28 |
+
}
|
checkpoint-1000/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.36.0.dev0"
|
| 7 |
+
}
|
checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aca7e1e3a7ac58fc36313e66b7502f3d7c4bf03e8869f06228adafb38483f0ae
|
| 3 |
+
size 2200119664
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8040fb77eaa911da75dd4aa44cced35aeb81d1db5fefe40ceb4c3aa73aef4da4
|
| 3 |
+
size 2205161786
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8748f9c0f005c51ecb3c36eff4ca818edc4663c6499fe0cdc854d122b22097cf
|
| 3 |
+
size 14244
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d0f25bcc1f1518a06ae036d2fecae79a53374d049e84d421fa0c640ceb01ab1
|
| 3 |
+
size 1064
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,3520 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.5175316333770752,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-1000",
|
| 4 |
+
"epoch": 0.4,
|
| 5 |
+
"eval_steps": 4,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 2.9951999999999997e-07,
|
| 14 |
+
"loss": 2.6285,
|
| 15 |
+
"step": 4
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"eval_loss": 2.4697508811950684,
|
| 20 |
+
"eval_runtime": 0.485,
|
| 21 |
+
"eval_samples_per_second": 8.248,
|
| 22 |
+
"eval_steps_per_second": 2.062,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0,
|
| 27 |
+
"learning_rate": 2.9904e-07,
|
| 28 |
+
"loss": 2.6222,
|
| 29 |
+
"step": 8
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.0,
|
| 33 |
+
"eval_loss": 2.465975284576416,
|
| 34 |
+
"eval_runtime": 0.6323,
|
| 35 |
+
"eval_samples_per_second": 6.326,
|
| 36 |
+
"eval_steps_per_second": 1.582,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0,
|
| 41 |
+
"learning_rate": 2.9856e-07,
|
| 42 |
+
"loss": 2.6536,
|
| 43 |
+
"step": 12
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.0,
|
| 47 |
+
"eval_loss": 2.460374116897583,
|
| 48 |
+
"eval_runtime": 0.6478,
|
| 49 |
+
"eval_samples_per_second": 6.175,
|
| 50 |
+
"eval_steps_per_second": 1.544,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"learning_rate": 2.9808e-07,
|
| 56 |
+
"loss": 2.6785,
|
| 57 |
+
"step": 16
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.01,
|
| 61 |
+
"eval_loss": 2.4556970596313477,
|
| 62 |
+
"eval_runtime": 0.6653,
|
| 63 |
+
"eval_samples_per_second": 6.012,
|
| 64 |
+
"eval_steps_per_second": 1.503,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.01,
|
| 69 |
+
"learning_rate": 2.9759999999999996e-07,
|
| 70 |
+
"loss": 2.6085,
|
| 71 |
+
"step": 20
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.01,
|
| 75 |
+
"eval_loss": 2.4514715671539307,
|
| 76 |
+
"eval_runtime": 0.5241,
|
| 77 |
+
"eval_samples_per_second": 7.632,
|
| 78 |
+
"eval_steps_per_second": 1.908,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.01,
|
| 83 |
+
"learning_rate": 2.9711999999999995e-07,
|
| 84 |
+
"loss": 2.5907,
|
| 85 |
+
"step": 24
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.01,
|
| 89 |
+
"eval_loss": 2.4462974071502686,
|
| 90 |
+
"eval_runtime": 0.4689,
|
| 91 |
+
"eval_samples_per_second": 8.53,
|
| 92 |
+
"eval_steps_per_second": 2.133,
|
| 93 |
+
"step": 24
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.01,
|
| 97 |
+
"learning_rate": 2.9664e-07,
|
| 98 |
+
"loss": 2.5942,
|
| 99 |
+
"step": 28
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.01,
|
| 103 |
+
"eval_loss": 2.4415194988250732,
|
| 104 |
+
"eval_runtime": 0.4829,
|
| 105 |
+
"eval_samples_per_second": 8.284,
|
| 106 |
+
"eval_steps_per_second": 2.071,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.01,
|
| 111 |
+
"learning_rate": 2.9615999999999997e-07,
|
| 112 |
+
"loss": 2.6101,
|
| 113 |
+
"step": 32
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.01,
|
| 117 |
+
"eval_loss": 2.437161922454834,
|
| 118 |
+
"eval_runtime": 0.4715,
|
| 119 |
+
"eval_samples_per_second": 8.483,
|
| 120 |
+
"eval_steps_per_second": 2.121,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.01,
|
| 125 |
+
"learning_rate": 2.9568e-07,
|
| 126 |
+
"loss": 2.5827,
|
| 127 |
+
"step": 36
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.01,
|
| 131 |
+
"eval_loss": 2.432689666748047,
|
| 132 |
+
"eval_runtime": 0.4938,
|
| 133 |
+
"eval_samples_per_second": 8.1,
|
| 134 |
+
"eval_steps_per_second": 2.025,
|
| 135 |
+
"step": 36
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.02,
|
| 139 |
+
"learning_rate": 2.952e-07,
|
| 140 |
+
"loss": 2.5729,
|
| 141 |
+
"step": 40
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.02,
|
| 145 |
+
"eval_loss": 2.4281153678894043,
|
| 146 |
+
"eval_runtime": 0.5021,
|
| 147 |
+
"eval_samples_per_second": 7.966,
|
| 148 |
+
"eval_steps_per_second": 1.991,
|
| 149 |
+
"step": 40
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.02,
|
| 153 |
+
"learning_rate": 2.9472e-07,
|
| 154 |
+
"loss": 2.5856,
|
| 155 |
+
"step": 44
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.02,
|
| 159 |
+
"eval_loss": 2.423053741455078,
|
| 160 |
+
"eval_runtime": 0.593,
|
| 161 |
+
"eval_samples_per_second": 6.746,
|
| 162 |
+
"eval_steps_per_second": 1.686,
|
| 163 |
+
"step": 44
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.02,
|
| 167 |
+
"learning_rate": 2.9423999999999997e-07,
|
| 168 |
+
"loss": 2.589,
|
| 169 |
+
"step": 48
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.02,
|
| 173 |
+
"eval_loss": 2.418571949005127,
|
| 174 |
+
"eval_runtime": 0.6933,
|
| 175 |
+
"eval_samples_per_second": 5.77,
|
| 176 |
+
"eval_steps_per_second": 1.442,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.02,
|
| 181 |
+
"learning_rate": 2.9375999999999995e-07,
|
| 182 |
+
"loss": 2.6483,
|
| 183 |
+
"step": 52
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.02,
|
| 187 |
+
"eval_loss": 2.414531946182251,
|
| 188 |
+
"eval_runtime": 0.7167,
|
| 189 |
+
"eval_samples_per_second": 5.581,
|
| 190 |
+
"eval_steps_per_second": 1.395,
|
| 191 |
+
"step": 52
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.02,
|
| 195 |
+
"learning_rate": 2.9328e-07,
|
| 196 |
+
"loss": 2.517,
|
| 197 |
+
"step": 56
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.02,
|
| 201 |
+
"eval_loss": 2.409538745880127,
|
| 202 |
+
"eval_runtime": 0.4826,
|
| 203 |
+
"eval_samples_per_second": 8.289,
|
| 204 |
+
"eval_steps_per_second": 2.072,
|
| 205 |
+
"step": 56
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.02,
|
| 209 |
+
"learning_rate": 2.928e-07,
|
| 210 |
+
"loss": 2.5987,
|
| 211 |
+
"step": 60
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.02,
|
| 215 |
+
"eval_loss": 2.4050426483154297,
|
| 216 |
+
"eval_runtime": 0.4757,
|
| 217 |
+
"eval_samples_per_second": 8.409,
|
| 218 |
+
"eval_steps_per_second": 2.102,
|
| 219 |
+
"step": 60
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.03,
|
| 223 |
+
"learning_rate": 2.9232e-07,
|
| 224 |
+
"loss": 2.5489,
|
| 225 |
+
"step": 64
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.03,
|
| 229 |
+
"eval_loss": 2.400360107421875,
|
| 230 |
+
"eval_runtime": 0.4945,
|
| 231 |
+
"eval_samples_per_second": 8.089,
|
| 232 |
+
"eval_steps_per_second": 2.022,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.03,
|
| 237 |
+
"learning_rate": 2.9184e-07,
|
| 238 |
+
"loss": 2.5063,
|
| 239 |
+
"step": 68
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.03,
|
| 243 |
+
"eval_loss": 2.396500587463379,
|
| 244 |
+
"eval_runtime": 0.5,
|
| 245 |
+
"eval_samples_per_second": 8.001,
|
| 246 |
+
"eval_steps_per_second": 2.0,
|
| 247 |
+
"step": 68
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.03,
|
| 251 |
+
"learning_rate": 2.9136e-07,
|
| 252 |
+
"loss": 2.5867,
|
| 253 |
+
"step": 72
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.03,
|
| 257 |
+
"eval_loss": 2.3916146755218506,
|
| 258 |
+
"eval_runtime": 0.4602,
|
| 259 |
+
"eval_samples_per_second": 8.693,
|
| 260 |
+
"eval_steps_per_second": 2.173,
|
| 261 |
+
"step": 72
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.03,
|
| 265 |
+
"learning_rate": 2.9087999999999997e-07,
|
| 266 |
+
"loss": 2.544,
|
| 267 |
+
"step": 76
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.03,
|
| 271 |
+
"eval_loss": 2.3873047828674316,
|
| 272 |
+
"eval_runtime": 0.4731,
|
| 273 |
+
"eval_samples_per_second": 8.456,
|
| 274 |
+
"eval_steps_per_second": 2.114,
|
| 275 |
+
"step": 76
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.03,
|
| 279 |
+
"learning_rate": 2.9039999999999995e-07,
|
| 280 |
+
"loss": 2.5596,
|
| 281 |
+
"step": 80
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.03,
|
| 285 |
+
"eval_loss": 2.382803440093994,
|
| 286 |
+
"eval_runtime": 0.6092,
|
| 287 |
+
"eval_samples_per_second": 6.566,
|
| 288 |
+
"eval_steps_per_second": 1.642,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.03,
|
| 293 |
+
"learning_rate": 2.8992e-07,
|
| 294 |
+
"loss": 2.5744,
|
| 295 |
+
"step": 84
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.03,
|
| 299 |
+
"eval_loss": 2.3786380290985107,
|
| 300 |
+
"eval_runtime": 0.7212,
|
| 301 |
+
"eval_samples_per_second": 5.546,
|
| 302 |
+
"eval_steps_per_second": 1.387,
|
| 303 |
+
"step": 84
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.04,
|
| 307 |
+
"learning_rate": 2.8944e-07,
|
| 308 |
+
"loss": 2.5588,
|
| 309 |
+
"step": 88
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.04,
|
| 313 |
+
"eval_loss": 2.374176502227783,
|
| 314 |
+
"eval_runtime": 0.6826,
|
| 315 |
+
"eval_samples_per_second": 5.86,
|
| 316 |
+
"eval_steps_per_second": 1.465,
|
| 317 |
+
"step": 88
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.04,
|
| 321 |
+
"learning_rate": 2.8895999999999996e-07,
|
| 322 |
+
"loss": 2.5579,
|
| 323 |
+
"step": 92
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.04,
|
| 327 |
+
"eval_loss": 2.3702104091644287,
|
| 328 |
+
"eval_runtime": 0.4896,
|
| 329 |
+
"eval_samples_per_second": 8.169,
|
| 330 |
+
"eval_steps_per_second": 2.042,
|
| 331 |
+
"step": 92
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.04,
|
| 335 |
+
"learning_rate": 2.8848e-07,
|
| 336 |
+
"loss": 2.5245,
|
| 337 |
+
"step": 96
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.04,
|
| 341 |
+
"eval_loss": 2.3660218715667725,
|
| 342 |
+
"eval_runtime": 0.4764,
|
| 343 |
+
"eval_samples_per_second": 8.397,
|
| 344 |
+
"eval_steps_per_second": 2.099,
|
| 345 |
+
"step": 96
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.04,
|
| 349 |
+
"learning_rate": 2.88e-07,
|
| 350 |
+
"loss": 2.5132,
|
| 351 |
+
"step": 100
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.04,
|
| 355 |
+
"eval_loss": 2.36110520362854,
|
| 356 |
+
"eval_runtime": 0.4799,
|
| 357 |
+
"eval_samples_per_second": 8.335,
|
| 358 |
+
"eval_steps_per_second": 2.084,
|
| 359 |
+
"step": 100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.04,
|
| 363 |
+
"learning_rate": 2.8751999999999997e-07,
|
| 364 |
+
"loss": 2.5037,
|
| 365 |
+
"step": 104
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.04,
|
| 369 |
+
"eval_loss": 2.3570125102996826,
|
| 370 |
+
"eval_runtime": 0.4722,
|
| 371 |
+
"eval_samples_per_second": 8.47,
|
| 372 |
+
"eval_steps_per_second": 2.118,
|
| 373 |
+
"step": 104
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.04,
|
| 377 |
+
"learning_rate": 2.8704e-07,
|
| 378 |
+
"loss": 2.4727,
|
| 379 |
+
"step": 108
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.04,
|
| 383 |
+
"eval_loss": 2.3530666828155518,
|
| 384 |
+
"eval_runtime": 0.467,
|
| 385 |
+
"eval_samples_per_second": 8.565,
|
| 386 |
+
"eval_steps_per_second": 2.141,
|
| 387 |
+
"step": 108
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.04,
|
| 391 |
+
"learning_rate": 2.8656e-07,
|
| 392 |
+
"loss": 2.4709,
|
| 393 |
+
"step": 112
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.04,
|
| 397 |
+
"eval_loss": 2.348759412765503,
|
| 398 |
+
"eval_runtime": 0.501,
|
| 399 |
+
"eval_samples_per_second": 7.984,
|
| 400 |
+
"eval_steps_per_second": 1.996,
|
| 401 |
+
"step": 112
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.05,
|
| 405 |
+
"learning_rate": 2.8608e-07,
|
| 406 |
+
"loss": 2.4711,
|
| 407 |
+
"step": 116
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.05,
|
| 411 |
+
"eval_loss": 2.344454050064087,
|
| 412 |
+
"eval_runtime": 0.6607,
|
| 413 |
+
"eval_samples_per_second": 6.054,
|
| 414 |
+
"eval_steps_per_second": 1.513,
|
| 415 |
+
"step": 116
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.05,
|
| 419 |
+
"learning_rate": 2.8559999999999996e-07,
|
| 420 |
+
"loss": 2.5445,
|
| 421 |
+
"step": 120
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.05,
|
| 425 |
+
"eval_loss": 2.3402156829833984,
|
| 426 |
+
"eval_runtime": 0.704,
|
| 427 |
+
"eval_samples_per_second": 5.682,
|
| 428 |
+
"eval_steps_per_second": 1.42,
|
| 429 |
+
"step": 120
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.05,
|
| 433 |
+
"learning_rate": 2.8512e-07,
|
| 434 |
+
"loss": 2.4994,
|
| 435 |
+
"step": 124
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.05,
|
| 439 |
+
"eval_loss": 2.3362019062042236,
|
| 440 |
+
"eval_runtime": 0.6849,
|
| 441 |
+
"eval_samples_per_second": 5.84,
|
| 442 |
+
"eval_steps_per_second": 1.46,
|
| 443 |
+
"step": 124
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.05,
|
| 447 |
+
"learning_rate": 2.8464e-07,
|
| 448 |
+
"loss": 2.5036,
|
| 449 |
+
"step": 128
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.05,
|
| 453 |
+
"eval_loss": 2.3319339752197266,
|
| 454 |
+
"eval_runtime": 0.4864,
|
| 455 |
+
"eval_samples_per_second": 8.223,
|
| 456 |
+
"eval_steps_per_second": 2.056,
|
| 457 |
+
"step": 128
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.05,
|
| 461 |
+
"learning_rate": 2.8416e-07,
|
| 462 |
+
"loss": 2.5525,
|
| 463 |
+
"step": 132
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.05,
|
| 467 |
+
"eval_loss": 2.3276522159576416,
|
| 468 |
+
"eval_runtime": 0.4783,
|
| 469 |
+
"eval_samples_per_second": 8.364,
|
| 470 |
+
"eval_steps_per_second": 2.091,
|
| 471 |
+
"step": 132
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.05,
|
| 475 |
+
"learning_rate": 2.8368e-07,
|
| 476 |
+
"loss": 2.5245,
|
| 477 |
+
"step": 136
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.05,
|
| 481 |
+
"eval_loss": 2.3241090774536133,
|
| 482 |
+
"eval_runtime": 0.4805,
|
| 483 |
+
"eval_samples_per_second": 8.324,
|
| 484 |
+
"eval_steps_per_second": 2.081,
|
| 485 |
+
"step": 136
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.06,
|
| 489 |
+
"learning_rate": 2.832e-07,
|
| 490 |
+
"loss": 2.4946,
|
| 491 |
+
"step": 140
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.06,
|
| 495 |
+
"eval_loss": 2.3198165893554688,
|
| 496 |
+
"eval_runtime": 0.473,
|
| 497 |
+
"eval_samples_per_second": 8.457,
|
| 498 |
+
"eval_steps_per_second": 2.114,
|
| 499 |
+
"step": 140
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.06,
|
| 503 |
+
"learning_rate": 2.8272e-07,
|
| 504 |
+
"loss": 2.5142,
|
| 505 |
+
"step": 144
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.06,
|
| 509 |
+
"eval_loss": 2.3152613639831543,
|
| 510 |
+
"eval_runtime": 0.4858,
|
| 511 |
+
"eval_samples_per_second": 8.234,
|
| 512 |
+
"eval_steps_per_second": 2.058,
|
| 513 |
+
"step": 144
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.06,
|
| 517 |
+
"learning_rate": 2.8223999999999997e-07,
|
| 518 |
+
"loss": 2.4639,
|
| 519 |
+
"step": 148
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.06,
|
| 523 |
+
"eval_loss": 2.3112645149230957,
|
| 524 |
+
"eval_runtime": 0.488,
|
| 525 |
+
"eval_samples_per_second": 8.196,
|
| 526 |
+
"eval_steps_per_second": 2.049,
|
| 527 |
+
"step": 148
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.06,
|
| 531 |
+
"learning_rate": 2.8176e-07,
|
| 532 |
+
"loss": 2.4796,
|
| 533 |
+
"step": 152
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.06,
|
| 537 |
+
"eval_loss": 2.307020902633667,
|
| 538 |
+
"eval_runtime": 0.6163,
|
| 539 |
+
"eval_samples_per_second": 6.49,
|
| 540 |
+
"eval_steps_per_second": 1.623,
|
| 541 |
+
"step": 152
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.06,
|
| 545 |
+
"learning_rate": 2.8128e-07,
|
| 546 |
+
"loss": 2.4529,
|
| 547 |
+
"step": 156
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.06,
|
| 551 |
+
"eval_loss": 2.303062915802002,
|
| 552 |
+
"eval_runtime": 0.6764,
|
| 553 |
+
"eval_samples_per_second": 5.913,
|
| 554 |
+
"eval_steps_per_second": 1.478,
|
| 555 |
+
"step": 156
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.06,
|
| 559 |
+
"learning_rate": 2.808e-07,
|
| 560 |
+
"loss": 2.4823,
|
| 561 |
+
"step": 160
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.06,
|
| 565 |
+
"eval_loss": 2.2993311882019043,
|
| 566 |
+
"eval_runtime": 0.6854,
|
| 567 |
+
"eval_samples_per_second": 5.836,
|
| 568 |
+
"eval_steps_per_second": 1.459,
|
| 569 |
+
"step": 160
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.07,
|
| 573 |
+
"learning_rate": 2.8032e-07,
|
| 574 |
+
"loss": 2.4439,
|
| 575 |
+
"step": 164
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.07,
|
| 579 |
+
"eval_loss": 2.2947850227355957,
|
| 580 |
+
"eval_runtime": 0.4745,
|
| 581 |
+
"eval_samples_per_second": 8.429,
|
| 582 |
+
"eval_steps_per_second": 2.107,
|
| 583 |
+
"step": 164
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.07,
|
| 587 |
+
"learning_rate": 2.7984e-07,
|
| 588 |
+
"loss": 2.4652,
|
| 589 |
+
"step": 168
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.07,
|
| 593 |
+
"eval_loss": 2.2908992767333984,
|
| 594 |
+
"eval_runtime": 0.4759,
|
| 595 |
+
"eval_samples_per_second": 8.406,
|
| 596 |
+
"eval_steps_per_second": 2.101,
|
| 597 |
+
"step": 168
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.07,
|
| 601 |
+
"learning_rate": 2.7936e-07,
|
| 602 |
+
"loss": 2.4574,
|
| 603 |
+
"step": 172
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.07,
|
| 607 |
+
"eval_loss": 2.2867026329040527,
|
| 608 |
+
"eval_runtime": 0.4973,
|
| 609 |
+
"eval_samples_per_second": 8.043,
|
| 610 |
+
"eval_steps_per_second": 2.011,
|
| 611 |
+
"step": 172
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.07,
|
| 615 |
+
"learning_rate": 2.7887999999999997e-07,
|
| 616 |
+
"loss": 2.4557,
|
| 617 |
+
"step": 176
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.07,
|
| 621 |
+
"eval_loss": 2.283027172088623,
|
| 622 |
+
"eval_runtime": 0.4719,
|
| 623 |
+
"eval_samples_per_second": 8.477,
|
| 624 |
+
"eval_steps_per_second": 2.119,
|
| 625 |
+
"step": 176
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.07,
|
| 629 |
+
"learning_rate": 2.784e-07,
|
| 630 |
+
"loss": 2.4462,
|
| 631 |
+
"step": 180
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.07,
|
| 635 |
+
"eval_loss": 2.2787420749664307,
|
| 636 |
+
"eval_runtime": 0.472,
|
| 637 |
+
"eval_samples_per_second": 8.474,
|
| 638 |
+
"eval_steps_per_second": 2.119,
|
| 639 |
+
"step": 180
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.07,
|
| 643 |
+
"learning_rate": 2.7792e-07,
|
| 644 |
+
"loss": 2.3962,
|
| 645 |
+
"step": 184
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.07,
|
| 649 |
+
"eval_loss": 2.2745461463928223,
|
| 650 |
+
"eval_runtime": 0.6328,
|
| 651 |
+
"eval_samples_per_second": 6.322,
|
| 652 |
+
"eval_steps_per_second": 1.58,
|
| 653 |
+
"step": 184
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.08,
|
| 657 |
+
"learning_rate": 2.7744e-07,
|
| 658 |
+
"loss": 2.3666,
|
| 659 |
+
"step": 188
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.08,
|
| 663 |
+
"eval_loss": 2.2705912590026855,
|
| 664 |
+
"eval_runtime": 0.6375,
|
| 665 |
+
"eval_samples_per_second": 6.274,
|
| 666 |
+
"eval_steps_per_second": 1.569,
|
| 667 |
+
"step": 188
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.08,
|
| 671 |
+
"learning_rate": 2.7696e-07,
|
| 672 |
+
"loss": 2.5024,
|
| 673 |
+
"step": 192
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.08,
|
| 677 |
+
"eval_loss": 2.266995906829834,
|
| 678 |
+
"eval_runtime": 0.6984,
|
| 679 |
+
"eval_samples_per_second": 5.727,
|
| 680 |
+
"eval_steps_per_second": 1.432,
|
| 681 |
+
"step": 192
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.08,
|
| 685 |
+
"learning_rate": 2.7648e-07,
|
| 686 |
+
"loss": 2.4419,
|
| 687 |
+
"step": 196
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.08,
|
| 691 |
+
"eval_loss": 2.2626519203186035,
|
| 692 |
+
"eval_runtime": 0.7334,
|
| 693 |
+
"eval_samples_per_second": 5.454,
|
| 694 |
+
"eval_steps_per_second": 1.363,
|
| 695 |
+
"step": 196
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.08,
|
| 699 |
+
"learning_rate": 2.76e-07,
|
| 700 |
+
"loss": 2.4246,
|
| 701 |
+
"step": 200
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.08,
|
| 705 |
+
"eval_loss": 2.2583603858947754,
|
| 706 |
+
"eval_runtime": 0.48,
|
| 707 |
+
"eval_samples_per_second": 8.333,
|
| 708 |
+
"eval_steps_per_second": 2.083,
|
| 709 |
+
"step": 200
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.08,
|
| 713 |
+
"learning_rate": 2.7551999999999997e-07,
|
| 714 |
+
"loss": 2.3853,
|
| 715 |
+
"step": 204
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.08,
|
| 719 |
+
"eval_loss": 2.2551512718200684,
|
| 720 |
+
"eval_runtime": 0.4939,
|
| 721 |
+
"eval_samples_per_second": 8.098,
|
| 722 |
+
"eval_steps_per_second": 2.025,
|
| 723 |
+
"step": 204
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.08,
|
| 727 |
+
"learning_rate": 2.7503999999999995e-07,
|
| 728 |
+
"loss": 2.4032,
|
| 729 |
+
"step": 208
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.08,
|
| 733 |
+
"eval_loss": 2.251105785369873,
|
| 734 |
+
"eval_runtime": 0.46,
|
| 735 |
+
"eval_samples_per_second": 8.695,
|
| 736 |
+
"eval_steps_per_second": 2.174,
|
| 737 |
+
"step": 208
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.08,
|
| 741 |
+
"learning_rate": 2.7456e-07,
|
| 742 |
+
"loss": 2.4444,
|
| 743 |
+
"step": 212
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.08,
|
| 747 |
+
"eval_loss": 2.247025489807129,
|
| 748 |
+
"eval_runtime": 0.4948,
|
| 749 |
+
"eval_samples_per_second": 8.084,
|
| 750 |
+
"eval_steps_per_second": 2.021,
|
| 751 |
+
"step": 212
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.09,
|
| 755 |
+
"learning_rate": 2.7408e-07,
|
| 756 |
+
"loss": 2.2932,
|
| 757 |
+
"step": 216
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.09,
|
| 761 |
+
"eval_loss": 2.242764472961426,
|
| 762 |
+
"eval_runtime": 0.4897,
|
| 763 |
+
"eval_samples_per_second": 8.168,
|
| 764 |
+
"eval_steps_per_second": 2.042,
|
| 765 |
+
"step": 216
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.09,
|
| 769 |
+
"learning_rate": 2.736e-07,
|
| 770 |
+
"loss": 2.3929,
|
| 771 |
+
"step": 220
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.09,
|
| 775 |
+
"eval_loss": 2.2391483783721924,
|
| 776 |
+
"eval_runtime": 0.6128,
|
| 777 |
+
"eval_samples_per_second": 6.528,
|
| 778 |
+
"eval_steps_per_second": 1.632,
|
| 779 |
+
"step": 220
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.09,
|
| 783 |
+
"learning_rate": 2.7312e-07,
|
| 784 |
+
"loss": 2.4112,
|
| 785 |
+
"step": 224
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.09,
|
| 789 |
+
"eval_loss": 2.234977960586548,
|
| 790 |
+
"eval_runtime": 0.648,
|
| 791 |
+
"eval_samples_per_second": 6.172,
|
| 792 |
+
"eval_steps_per_second": 1.543,
|
| 793 |
+
"step": 224
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.09,
|
| 797 |
+
"learning_rate": 2.7264e-07,
|
| 798 |
+
"loss": 2.4191,
|
| 799 |
+
"step": 228
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.09,
|
| 803 |
+
"eval_loss": 2.231099843978882,
|
| 804 |
+
"eval_runtime": 0.6862,
|
| 805 |
+
"eval_samples_per_second": 5.829,
|
| 806 |
+
"eval_steps_per_second": 1.457,
|
| 807 |
+
"step": 228
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.09,
|
| 811 |
+
"learning_rate": 2.7215999999999997e-07,
|
| 812 |
+
"loss": 2.4408,
|
| 813 |
+
"step": 232
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.09,
|
| 817 |
+
"eval_loss": 2.2272462844848633,
|
| 818 |
+
"eval_runtime": 0.7076,
|
| 819 |
+
"eval_samples_per_second": 5.653,
|
| 820 |
+
"eval_steps_per_second": 1.413,
|
| 821 |
+
"step": 232
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.09,
|
| 825 |
+
"learning_rate": 2.7167999999999996e-07,
|
| 826 |
+
"loss": 2.3884,
|
| 827 |
+
"step": 236
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.09,
|
| 831 |
+
"eval_loss": 2.223376750946045,
|
| 832 |
+
"eval_runtime": 0.5169,
|
| 833 |
+
"eval_samples_per_second": 7.738,
|
| 834 |
+
"eval_steps_per_second": 1.935,
|
| 835 |
+
"step": 236
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.1,
|
| 839 |
+
"learning_rate": 2.712e-07,
|
| 840 |
+
"loss": 2.3689,
|
| 841 |
+
"step": 240
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.1,
|
| 845 |
+
"eval_loss": 2.2195653915405273,
|
| 846 |
+
"eval_runtime": 0.4793,
|
| 847 |
+
"eval_samples_per_second": 8.346,
|
| 848 |
+
"eval_steps_per_second": 2.086,
|
| 849 |
+
"step": 240
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.1,
|
| 853 |
+
"learning_rate": 2.7072e-07,
|
| 854 |
+
"loss": 2.3689,
|
| 855 |
+
"step": 244
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.1,
|
| 859 |
+
"eval_loss": 2.2153775691986084,
|
| 860 |
+
"eval_runtime": 0.4771,
|
| 861 |
+
"eval_samples_per_second": 8.384,
|
| 862 |
+
"eval_steps_per_second": 2.096,
|
| 863 |
+
"step": 244
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.1,
|
| 867 |
+
"learning_rate": 2.7024e-07,
|
| 868 |
+
"loss": 2.3249,
|
| 869 |
+
"step": 248
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.1,
|
| 873 |
+
"eval_loss": 2.211355209350586,
|
| 874 |
+
"eval_runtime": 0.4778,
|
| 875 |
+
"eval_samples_per_second": 8.372,
|
| 876 |
+
"eval_steps_per_second": 2.093,
|
| 877 |
+
"step": 248
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.1,
|
| 881 |
+
"learning_rate": 2.6976e-07,
|
| 882 |
+
"loss": 2.4286,
|
| 883 |
+
"step": 252
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.1,
|
| 887 |
+
"eval_loss": 2.207773208618164,
|
| 888 |
+
"eval_runtime": 0.4873,
|
| 889 |
+
"eval_samples_per_second": 8.209,
|
| 890 |
+
"eval_steps_per_second": 2.052,
|
| 891 |
+
"step": 252
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.1,
|
| 895 |
+
"learning_rate": 2.6928e-07,
|
| 896 |
+
"loss": 2.3497,
|
| 897 |
+
"step": 256
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.1,
|
| 901 |
+
"eval_loss": 2.203867197036743,
|
| 902 |
+
"eval_runtime": 0.6281,
|
| 903 |
+
"eval_samples_per_second": 6.368,
|
| 904 |
+
"eval_steps_per_second": 1.592,
|
| 905 |
+
"step": 256
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.1,
|
| 909 |
+
"learning_rate": 2.6879999999999997e-07,
|
| 910 |
+
"loss": 2.284,
|
| 911 |
+
"step": 260
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.1,
|
| 915 |
+
"eval_loss": 2.199937582015991,
|
| 916 |
+
"eval_runtime": 0.6885,
|
| 917 |
+
"eval_samples_per_second": 5.81,
|
| 918 |
+
"eval_steps_per_second": 1.452,
|
| 919 |
+
"step": 260
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.11,
|
| 923 |
+
"learning_rate": 2.6831999999999996e-07,
|
| 924 |
+
"loss": 2.3333,
|
| 925 |
+
"step": 264
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.11,
|
| 929 |
+
"eval_loss": 2.1958465576171875,
|
| 930 |
+
"eval_runtime": 0.6799,
|
| 931 |
+
"eval_samples_per_second": 5.883,
|
| 932 |
+
"eval_steps_per_second": 1.471,
|
| 933 |
+
"step": 264
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.11,
|
| 937 |
+
"learning_rate": 2.6784e-07,
|
| 938 |
+
"loss": 2.3305,
|
| 939 |
+
"step": 268
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.11,
|
| 943 |
+
"eval_loss": 2.192072868347168,
|
| 944 |
+
"eval_runtime": 0.7165,
|
| 945 |
+
"eval_samples_per_second": 5.583,
|
| 946 |
+
"eval_steps_per_second": 1.396,
|
| 947 |
+
"step": 268
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.11,
|
| 951 |
+
"learning_rate": 2.6736e-07,
|
| 952 |
+
"loss": 2.3465,
|
| 953 |
+
"step": 272
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.11,
|
| 957 |
+
"eval_loss": 2.1882476806640625,
|
| 958 |
+
"eval_runtime": 0.485,
|
| 959 |
+
"eval_samples_per_second": 8.247,
|
| 960 |
+
"eval_steps_per_second": 2.062,
|
| 961 |
+
"step": 272
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.11,
|
| 965 |
+
"learning_rate": 2.6687999999999997e-07,
|
| 966 |
+
"loss": 2.3274,
|
| 967 |
+
"step": 276
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.11,
|
| 971 |
+
"eval_loss": 2.1841320991516113,
|
| 972 |
+
"eval_runtime": 0.4767,
|
| 973 |
+
"eval_samples_per_second": 8.391,
|
| 974 |
+
"eval_steps_per_second": 2.098,
|
| 975 |
+
"step": 276
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.11,
|
| 979 |
+
"learning_rate": 2.664e-07,
|
| 980 |
+
"loss": 2.3641,
|
| 981 |
+
"step": 280
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.11,
|
| 985 |
+
"eval_loss": 2.1803271770477295,
|
| 986 |
+
"eval_runtime": 0.5146,
|
| 987 |
+
"eval_samples_per_second": 7.774,
|
| 988 |
+
"eval_steps_per_second": 1.943,
|
| 989 |
+
"step": 280
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.11,
|
| 993 |
+
"learning_rate": 2.6592e-07,
|
| 994 |
+
"loss": 2.3089,
|
| 995 |
+
"step": 284
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.11,
|
| 999 |
+
"eval_loss": 2.176274538040161,
|
| 1000 |
+
"eval_runtime": 0.488,
|
| 1001 |
+
"eval_samples_per_second": 8.196,
|
| 1002 |
+
"eval_steps_per_second": 2.049,
|
| 1003 |
+
"step": 284
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.12,
|
| 1007 |
+
"learning_rate": 2.6543999999999997e-07,
|
| 1008 |
+
"loss": 2.2645,
|
| 1009 |
+
"step": 288
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.12,
|
| 1013 |
+
"eval_loss": 2.1720588207244873,
|
| 1014 |
+
"eval_runtime": 0.4973,
|
| 1015 |
+
"eval_samples_per_second": 8.043,
|
| 1016 |
+
"eval_steps_per_second": 2.011,
|
| 1017 |
+
"step": 288
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.12,
|
| 1021 |
+
"learning_rate": 2.6495999999999996e-07,
|
| 1022 |
+
"loss": 2.3439,
|
| 1023 |
+
"step": 292
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.12,
|
| 1027 |
+
"eval_loss": 2.1687240600585938,
|
| 1028 |
+
"eval_runtime": 0.6283,
|
| 1029 |
+
"eval_samples_per_second": 6.366,
|
| 1030 |
+
"eval_steps_per_second": 1.592,
|
| 1031 |
+
"step": 292
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.12,
|
| 1035 |
+
"learning_rate": 2.6448e-07,
|
| 1036 |
+
"loss": 2.3285,
|
| 1037 |
+
"step": 296
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.12,
|
| 1041 |
+
"eval_loss": 2.1649253368377686,
|
| 1042 |
+
"eval_runtime": 0.6996,
|
| 1043 |
+
"eval_samples_per_second": 5.718,
|
| 1044 |
+
"eval_steps_per_second": 1.429,
|
| 1045 |
+
"step": 296
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.12,
|
| 1049 |
+
"learning_rate": 2.64e-07,
|
| 1050 |
+
"loss": 2.3126,
|
| 1051 |
+
"step": 300
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.12,
|
| 1055 |
+
"eval_loss": 2.160398483276367,
|
| 1056 |
+
"eval_runtime": 0.6904,
|
| 1057 |
+
"eval_samples_per_second": 5.794,
|
| 1058 |
+
"eval_steps_per_second": 1.448,
|
| 1059 |
+
"step": 300
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.12,
|
| 1063 |
+
"learning_rate": 2.6351999999999997e-07,
|
| 1064 |
+
"loss": 2.3356,
|
| 1065 |
+
"step": 304
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.12,
|
| 1069 |
+
"eval_loss": 2.1570284366607666,
|
| 1070 |
+
"eval_runtime": 0.4953,
|
| 1071 |
+
"eval_samples_per_second": 8.076,
|
| 1072 |
+
"eval_steps_per_second": 2.019,
|
| 1073 |
+
"step": 304
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.12,
|
| 1077 |
+
"learning_rate": 2.6304e-07,
|
| 1078 |
+
"loss": 2.3396,
|
| 1079 |
+
"step": 308
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.12,
|
| 1083 |
+
"eval_loss": 2.1527013778686523,
|
| 1084 |
+
"eval_runtime": 0.4977,
|
| 1085 |
+
"eval_samples_per_second": 8.037,
|
| 1086 |
+
"eval_steps_per_second": 2.009,
|
| 1087 |
+
"step": 308
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.12,
|
| 1091 |
+
"learning_rate": 2.6256e-07,
|
| 1092 |
+
"loss": 2.2972,
|
| 1093 |
+
"step": 312
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 0.12,
|
| 1097 |
+
"eval_loss": 2.148724317550659,
|
| 1098 |
+
"eval_runtime": 0.4939,
|
| 1099 |
+
"eval_samples_per_second": 8.099,
|
| 1100 |
+
"eval_steps_per_second": 2.025,
|
| 1101 |
+
"step": 312
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.13,
|
| 1105 |
+
"learning_rate": 2.6208e-07,
|
| 1106 |
+
"loss": 2.3321,
|
| 1107 |
+
"step": 316
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.13,
|
| 1111 |
+
"eval_loss": 2.1449663639068604,
|
| 1112 |
+
"eval_runtime": 0.4784,
|
| 1113 |
+
"eval_samples_per_second": 8.362,
|
| 1114 |
+
"eval_steps_per_second": 2.09,
|
| 1115 |
+
"step": 316
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.13,
|
| 1119 |
+
"learning_rate": 2.616e-07,
|
| 1120 |
+
"loss": 2.3348,
|
| 1121 |
+
"step": 320
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.13,
|
| 1125 |
+
"eval_loss": 2.1414906978607178,
|
| 1126 |
+
"eval_runtime": 0.4949,
|
| 1127 |
+
"eval_samples_per_second": 8.082,
|
| 1128 |
+
"eval_steps_per_second": 2.021,
|
| 1129 |
+
"step": 320
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.13,
|
| 1133 |
+
"learning_rate": 2.6112e-07,
|
| 1134 |
+
"loss": 2.2728,
|
| 1135 |
+
"step": 324
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 0.13,
|
| 1139 |
+
"eval_loss": 2.1374001502990723,
|
| 1140 |
+
"eval_runtime": 0.6321,
|
| 1141 |
+
"eval_samples_per_second": 6.328,
|
| 1142 |
+
"eval_steps_per_second": 1.582,
|
| 1143 |
+
"step": 324
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.13,
|
| 1147 |
+
"learning_rate": 2.6064e-07,
|
| 1148 |
+
"loss": 2.287,
|
| 1149 |
+
"step": 328
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.13,
|
| 1153 |
+
"eval_loss": 2.1333529949188232,
|
| 1154 |
+
"eval_runtime": 0.6547,
|
| 1155 |
+
"eval_samples_per_second": 6.109,
|
| 1156 |
+
"eval_steps_per_second": 1.527,
|
| 1157 |
+
"step": 328
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.13,
|
| 1161 |
+
"learning_rate": 2.6015999999999997e-07,
|
| 1162 |
+
"loss": 2.2474,
|
| 1163 |
+
"step": 332
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 0.13,
|
| 1167 |
+
"eval_loss": 2.1297547817230225,
|
| 1168 |
+
"eval_runtime": 0.7093,
|
| 1169 |
+
"eval_samples_per_second": 5.639,
|
| 1170 |
+
"eval_steps_per_second": 1.41,
|
| 1171 |
+
"step": 332
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.13,
|
| 1175 |
+
"learning_rate": 2.5968e-07,
|
| 1176 |
+
"loss": 2.3214,
|
| 1177 |
+
"step": 336
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.13,
|
| 1181 |
+
"eval_loss": 2.126392364501953,
|
| 1182 |
+
"eval_runtime": 0.6909,
|
| 1183 |
+
"eval_samples_per_second": 5.789,
|
| 1184 |
+
"eval_steps_per_second": 1.447,
|
| 1185 |
+
"step": 336
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.14,
|
| 1189 |
+
"learning_rate": 2.592e-07,
|
| 1190 |
+
"loss": 2.2725,
|
| 1191 |
+
"step": 340
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.14,
|
| 1195 |
+
"eval_loss": 2.122309923171997,
|
| 1196 |
+
"eval_runtime": 0.4823,
|
| 1197 |
+
"eval_samples_per_second": 8.293,
|
| 1198 |
+
"eval_steps_per_second": 2.073,
|
| 1199 |
+
"step": 340
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.14,
|
| 1203 |
+
"learning_rate": 2.5872000000000003e-07,
|
| 1204 |
+
"loss": 2.3114,
|
| 1205 |
+
"step": 344
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.14,
|
| 1209 |
+
"eval_loss": 2.118303060531616,
|
| 1210 |
+
"eval_runtime": 0.4954,
|
| 1211 |
+
"eval_samples_per_second": 8.075,
|
| 1212 |
+
"eval_steps_per_second": 2.019,
|
| 1213 |
+
"step": 344
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.14,
|
| 1217 |
+
"learning_rate": 2.5824e-07,
|
| 1218 |
+
"loss": 2.2333,
|
| 1219 |
+
"step": 348
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 0.14,
|
| 1223 |
+
"eval_loss": 2.114621162414551,
|
| 1224 |
+
"eval_runtime": 0.4856,
|
| 1225 |
+
"eval_samples_per_second": 8.238,
|
| 1226 |
+
"eval_steps_per_second": 2.059,
|
| 1227 |
+
"step": 348
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.14,
|
| 1231 |
+
"learning_rate": 2.5776e-07,
|
| 1232 |
+
"loss": 2.2812,
|
| 1233 |
+
"step": 352
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.14,
|
| 1237 |
+
"eval_loss": 2.11067795753479,
|
| 1238 |
+
"eval_runtime": 0.4778,
|
| 1239 |
+
"eval_samples_per_second": 8.372,
|
| 1240 |
+
"eval_steps_per_second": 2.093,
|
| 1241 |
+
"step": 352
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.14,
|
| 1245 |
+
"learning_rate": 2.5728e-07,
|
| 1246 |
+
"loss": 2.2454,
|
| 1247 |
+
"step": 356
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 0.14,
|
| 1251 |
+
"eval_loss": 2.106940746307373,
|
| 1252 |
+
"eval_runtime": 0.4945,
|
| 1253 |
+
"eval_samples_per_second": 8.089,
|
| 1254 |
+
"eval_steps_per_second": 2.022,
|
| 1255 |
+
"step": 356
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.14,
|
| 1259 |
+
"learning_rate": 2.5679999999999997e-07,
|
| 1260 |
+
"loss": 2.2261,
|
| 1261 |
+
"step": 360
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.14,
|
| 1265 |
+
"eval_loss": 2.1031668186187744,
|
| 1266 |
+
"eval_runtime": 0.6521,
|
| 1267 |
+
"eval_samples_per_second": 6.134,
|
| 1268 |
+
"eval_steps_per_second": 1.533,
|
| 1269 |
+
"step": 360
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.15,
|
| 1273 |
+
"learning_rate": 2.5632e-07,
|
| 1274 |
+
"loss": 2.2841,
|
| 1275 |
+
"step": 364
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.15,
|
| 1279 |
+
"eval_loss": 2.0989203453063965,
|
| 1280 |
+
"eval_runtime": 0.6249,
|
| 1281 |
+
"eval_samples_per_second": 6.401,
|
| 1282 |
+
"eval_steps_per_second": 1.6,
|
| 1283 |
+
"step": 364
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.15,
|
| 1287 |
+
"learning_rate": 2.5584e-07,
|
| 1288 |
+
"loss": 2.2481,
|
| 1289 |
+
"step": 368
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 0.15,
|
| 1293 |
+
"eval_loss": 2.095189332962036,
|
| 1294 |
+
"eval_runtime": 0.6855,
|
| 1295 |
+
"eval_samples_per_second": 5.835,
|
| 1296 |
+
"eval_steps_per_second": 1.459,
|
| 1297 |
+
"step": 368
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.15,
|
| 1301 |
+
"learning_rate": 2.5536e-07,
|
| 1302 |
+
"loss": 2.278,
|
| 1303 |
+
"step": 372
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 0.15,
|
| 1307 |
+
"eval_loss": 2.0912463665008545,
|
| 1308 |
+
"eval_runtime": 0.7393,
|
| 1309 |
+
"eval_samples_per_second": 5.411,
|
| 1310 |
+
"eval_steps_per_second": 1.353,
|
| 1311 |
+
"step": 372
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.15,
|
| 1315 |
+
"learning_rate": 2.5488e-07,
|
| 1316 |
+
"loss": 2.2765,
|
| 1317 |
+
"step": 376
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.15,
|
| 1321 |
+
"eval_loss": 2.087336301803589,
|
| 1322 |
+
"eval_runtime": 0.4793,
|
| 1323 |
+
"eval_samples_per_second": 8.345,
|
| 1324 |
+
"eval_steps_per_second": 2.086,
|
| 1325 |
+
"step": 376
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.15,
|
| 1329 |
+
"learning_rate": 2.544e-07,
|
| 1330 |
+
"loss": 2.2232,
|
| 1331 |
+
"step": 380
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 0.15,
|
| 1335 |
+
"eval_loss": 2.0833120346069336,
|
| 1336 |
+
"eval_runtime": 0.487,
|
| 1337 |
+
"eval_samples_per_second": 8.214,
|
| 1338 |
+
"eval_steps_per_second": 2.053,
|
| 1339 |
+
"step": 380
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.15,
|
| 1343 |
+
"learning_rate": 2.5392e-07,
|
| 1344 |
+
"loss": 2.306,
|
| 1345 |
+
"step": 384
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 0.15,
|
| 1349 |
+
"eval_loss": 2.079479932785034,
|
| 1350 |
+
"eval_runtime": 0.4722,
|
| 1351 |
+
"eval_samples_per_second": 8.471,
|
| 1352 |
+
"eval_steps_per_second": 2.118,
|
| 1353 |
+
"step": 384
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.16,
|
| 1357 |
+
"learning_rate": 2.5343999999999997e-07,
|
| 1358 |
+
"loss": 2.2126,
|
| 1359 |
+
"step": 388
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.16,
|
| 1363 |
+
"eval_loss": 2.0760295391082764,
|
| 1364 |
+
"eval_runtime": 0.4958,
|
| 1365 |
+
"eval_samples_per_second": 8.068,
|
| 1366 |
+
"eval_steps_per_second": 2.017,
|
| 1367 |
+
"step": 388
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.16,
|
| 1371 |
+
"learning_rate": 2.5295999999999996e-07,
|
| 1372 |
+
"loss": 2.2557,
|
| 1373 |
+
"step": 392
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.16,
|
| 1377 |
+
"eval_loss": 2.072136402130127,
|
| 1378 |
+
"eval_runtime": 0.469,
|
| 1379 |
+
"eval_samples_per_second": 8.529,
|
| 1380 |
+
"eval_steps_per_second": 2.132,
|
| 1381 |
+
"step": 392
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.16,
|
| 1385 |
+
"learning_rate": 2.5248e-07,
|
| 1386 |
+
"loss": 2.1988,
|
| 1387 |
+
"step": 396
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.16,
|
| 1391 |
+
"eval_loss": 2.0683670043945312,
|
| 1392 |
+
"eval_runtime": 0.6385,
|
| 1393 |
+
"eval_samples_per_second": 6.264,
|
| 1394 |
+
"eval_steps_per_second": 1.566,
|
| 1395 |
+
"step": 396
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.16,
|
| 1399 |
+
"learning_rate": 2.52e-07,
|
| 1400 |
+
"loss": 2.1917,
|
| 1401 |
+
"step": 400
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.16,
|
| 1405 |
+
"eval_loss": 2.0638906955718994,
|
| 1406 |
+
"eval_runtime": 0.6834,
|
| 1407 |
+
"eval_samples_per_second": 5.853,
|
| 1408 |
+
"eval_steps_per_second": 1.463,
|
| 1409 |
+
"step": 400
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.16,
|
| 1413 |
+
"learning_rate": 2.5152e-07,
|
| 1414 |
+
"loss": 2.2479,
|
| 1415 |
+
"step": 404
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.16,
|
| 1419 |
+
"eval_loss": 2.0599253177642822,
|
| 1420 |
+
"eval_runtime": 0.7261,
|
| 1421 |
+
"eval_samples_per_second": 5.509,
|
| 1422 |
+
"eval_steps_per_second": 1.377,
|
| 1423 |
+
"step": 404
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.16,
|
| 1427 |
+
"learning_rate": 2.5104e-07,
|
| 1428 |
+
"loss": 2.1484,
|
| 1429 |
+
"step": 408
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 0.16,
|
| 1433 |
+
"eval_loss": 2.055751085281372,
|
| 1434 |
+
"eval_runtime": 0.7367,
|
| 1435 |
+
"eval_samples_per_second": 5.429,
|
| 1436 |
+
"eval_steps_per_second": 1.357,
|
| 1437 |
+
"step": 408
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.16,
|
| 1441 |
+
"learning_rate": 2.5056e-07,
|
| 1442 |
+
"loss": 2.1886,
|
| 1443 |
+
"step": 412
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.16,
|
| 1447 |
+
"eval_loss": 2.052119016647339,
|
| 1448 |
+
"eval_runtime": 0.4808,
|
| 1449 |
+
"eval_samples_per_second": 8.319,
|
| 1450 |
+
"eval_steps_per_second": 2.08,
|
| 1451 |
+
"step": 412
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.17,
|
| 1455 |
+
"learning_rate": 2.5007999999999997e-07,
|
| 1456 |
+
"loss": 2.2026,
|
| 1457 |
+
"step": 416
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 0.17,
|
| 1461 |
+
"eval_loss": 2.0482354164123535,
|
| 1462 |
+
"eval_runtime": 0.4856,
|
| 1463 |
+
"eval_samples_per_second": 8.238,
|
| 1464 |
+
"eval_steps_per_second": 2.059,
|
| 1465 |
+
"step": 416
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.17,
|
| 1469 |
+
"learning_rate": 2.4959999999999996e-07,
|
| 1470 |
+
"loss": 2.1572,
|
| 1471 |
+
"step": 420
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.17,
|
| 1475 |
+
"eval_loss": 2.0441887378692627,
|
| 1476 |
+
"eval_runtime": 0.4779,
|
| 1477 |
+
"eval_samples_per_second": 8.37,
|
| 1478 |
+
"eval_steps_per_second": 2.093,
|
| 1479 |
+
"step": 420
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.17,
|
| 1483 |
+
"learning_rate": 2.4912e-07,
|
| 1484 |
+
"loss": 2.1931,
|
| 1485 |
+
"step": 424
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.17,
|
| 1489 |
+
"eval_loss": 2.0399935245513916,
|
| 1490 |
+
"eval_runtime": 0.4803,
|
| 1491 |
+
"eval_samples_per_second": 8.329,
|
| 1492 |
+
"eval_steps_per_second": 2.082,
|
| 1493 |
+
"step": 424
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.17,
|
| 1497 |
+
"learning_rate": 2.4864e-07,
|
| 1498 |
+
"loss": 2.161,
|
| 1499 |
+
"step": 428
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.17,
|
| 1503 |
+
"eval_loss": 2.03645920753479,
|
| 1504 |
+
"eval_runtime": 0.4924,
|
| 1505 |
+
"eval_samples_per_second": 8.123,
|
| 1506 |
+
"eval_steps_per_second": 2.031,
|
| 1507 |
+
"step": 428
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.17,
|
| 1511 |
+
"learning_rate": 2.4816e-07,
|
| 1512 |
+
"loss": 2.1115,
|
| 1513 |
+
"step": 432
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.17,
|
| 1517 |
+
"eval_loss": 2.032196044921875,
|
| 1518 |
+
"eval_runtime": 0.6345,
|
| 1519 |
+
"eval_samples_per_second": 6.304,
|
| 1520 |
+
"eval_steps_per_second": 1.576,
|
| 1521 |
+
"step": 432
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.17,
|
| 1525 |
+
"learning_rate": 2.4768e-07,
|
| 1526 |
+
"loss": 2.173,
|
| 1527 |
+
"step": 436
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.17,
|
| 1531 |
+
"eval_loss": 2.028397560119629,
|
| 1532 |
+
"eval_runtime": 0.6625,
|
| 1533 |
+
"eval_samples_per_second": 6.038,
|
| 1534 |
+
"eval_steps_per_second": 1.509,
|
| 1535 |
+
"step": 436
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.18,
|
| 1539 |
+
"learning_rate": 2.472e-07,
|
| 1540 |
+
"loss": 2.1491,
|
| 1541 |
+
"step": 440
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.18,
|
| 1545 |
+
"eval_loss": 2.0247464179992676,
|
| 1546 |
+
"eval_runtime": 0.6969,
|
| 1547 |
+
"eval_samples_per_second": 5.74,
|
| 1548 |
+
"eval_steps_per_second": 1.435,
|
| 1549 |
+
"step": 440
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.18,
|
| 1553 |
+
"learning_rate": 2.4672e-07,
|
| 1554 |
+
"loss": 2.1716,
|
| 1555 |
+
"step": 444
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.18,
|
| 1559 |
+
"eval_loss": 2.0203933715820312,
|
| 1560 |
+
"eval_runtime": 0.7311,
|
| 1561 |
+
"eval_samples_per_second": 5.471,
|
| 1562 |
+
"eval_steps_per_second": 1.368,
|
| 1563 |
+
"step": 444
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.18,
|
| 1567 |
+
"learning_rate": 2.4623999999999996e-07,
|
| 1568 |
+
"loss": 2.2031,
|
| 1569 |
+
"step": 448
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.18,
|
| 1573 |
+
"eval_loss": 2.016533374786377,
|
| 1574 |
+
"eval_runtime": 0.4875,
|
| 1575 |
+
"eval_samples_per_second": 8.206,
|
| 1576 |
+
"eval_steps_per_second": 2.051,
|
| 1577 |
+
"step": 448
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.18,
|
| 1581 |
+
"learning_rate": 2.4576e-07,
|
| 1582 |
+
"loss": 2.1466,
|
| 1583 |
+
"step": 452
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 0.18,
|
| 1587 |
+
"eval_loss": 2.012568473815918,
|
| 1588 |
+
"eval_runtime": 0.4897,
|
| 1589 |
+
"eval_samples_per_second": 8.168,
|
| 1590 |
+
"eval_steps_per_second": 2.042,
|
| 1591 |
+
"step": 452
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.18,
|
| 1595 |
+
"learning_rate": 2.4528e-07,
|
| 1596 |
+
"loss": 2.1384,
|
| 1597 |
+
"step": 456
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 0.18,
|
| 1601 |
+
"eval_loss": 2.0088417530059814,
|
| 1602 |
+
"eval_runtime": 0.4969,
|
| 1603 |
+
"eval_samples_per_second": 8.05,
|
| 1604 |
+
"eval_steps_per_second": 2.013,
|
| 1605 |
+
"step": 456
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.18,
|
| 1609 |
+
"learning_rate": 2.4479999999999997e-07,
|
| 1610 |
+
"loss": 2.1824,
|
| 1611 |
+
"step": 460
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.18,
|
| 1615 |
+
"eval_loss": 2.0047850608825684,
|
| 1616 |
+
"eval_runtime": 0.4897,
|
| 1617 |
+
"eval_samples_per_second": 8.168,
|
| 1618 |
+
"eval_steps_per_second": 2.042,
|
| 1619 |
+
"step": 460
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.19,
|
| 1623 |
+
"learning_rate": 2.4432e-07,
|
| 1624 |
+
"loss": 2.1401,
|
| 1625 |
+
"step": 464
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 0.19,
|
| 1629 |
+
"eval_loss": 2.0006463527679443,
|
| 1630 |
+
"eval_runtime": 0.4882,
|
| 1631 |
+
"eval_samples_per_second": 8.193,
|
| 1632 |
+
"eval_steps_per_second": 2.048,
|
| 1633 |
+
"step": 464
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.19,
|
| 1637 |
+
"learning_rate": 2.4384e-07,
|
| 1638 |
+
"loss": 2.2086,
|
| 1639 |
+
"step": 468
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.19,
|
| 1643 |
+
"eval_loss": 1.9969314336776733,
|
| 1644 |
+
"eval_runtime": 0.6612,
|
| 1645 |
+
"eval_samples_per_second": 6.049,
|
| 1646 |
+
"eval_steps_per_second": 1.512,
|
| 1647 |
+
"step": 468
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.19,
|
| 1651 |
+
"learning_rate": 2.4336e-07,
|
| 1652 |
+
"loss": 2.1687,
|
| 1653 |
+
"step": 472
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 0.19,
|
| 1657 |
+
"eval_loss": 1.9925954341888428,
|
| 1658 |
+
"eval_runtime": 0.6804,
|
| 1659 |
+
"eval_samples_per_second": 5.879,
|
| 1660 |
+
"eval_steps_per_second": 1.47,
|
| 1661 |
+
"step": 472
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.19,
|
| 1665 |
+
"learning_rate": 2.4287999999999996e-07,
|
| 1666 |
+
"loss": 2.145,
|
| 1667 |
+
"step": 476
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 0.19,
|
| 1671 |
+
"eval_loss": 1.9888066053390503,
|
| 1672 |
+
"eval_runtime": 0.6955,
|
| 1673 |
+
"eval_samples_per_second": 5.752,
|
| 1674 |
+
"eval_steps_per_second": 1.438,
|
| 1675 |
+
"step": 476
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.19,
|
| 1679 |
+
"learning_rate": 2.424e-07,
|
| 1680 |
+
"loss": 2.2007,
|
| 1681 |
+
"step": 480
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.19,
|
| 1685 |
+
"eval_loss": 1.9850127696990967,
|
| 1686 |
+
"eval_runtime": 0.7558,
|
| 1687 |
+
"eval_samples_per_second": 5.292,
|
| 1688 |
+
"eval_steps_per_second": 1.323,
|
| 1689 |
+
"step": 480
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.19,
|
| 1693 |
+
"learning_rate": 2.4192e-07,
|
| 1694 |
+
"loss": 2.1367,
|
| 1695 |
+
"step": 484
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.19,
|
| 1699 |
+
"eval_loss": 1.9808437824249268,
|
| 1700 |
+
"eval_runtime": 0.4706,
|
| 1701 |
+
"eval_samples_per_second": 8.499,
|
| 1702 |
+
"eval_steps_per_second": 2.125,
|
| 1703 |
+
"step": 484
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.2,
|
| 1707 |
+
"learning_rate": 2.4143999999999997e-07,
|
| 1708 |
+
"loss": 2.1291,
|
| 1709 |
+
"step": 488
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 0.2,
|
| 1713 |
+
"eval_loss": 1.9767786264419556,
|
| 1714 |
+
"eval_runtime": 0.4803,
|
| 1715 |
+
"eval_samples_per_second": 8.327,
|
| 1716 |
+
"eval_steps_per_second": 2.082,
|
| 1717 |
+
"step": 488
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.2,
|
| 1721 |
+
"learning_rate": 2.4096e-07,
|
| 1722 |
+
"loss": 2.1124,
|
| 1723 |
+
"step": 492
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 0.2,
|
| 1727 |
+
"eval_loss": 1.9728602170944214,
|
| 1728 |
+
"eval_runtime": 0.4802,
|
| 1729 |
+
"eval_samples_per_second": 8.33,
|
| 1730 |
+
"eval_steps_per_second": 2.082,
|
| 1731 |
+
"step": 492
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.2,
|
| 1735 |
+
"learning_rate": 2.4048e-07,
|
| 1736 |
+
"loss": 2.0738,
|
| 1737 |
+
"step": 496
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.2,
|
| 1741 |
+
"eval_loss": 1.968900203704834,
|
| 1742 |
+
"eval_runtime": 0.4884,
|
| 1743 |
+
"eval_samples_per_second": 8.189,
|
| 1744 |
+
"eval_steps_per_second": 2.047,
|
| 1745 |
+
"step": 496
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.2,
|
| 1749 |
+
"learning_rate": 2.4e-07,
|
| 1750 |
+
"loss": 2.1048,
|
| 1751 |
+
"step": 500
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 0.2,
|
| 1755 |
+
"eval_loss": 1.9646457433700562,
|
| 1756 |
+
"eval_runtime": 0.5026,
|
| 1757 |
+
"eval_samples_per_second": 7.959,
|
| 1758 |
+
"eval_steps_per_second": 1.99,
|
| 1759 |
+
"step": 500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.2,
|
| 1763 |
+
"learning_rate": 2.3951999999999996e-07,
|
| 1764 |
+
"loss": 2.0995,
|
| 1765 |
+
"step": 504
|
| 1766 |
+
},
|
| 1767 |
+
{
|
| 1768 |
+
"epoch": 0.2,
|
| 1769 |
+
"eval_loss": 1.9606600999832153,
|
| 1770 |
+
"eval_runtime": 0.7928,
|
| 1771 |
+
"eval_samples_per_second": 5.045,
|
| 1772 |
+
"eval_steps_per_second": 1.261,
|
| 1773 |
+
"step": 504
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.2,
|
| 1777 |
+
"learning_rate": 2.3903999999999995e-07,
|
| 1778 |
+
"loss": 2.0816,
|
| 1779 |
+
"step": 508
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.2,
|
| 1783 |
+
"eval_loss": 1.956822395324707,
|
| 1784 |
+
"eval_runtime": 0.5321,
|
| 1785 |
+
"eval_samples_per_second": 7.518,
|
| 1786 |
+
"eval_steps_per_second": 1.879,
|
| 1787 |
+
"step": 508
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.2,
|
| 1791 |
+
"learning_rate": 2.3856e-07,
|
| 1792 |
+
"loss": 2.0969,
|
| 1793 |
+
"step": 512
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 0.2,
|
| 1797 |
+
"eval_loss": 1.9526716470718384,
|
| 1798 |
+
"eval_runtime": 0.5174,
|
| 1799 |
+
"eval_samples_per_second": 7.732,
|
| 1800 |
+
"eval_steps_per_second": 1.933,
|
| 1801 |
+
"step": 512
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.21,
|
| 1805 |
+
"learning_rate": 2.3807999999999997e-07,
|
| 1806 |
+
"loss": 2.1034,
|
| 1807 |
+
"step": 516
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.21,
|
| 1811 |
+
"eval_loss": 1.948419451713562,
|
| 1812 |
+
"eval_runtime": 0.5393,
|
| 1813 |
+
"eval_samples_per_second": 7.418,
|
| 1814 |
+
"eval_steps_per_second": 1.854,
|
| 1815 |
+
"step": 516
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.21,
|
| 1819 |
+
"learning_rate": 2.376e-07,
|
| 1820 |
+
"loss": 2.0654,
|
| 1821 |
+
"step": 520
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.21,
|
| 1825 |
+
"eval_loss": 1.9442145824432373,
|
| 1826 |
+
"eval_runtime": 0.5372,
|
| 1827 |
+
"eval_samples_per_second": 7.446,
|
| 1828 |
+
"eval_steps_per_second": 1.861,
|
| 1829 |
+
"step": 520
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.21,
|
| 1833 |
+
"learning_rate": 2.3712e-07,
|
| 1834 |
+
"loss": 2.1175,
|
| 1835 |
+
"step": 524
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 0.21,
|
| 1839 |
+
"eval_loss": 1.9403698444366455,
|
| 1840 |
+
"eval_runtime": 0.5129,
|
| 1841 |
+
"eval_samples_per_second": 7.798,
|
| 1842 |
+
"eval_steps_per_second": 1.95,
|
| 1843 |
+
"step": 524
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.21,
|
| 1847 |
+
"learning_rate": 2.3663999999999998e-07,
|
| 1848 |
+
"loss": 2.0829,
|
| 1849 |
+
"step": 528
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.21,
|
| 1853 |
+
"eval_loss": 1.936263084411621,
|
| 1854 |
+
"eval_runtime": 0.7202,
|
| 1855 |
+
"eval_samples_per_second": 5.554,
|
| 1856 |
+
"eval_steps_per_second": 1.388,
|
| 1857 |
+
"step": 528
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.21,
|
| 1861 |
+
"learning_rate": 2.3616e-07,
|
| 1862 |
+
"loss": 2.0973,
|
| 1863 |
+
"step": 532
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.21,
|
| 1867 |
+
"eval_loss": 1.9322115182876587,
|
| 1868 |
+
"eval_runtime": 0.6884,
|
| 1869 |
+
"eval_samples_per_second": 5.81,
|
| 1870 |
+
"eval_steps_per_second": 1.453,
|
| 1871 |
+
"step": 532
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.21,
|
| 1875 |
+
"learning_rate": 2.3567999999999998e-07,
|
| 1876 |
+
"loss": 2.0439,
|
| 1877 |
+
"step": 536
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 0.21,
|
| 1881 |
+
"eval_loss": 1.927826166152954,
|
| 1882 |
+
"eval_runtime": 0.7779,
|
| 1883 |
+
"eval_samples_per_second": 5.142,
|
| 1884 |
+
"eval_steps_per_second": 1.286,
|
| 1885 |
+
"step": 536
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.22,
|
| 1889 |
+
"learning_rate": 2.352e-07,
|
| 1890 |
+
"loss": 2.0791,
|
| 1891 |
+
"step": 540
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.22,
|
| 1895 |
+
"eval_loss": 1.923945426940918,
|
| 1896 |
+
"eval_runtime": 0.7514,
|
| 1897 |
+
"eval_samples_per_second": 5.323,
|
| 1898 |
+
"eval_steps_per_second": 1.331,
|
| 1899 |
+
"step": 540
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.22,
|
| 1903 |
+
"learning_rate": 2.3471999999999997e-07,
|
| 1904 |
+
"loss": 2.0988,
|
| 1905 |
+
"step": 544
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.22,
|
| 1909 |
+
"eval_loss": 1.9202955961227417,
|
| 1910 |
+
"eval_runtime": 0.5194,
|
| 1911 |
+
"eval_samples_per_second": 7.701,
|
| 1912 |
+
"eval_steps_per_second": 1.925,
|
| 1913 |
+
"step": 544
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.22,
|
| 1917 |
+
"learning_rate": 2.3424e-07,
|
| 1918 |
+
"loss": 2.0179,
|
| 1919 |
+
"step": 548
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.22,
|
| 1923 |
+
"eval_loss": 1.916027307510376,
|
| 1924 |
+
"eval_runtime": 0.5072,
|
| 1925 |
+
"eval_samples_per_second": 7.887,
|
| 1926 |
+
"eval_steps_per_second": 1.972,
|
| 1927 |
+
"step": 548
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.22,
|
| 1931 |
+
"learning_rate": 2.3376e-07,
|
| 1932 |
+
"loss": 2.0452,
|
| 1933 |
+
"step": 552
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.22,
|
| 1937 |
+
"eval_loss": 1.911855697631836,
|
| 1938 |
+
"eval_runtime": 0.5112,
|
| 1939 |
+
"eval_samples_per_second": 7.825,
|
| 1940 |
+
"eval_steps_per_second": 1.956,
|
| 1941 |
+
"step": 552
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.22,
|
| 1945 |
+
"learning_rate": 2.3327999999999998e-07,
|
| 1946 |
+
"loss": 1.9792,
|
| 1947 |
+
"step": 556
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.22,
|
| 1951 |
+
"eval_loss": 1.907868504524231,
|
| 1952 |
+
"eval_runtime": 0.5368,
|
| 1953 |
+
"eval_samples_per_second": 7.452,
|
| 1954 |
+
"eval_steps_per_second": 1.863,
|
| 1955 |
+
"step": 556
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.22,
|
| 1959 |
+
"learning_rate": 2.328e-07,
|
| 1960 |
+
"loss": 1.9862,
|
| 1961 |
+
"step": 560
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.22,
|
| 1965 |
+
"eval_loss": 1.9032366275787354,
|
| 1966 |
+
"eval_runtime": 0.52,
|
| 1967 |
+
"eval_samples_per_second": 7.692,
|
| 1968 |
+
"eval_steps_per_second": 1.923,
|
| 1969 |
+
"step": 560
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.23,
|
| 1973 |
+
"learning_rate": 2.3231999999999998e-07,
|
| 1974 |
+
"loss": 2.0176,
|
| 1975 |
+
"step": 564
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.23,
|
| 1979 |
+
"eval_loss": 1.8994207382202148,
|
| 1980 |
+
"eval_runtime": 0.5141,
|
| 1981 |
+
"eval_samples_per_second": 7.78,
|
| 1982 |
+
"eval_steps_per_second": 1.945,
|
| 1983 |
+
"step": 564
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.23,
|
| 1987 |
+
"learning_rate": 2.3184e-07,
|
| 1988 |
+
"loss": 2.0066,
|
| 1989 |
+
"step": 568
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.23,
|
| 1993 |
+
"eval_loss": 1.8953509330749512,
|
| 1994 |
+
"eval_runtime": 0.7027,
|
| 1995 |
+
"eval_samples_per_second": 5.692,
|
| 1996 |
+
"eval_steps_per_second": 1.423,
|
| 1997 |
+
"step": 568
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.23,
|
| 2001 |
+
"learning_rate": 2.3135999999999998e-07,
|
| 2002 |
+
"loss": 2.0333,
|
| 2003 |
+
"step": 572
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.23,
|
| 2007 |
+
"eval_loss": 1.8914432525634766,
|
| 2008 |
+
"eval_runtime": 0.7279,
|
| 2009 |
+
"eval_samples_per_second": 5.495,
|
| 2010 |
+
"eval_steps_per_second": 1.374,
|
| 2011 |
+
"step": 572
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.23,
|
| 2015 |
+
"learning_rate": 2.3088e-07,
|
| 2016 |
+
"loss": 2.0316,
|
| 2017 |
+
"step": 576
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.23,
|
| 2021 |
+
"eval_loss": 1.8870800733566284,
|
| 2022 |
+
"eval_runtime": 0.7212,
|
| 2023 |
+
"eval_samples_per_second": 5.546,
|
| 2024 |
+
"eval_steps_per_second": 1.386,
|
| 2025 |
+
"step": 576
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.23,
|
| 2029 |
+
"learning_rate": 2.304e-07,
|
| 2030 |
+
"loss": 2.0114,
|
| 2031 |
+
"step": 580
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 0.23,
|
| 2035 |
+
"eval_loss": 1.8827916383743286,
|
| 2036 |
+
"eval_runtime": 0.6774,
|
| 2037 |
+
"eval_samples_per_second": 5.905,
|
| 2038 |
+
"eval_steps_per_second": 1.476,
|
| 2039 |
+
"step": 580
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.23,
|
| 2043 |
+
"learning_rate": 2.2991999999999998e-07,
|
| 2044 |
+
"loss": 2.0093,
|
| 2045 |
+
"step": 584
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 0.23,
|
| 2049 |
+
"eval_loss": 1.8788678646087646,
|
| 2050 |
+
"eval_runtime": 0.5185,
|
| 2051 |
+
"eval_samples_per_second": 7.715,
|
| 2052 |
+
"eval_steps_per_second": 1.929,
|
| 2053 |
+
"step": 584
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.24,
|
| 2057 |
+
"learning_rate": 2.2944e-07,
|
| 2058 |
+
"loss": 1.9829,
|
| 2059 |
+
"step": 588
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 0.24,
|
| 2063 |
+
"eval_loss": 1.8749186992645264,
|
| 2064 |
+
"eval_runtime": 0.5091,
|
| 2065 |
+
"eval_samples_per_second": 7.857,
|
| 2066 |
+
"eval_steps_per_second": 1.964,
|
| 2067 |
+
"step": 588
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.24,
|
| 2071 |
+
"learning_rate": 2.2895999999999998e-07,
|
| 2072 |
+
"loss": 1.971,
|
| 2073 |
+
"step": 592
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.24,
|
| 2077 |
+
"eval_loss": 1.8706499338150024,
|
| 2078 |
+
"eval_runtime": 0.5204,
|
| 2079 |
+
"eval_samples_per_second": 7.687,
|
| 2080 |
+
"eval_steps_per_second": 1.922,
|
| 2081 |
+
"step": 592
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.24,
|
| 2085 |
+
"learning_rate": 2.2848000000000002e-07,
|
| 2086 |
+
"loss": 2.0188,
|
| 2087 |
+
"step": 596
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 0.24,
|
| 2091 |
+
"eval_loss": 1.8667842149734497,
|
| 2092 |
+
"eval_runtime": 0.5224,
|
| 2093 |
+
"eval_samples_per_second": 7.657,
|
| 2094 |
+
"eval_steps_per_second": 1.914,
|
| 2095 |
+
"step": 596
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.24,
|
| 2099 |
+
"learning_rate": 2.28e-07,
|
| 2100 |
+
"loss": 2.0081,
|
| 2101 |
+
"step": 600
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.24,
|
| 2105 |
+
"eval_loss": 1.8627525568008423,
|
| 2106 |
+
"eval_runtime": 0.5196,
|
| 2107 |
+
"eval_samples_per_second": 7.699,
|
| 2108 |
+
"eval_steps_per_second": 1.925,
|
| 2109 |
+
"step": 600
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.24,
|
| 2113 |
+
"learning_rate": 2.2752e-07,
|
| 2114 |
+
"loss": 2.0014,
|
| 2115 |
+
"step": 604
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 0.24,
|
| 2119 |
+
"eval_loss": 1.8587167263031006,
|
| 2120 |
+
"eval_runtime": 0.7373,
|
| 2121 |
+
"eval_samples_per_second": 5.425,
|
| 2122 |
+
"eval_steps_per_second": 1.356,
|
| 2123 |
+
"step": 604
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.24,
|
| 2127 |
+
"learning_rate": 2.2704e-07,
|
| 2128 |
+
"loss": 1.9741,
|
| 2129 |
+
"step": 608
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 0.24,
|
| 2133 |
+
"eval_loss": 1.8543612957000732,
|
| 2134 |
+
"eval_runtime": 0.7492,
|
| 2135 |
+
"eval_samples_per_second": 5.339,
|
| 2136 |
+
"eval_steps_per_second": 1.335,
|
| 2137 |
+
"step": 608
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.24,
|
| 2141 |
+
"learning_rate": 2.2655999999999999e-07,
|
| 2142 |
+
"loss": 1.9828,
|
| 2143 |
+
"step": 612
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 0.24,
|
| 2147 |
+
"eval_loss": 1.8504937887191772,
|
| 2148 |
+
"eval_runtime": 0.7242,
|
| 2149 |
+
"eval_samples_per_second": 5.524,
|
| 2150 |
+
"eval_steps_per_second": 1.381,
|
| 2151 |
+
"step": 612
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.25,
|
| 2155 |
+
"learning_rate": 2.2608e-07,
|
| 2156 |
+
"loss": 1.9481,
|
| 2157 |
+
"step": 616
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 0.25,
|
| 2161 |
+
"eval_loss": 1.8463339805603027,
|
| 2162 |
+
"eval_runtime": 0.6997,
|
| 2163 |
+
"eval_samples_per_second": 5.716,
|
| 2164 |
+
"eval_steps_per_second": 1.429,
|
| 2165 |
+
"step": 616
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.25,
|
| 2169 |
+
"learning_rate": 2.2559999999999998e-07,
|
| 2170 |
+
"loss": 1.9584,
|
| 2171 |
+
"step": 620
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 0.25,
|
| 2175 |
+
"eval_loss": 1.8423882722854614,
|
| 2176 |
+
"eval_runtime": 0.5137,
|
| 2177 |
+
"eval_samples_per_second": 7.787,
|
| 2178 |
+
"eval_steps_per_second": 1.947,
|
| 2179 |
+
"step": 620
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.25,
|
| 2183 |
+
"learning_rate": 2.2511999999999997e-07,
|
| 2184 |
+
"loss": 1.9449,
|
| 2185 |
+
"step": 624
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 0.25,
|
| 2189 |
+
"eval_loss": 1.838066577911377,
|
| 2190 |
+
"eval_runtime": 0.5091,
|
| 2191 |
+
"eval_samples_per_second": 7.857,
|
| 2192 |
+
"eval_steps_per_second": 1.964,
|
| 2193 |
+
"step": 624
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.25,
|
| 2197 |
+
"learning_rate": 2.2464e-07,
|
| 2198 |
+
"loss": 1.9753,
|
| 2199 |
+
"step": 628
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 0.25,
|
| 2203 |
+
"eval_loss": 1.8342829942703247,
|
| 2204 |
+
"eval_runtime": 0.504,
|
| 2205 |
+
"eval_samples_per_second": 7.936,
|
| 2206 |
+
"eval_steps_per_second": 1.984,
|
| 2207 |
+
"step": 628
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.25,
|
| 2211 |
+
"learning_rate": 2.2416e-07,
|
| 2212 |
+
"loss": 2.0055,
|
| 2213 |
+
"step": 632
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 0.25,
|
| 2217 |
+
"eval_loss": 1.8300307989120483,
|
| 2218 |
+
"eval_runtime": 0.5201,
|
| 2219 |
+
"eval_samples_per_second": 7.691,
|
| 2220 |
+
"eval_steps_per_second": 1.923,
|
| 2221 |
+
"step": 632
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.25,
|
| 2225 |
+
"learning_rate": 2.2368e-07,
|
| 2226 |
+
"loss": 1.98,
|
| 2227 |
+
"step": 636
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 0.25,
|
| 2231 |
+
"eval_loss": 1.8260575532913208,
|
| 2232 |
+
"eval_runtime": 0.5267,
|
| 2233 |
+
"eval_samples_per_second": 7.594,
|
| 2234 |
+
"eval_steps_per_second": 1.898,
|
| 2235 |
+
"step": 636
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.26,
|
| 2239 |
+
"learning_rate": 2.232e-07,
|
| 2240 |
+
"loss": 1.9757,
|
| 2241 |
+
"step": 640
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 0.26,
|
| 2245 |
+
"eval_loss": 1.8222540616989136,
|
| 2246 |
+
"eval_runtime": 0.7574,
|
| 2247 |
+
"eval_samples_per_second": 5.281,
|
| 2248 |
+
"eval_steps_per_second": 1.32,
|
| 2249 |
+
"step": 640
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.26,
|
| 2253 |
+
"learning_rate": 2.2271999999999997e-07,
|
| 2254 |
+
"loss": 1.9683,
|
| 2255 |
+
"step": 644
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 0.26,
|
| 2259 |
+
"eval_loss": 1.818216323852539,
|
| 2260 |
+
"eval_runtime": 0.7304,
|
| 2261 |
+
"eval_samples_per_second": 5.476,
|
| 2262 |
+
"eval_steps_per_second": 1.369,
|
| 2263 |
+
"step": 644
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.26,
|
| 2267 |
+
"learning_rate": 2.2223999999999998e-07,
|
| 2268 |
+
"loss": 1.926,
|
| 2269 |
+
"step": 648
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 0.26,
|
| 2273 |
+
"eval_loss": 1.8140522241592407,
|
| 2274 |
+
"eval_runtime": 0.7453,
|
| 2275 |
+
"eval_samples_per_second": 5.367,
|
| 2276 |
+
"eval_steps_per_second": 1.342,
|
| 2277 |
+
"step": 648
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.26,
|
| 2281 |
+
"learning_rate": 2.2175999999999997e-07,
|
| 2282 |
+
"loss": 1.9454,
|
| 2283 |
+
"step": 652
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 0.26,
|
| 2287 |
+
"eval_loss": 1.8100805282592773,
|
| 2288 |
+
"eval_runtime": 0.6536,
|
| 2289 |
+
"eval_samples_per_second": 6.12,
|
| 2290 |
+
"eval_steps_per_second": 1.53,
|
| 2291 |
+
"step": 652
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.26,
|
| 2295 |
+
"learning_rate": 2.2128e-07,
|
| 2296 |
+
"loss": 1.9352,
|
| 2297 |
+
"step": 656
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 0.26,
|
| 2301 |
+
"eval_loss": 1.8059089183807373,
|
| 2302 |
+
"eval_runtime": 0.5193,
|
| 2303 |
+
"eval_samples_per_second": 7.702,
|
| 2304 |
+
"eval_steps_per_second": 1.926,
|
| 2305 |
+
"step": 656
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.26,
|
| 2309 |
+
"learning_rate": 2.208e-07,
|
| 2310 |
+
"loss": 1.8816,
|
| 2311 |
+
"step": 660
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 0.26,
|
| 2315 |
+
"eval_loss": 1.8020563125610352,
|
| 2316 |
+
"eval_runtime": 0.5265,
|
| 2317 |
+
"eval_samples_per_second": 7.597,
|
| 2318 |
+
"eval_steps_per_second": 1.899,
|
| 2319 |
+
"step": 660
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.27,
|
| 2323 |
+
"learning_rate": 2.2032e-07,
|
| 2324 |
+
"loss": 1.9182,
|
| 2325 |
+
"step": 664
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 0.27,
|
| 2329 |
+
"eval_loss": 1.7980492115020752,
|
| 2330 |
+
"eval_runtime": 0.5102,
|
| 2331 |
+
"eval_samples_per_second": 7.84,
|
| 2332 |
+
"eval_steps_per_second": 1.96,
|
| 2333 |
+
"step": 664
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.27,
|
| 2337 |
+
"learning_rate": 2.1984e-07,
|
| 2338 |
+
"loss": 1.9659,
|
| 2339 |
+
"step": 668
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 0.27,
|
| 2343 |
+
"eval_loss": 1.7941217422485352,
|
| 2344 |
+
"eval_runtime": 0.5988,
|
| 2345 |
+
"eval_samples_per_second": 6.681,
|
| 2346 |
+
"eval_steps_per_second": 1.67,
|
| 2347 |
+
"step": 668
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.27,
|
| 2351 |
+
"learning_rate": 2.1935999999999997e-07,
|
| 2352 |
+
"loss": 1.8932,
|
| 2353 |
+
"step": 672
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 0.27,
|
| 2357 |
+
"eval_loss": 1.7901490926742554,
|
| 2358 |
+
"eval_runtime": 0.5339,
|
| 2359 |
+
"eval_samples_per_second": 7.492,
|
| 2360 |
+
"eval_steps_per_second": 1.873,
|
| 2361 |
+
"step": 672
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.27,
|
| 2365 |
+
"learning_rate": 2.1887999999999999e-07,
|
| 2366 |
+
"loss": 1.8608,
|
| 2367 |
+
"step": 676
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 0.27,
|
| 2371 |
+
"eval_loss": 1.786109447479248,
|
| 2372 |
+
"eval_runtime": 0.7219,
|
| 2373 |
+
"eval_samples_per_second": 5.541,
|
| 2374 |
+
"eval_steps_per_second": 1.385,
|
| 2375 |
+
"step": 676
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.27,
|
| 2379 |
+
"learning_rate": 2.184e-07,
|
| 2380 |
+
"loss": 1.941,
|
| 2381 |
+
"step": 680
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 0.27,
|
| 2385 |
+
"eval_loss": 1.7824102640151978,
|
| 2386 |
+
"eval_runtime": 0.7619,
|
| 2387 |
+
"eval_samples_per_second": 5.25,
|
| 2388 |
+
"eval_steps_per_second": 1.313,
|
| 2389 |
+
"step": 680
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.27,
|
| 2393 |
+
"learning_rate": 2.1792e-07,
|
| 2394 |
+
"loss": 1.8854,
|
| 2395 |
+
"step": 684
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 0.27,
|
| 2399 |
+
"eval_loss": 1.77846097946167,
|
| 2400 |
+
"eval_runtime": 0.7601,
|
| 2401 |
+
"eval_samples_per_second": 5.262,
|
| 2402 |
+
"eval_steps_per_second": 1.316,
|
| 2403 |
+
"step": 684
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.28,
|
| 2407 |
+
"learning_rate": 2.1744e-07,
|
| 2408 |
+
"loss": 1.8912,
|
| 2409 |
+
"step": 688
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 0.28,
|
| 2413 |
+
"eval_loss": 1.7742952108383179,
|
| 2414 |
+
"eval_runtime": 0.59,
|
| 2415 |
+
"eval_samples_per_second": 6.78,
|
| 2416 |
+
"eval_steps_per_second": 1.695,
|
| 2417 |
+
"step": 688
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.28,
|
| 2421 |
+
"learning_rate": 2.1695999999999998e-07,
|
| 2422 |
+
"loss": 1.8667,
|
| 2423 |
+
"step": 692
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 0.28,
|
| 2427 |
+
"eval_loss": 1.770714521408081,
|
| 2428 |
+
"eval_runtime": 0.5262,
|
| 2429 |
+
"eval_samples_per_second": 7.601,
|
| 2430 |
+
"eval_steps_per_second": 1.9,
|
| 2431 |
+
"step": 692
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.28,
|
| 2435 |
+
"learning_rate": 2.1648e-07,
|
| 2436 |
+
"loss": 1.912,
|
| 2437 |
+
"step": 696
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 0.28,
|
| 2441 |
+
"eval_loss": 1.7666008472442627,
|
| 2442 |
+
"eval_runtime": 0.5272,
|
| 2443 |
+
"eval_samples_per_second": 7.587,
|
| 2444 |
+
"eval_steps_per_second": 1.897,
|
| 2445 |
+
"step": 696
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.28,
|
| 2449 |
+
"learning_rate": 2.1599999999999998e-07,
|
| 2450 |
+
"loss": 1.9009,
|
| 2451 |
+
"step": 700
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 0.28,
|
| 2455 |
+
"eval_loss": 1.7627824544906616,
|
| 2456 |
+
"eval_runtime": 0.5295,
|
| 2457 |
+
"eval_samples_per_second": 7.555,
|
| 2458 |
+
"eval_steps_per_second": 1.889,
|
| 2459 |
+
"step": 700
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.28,
|
| 2463 |
+
"learning_rate": 2.1552000000000001e-07,
|
| 2464 |
+
"loss": 1.906,
|
| 2465 |
+
"step": 704
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 0.28,
|
| 2469 |
+
"eval_loss": 1.75889253616333,
|
| 2470 |
+
"eval_runtime": 0.5589,
|
| 2471 |
+
"eval_samples_per_second": 7.157,
|
| 2472 |
+
"eval_steps_per_second": 1.789,
|
| 2473 |
+
"step": 704
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.28,
|
| 2477 |
+
"learning_rate": 2.1504e-07,
|
| 2478 |
+
"loss": 1.8671,
|
| 2479 |
+
"step": 708
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 0.28,
|
| 2483 |
+
"eval_loss": 1.7549973726272583,
|
| 2484 |
+
"eval_runtime": 0.687,
|
| 2485 |
+
"eval_samples_per_second": 5.822,
|
| 2486 |
+
"eval_steps_per_second": 1.456,
|
| 2487 |
+
"step": 708
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.28,
|
| 2491 |
+
"learning_rate": 2.1455999999999998e-07,
|
| 2492 |
+
"loss": 1.8609,
|
| 2493 |
+
"step": 712
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 0.28,
|
| 2497 |
+
"eval_loss": 1.7507662773132324,
|
| 2498 |
+
"eval_runtime": 0.7225,
|
| 2499 |
+
"eval_samples_per_second": 5.537,
|
| 2500 |
+
"eval_steps_per_second": 1.384,
|
| 2501 |
+
"step": 712
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.29,
|
| 2505 |
+
"learning_rate": 2.1408e-07,
|
| 2506 |
+
"loss": 1.8485,
|
| 2507 |
+
"step": 716
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 0.29,
|
| 2511 |
+
"eval_loss": 1.746917486190796,
|
| 2512 |
+
"eval_runtime": 0.7954,
|
| 2513 |
+
"eval_samples_per_second": 5.029,
|
| 2514 |
+
"eval_steps_per_second": 1.257,
|
| 2515 |
+
"step": 716
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.29,
|
| 2519 |
+
"learning_rate": 2.1359999999999998e-07,
|
| 2520 |
+
"loss": 1.8334,
|
| 2521 |
+
"step": 720
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 0.29,
|
| 2525 |
+
"eval_loss": 1.7430514097213745,
|
| 2526 |
+
"eval_runtime": 0.7433,
|
| 2527 |
+
"eval_samples_per_second": 5.381,
|
| 2528 |
+
"eval_steps_per_second": 1.345,
|
| 2529 |
+
"step": 720
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.29,
|
| 2533 |
+
"learning_rate": 2.1312e-07,
|
| 2534 |
+
"loss": 1.8763,
|
| 2535 |
+
"step": 724
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 0.29,
|
| 2539 |
+
"eval_loss": 1.7392196655273438,
|
| 2540 |
+
"eval_runtime": 0.5237,
|
| 2541 |
+
"eval_samples_per_second": 7.638,
|
| 2542 |
+
"eval_steps_per_second": 1.91,
|
| 2543 |
+
"step": 724
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.29,
|
| 2547 |
+
"learning_rate": 2.1263999999999998e-07,
|
| 2548 |
+
"loss": 1.9005,
|
| 2549 |
+
"step": 728
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 0.29,
|
| 2553 |
+
"eval_loss": 1.7355214357376099,
|
| 2554 |
+
"eval_runtime": 0.524,
|
| 2555 |
+
"eval_samples_per_second": 7.634,
|
| 2556 |
+
"eval_steps_per_second": 1.908,
|
| 2557 |
+
"step": 728
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.29,
|
| 2561 |
+
"learning_rate": 2.1216000000000002e-07,
|
| 2562 |
+
"loss": 1.8669,
|
| 2563 |
+
"step": 732
|
| 2564 |
+
},
|
| 2565 |
+
{
|
| 2566 |
+
"epoch": 0.29,
|
| 2567 |
+
"eval_loss": 1.731513261795044,
|
| 2568 |
+
"eval_runtime": 0.5593,
|
| 2569 |
+
"eval_samples_per_second": 7.152,
|
| 2570 |
+
"eval_steps_per_second": 1.788,
|
| 2571 |
+
"step": 732
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.29,
|
| 2575 |
+
"learning_rate": 2.1168e-07,
|
| 2576 |
+
"loss": 1.8984,
|
| 2577 |
+
"step": 736
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 0.29,
|
| 2581 |
+
"eval_loss": 1.727636694908142,
|
| 2582 |
+
"eval_runtime": 0.5241,
|
| 2583 |
+
"eval_samples_per_second": 7.632,
|
| 2584 |
+
"eval_steps_per_second": 1.908,
|
| 2585 |
+
"step": 736
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.3,
|
| 2589 |
+
"learning_rate": 2.1119999999999999e-07,
|
| 2590 |
+
"loss": 1.8074,
|
| 2591 |
+
"step": 740
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 0.3,
|
| 2595 |
+
"eval_loss": 1.7240556478500366,
|
| 2596 |
+
"eval_runtime": 0.715,
|
| 2597 |
+
"eval_samples_per_second": 5.594,
|
| 2598 |
+
"eval_steps_per_second": 1.399,
|
| 2599 |
+
"step": 740
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.3,
|
| 2603 |
+
"learning_rate": 2.1072e-07,
|
| 2604 |
+
"loss": 1.8614,
|
| 2605 |
+
"step": 744
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 0.3,
|
| 2609 |
+
"eval_loss": 1.7201639413833618,
|
| 2610 |
+
"eval_runtime": 0.7611,
|
| 2611 |
+
"eval_samples_per_second": 5.256,
|
| 2612 |
+
"eval_steps_per_second": 1.314,
|
| 2613 |
+
"step": 744
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.3,
|
| 2617 |
+
"learning_rate": 2.1023999999999998e-07,
|
| 2618 |
+
"loss": 1.8211,
|
| 2619 |
+
"step": 748
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 0.3,
|
| 2623 |
+
"eval_loss": 1.7165008783340454,
|
| 2624 |
+
"eval_runtime": 0.7193,
|
| 2625 |
+
"eval_samples_per_second": 5.561,
|
| 2626 |
+
"eval_steps_per_second": 1.39,
|
| 2627 |
+
"step": 748
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.3,
|
| 2631 |
+
"learning_rate": 2.0976e-07,
|
| 2632 |
+
"loss": 1.8553,
|
| 2633 |
+
"step": 752
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 0.3,
|
| 2637 |
+
"eval_loss": 1.7123990058898926,
|
| 2638 |
+
"eval_runtime": 0.5463,
|
| 2639 |
+
"eval_samples_per_second": 7.323,
|
| 2640 |
+
"eval_steps_per_second": 1.831,
|
| 2641 |
+
"step": 752
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.3,
|
| 2645 |
+
"learning_rate": 2.0927999999999998e-07,
|
| 2646 |
+
"loss": 1.7978,
|
| 2647 |
+
"step": 756
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 0.3,
|
| 2651 |
+
"eval_loss": 1.7084720134735107,
|
| 2652 |
+
"eval_runtime": 0.574,
|
| 2653 |
+
"eval_samples_per_second": 6.968,
|
| 2654 |
+
"eval_steps_per_second": 1.742,
|
| 2655 |
+
"step": 756
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.3,
|
| 2659 |
+
"learning_rate": 2.0879999999999996e-07,
|
| 2660 |
+
"loss": 1.8203,
|
| 2661 |
+
"step": 760
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 0.3,
|
| 2665 |
+
"eval_loss": 1.7048146724700928,
|
| 2666 |
+
"eval_runtime": 0.5838,
|
| 2667 |
+
"eval_samples_per_second": 6.852,
|
| 2668 |
+
"eval_steps_per_second": 1.713,
|
| 2669 |
+
"step": 760
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.31,
|
| 2673 |
+
"learning_rate": 2.0832e-07,
|
| 2674 |
+
"loss": 1.8192,
|
| 2675 |
+
"step": 764
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 0.31,
|
| 2679 |
+
"eval_loss": 1.7010469436645508,
|
| 2680 |
+
"eval_runtime": 0.5225,
|
| 2681 |
+
"eval_samples_per_second": 7.656,
|
| 2682 |
+
"eval_steps_per_second": 1.914,
|
| 2683 |
+
"step": 764
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.31,
|
| 2687 |
+
"learning_rate": 2.0784e-07,
|
| 2688 |
+
"loss": 1.8532,
|
| 2689 |
+
"step": 768
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 0.31,
|
| 2693 |
+
"eval_loss": 1.6973625421524048,
|
| 2694 |
+
"eval_runtime": 0.525,
|
| 2695 |
+
"eval_samples_per_second": 7.619,
|
| 2696 |
+
"eval_steps_per_second": 1.905,
|
| 2697 |
+
"step": 768
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.31,
|
| 2701 |
+
"learning_rate": 2.0736e-07,
|
| 2702 |
+
"loss": 1.8307,
|
| 2703 |
+
"step": 772
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 0.31,
|
| 2707 |
+
"eval_loss": 1.6935136318206787,
|
| 2708 |
+
"eval_runtime": 0.7235,
|
| 2709 |
+
"eval_samples_per_second": 5.528,
|
| 2710 |
+
"eval_steps_per_second": 1.382,
|
| 2711 |
+
"step": 772
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.31,
|
| 2715 |
+
"learning_rate": 2.0687999999999998e-07,
|
| 2716 |
+
"loss": 1.8207,
|
| 2717 |
+
"step": 776
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 0.31,
|
| 2721 |
+
"eval_loss": 1.6895670890808105,
|
| 2722 |
+
"eval_runtime": 0.8289,
|
| 2723 |
+
"eval_samples_per_second": 4.826,
|
| 2724 |
+
"eval_steps_per_second": 1.206,
|
| 2725 |
+
"step": 776
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.31,
|
| 2729 |
+
"learning_rate": 2.0639999999999997e-07,
|
| 2730 |
+
"loss": 1.7895,
|
| 2731 |
+
"step": 780
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 0.31,
|
| 2735 |
+
"eval_loss": 1.6858075857162476,
|
| 2736 |
+
"eval_runtime": 0.7778,
|
| 2737 |
+
"eval_samples_per_second": 5.143,
|
| 2738 |
+
"eval_steps_per_second": 1.286,
|
| 2739 |
+
"step": 780
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.31,
|
| 2743 |
+
"learning_rate": 2.0592e-07,
|
| 2744 |
+
"loss": 1.7976,
|
| 2745 |
+
"step": 784
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 0.31,
|
| 2749 |
+
"eval_loss": 1.6820955276489258,
|
| 2750 |
+
"eval_runtime": 0.5265,
|
| 2751 |
+
"eval_samples_per_second": 7.597,
|
| 2752 |
+
"eval_steps_per_second": 1.899,
|
| 2753 |
+
"step": 784
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.32,
|
| 2757 |
+
"learning_rate": 2.0544e-07,
|
| 2758 |
+
"loss": 1.814,
|
| 2759 |
+
"step": 788
|
| 2760 |
+
},
|
| 2761 |
+
{
|
| 2762 |
+
"epoch": 0.32,
|
| 2763 |
+
"eval_loss": 1.6785138845443726,
|
| 2764 |
+
"eval_runtime": 0.5179,
|
| 2765 |
+
"eval_samples_per_second": 7.724,
|
| 2766 |
+
"eval_steps_per_second": 1.931,
|
| 2767 |
+
"step": 788
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.32,
|
| 2771 |
+
"learning_rate": 2.0496e-07,
|
| 2772 |
+
"loss": 1.7972,
|
| 2773 |
+
"step": 792
|
| 2774 |
+
},
|
| 2775 |
+
{
|
| 2776 |
+
"epoch": 0.32,
|
| 2777 |
+
"eval_loss": 1.674804449081421,
|
| 2778 |
+
"eval_runtime": 0.5304,
|
| 2779 |
+
"eval_samples_per_second": 7.541,
|
| 2780 |
+
"eval_steps_per_second": 1.885,
|
| 2781 |
+
"step": 792
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.32,
|
| 2785 |
+
"learning_rate": 2.0448e-07,
|
| 2786 |
+
"loss": 1.8258,
|
| 2787 |
+
"step": 796
|
| 2788 |
+
},
|
| 2789 |
+
{
|
| 2790 |
+
"epoch": 0.32,
|
| 2791 |
+
"eval_loss": 1.6713837385177612,
|
| 2792 |
+
"eval_runtime": 0.5336,
|
| 2793 |
+
"eval_samples_per_second": 7.496,
|
| 2794 |
+
"eval_steps_per_second": 1.874,
|
| 2795 |
+
"step": 796
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.32,
|
| 2799 |
+
"learning_rate": 2.04e-07,
|
| 2800 |
+
"loss": 1.79,
|
| 2801 |
+
"step": 800
|
| 2802 |
+
},
|
| 2803 |
+
{
|
| 2804 |
+
"epoch": 0.32,
|
| 2805 |
+
"eval_loss": 1.667376160621643,
|
| 2806 |
+
"eval_runtime": 0.7608,
|
| 2807 |
+
"eval_samples_per_second": 5.258,
|
| 2808 |
+
"eval_steps_per_second": 1.314,
|
| 2809 |
+
"step": 800
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 0.32,
|
| 2813 |
+
"learning_rate": 2.0351999999999999e-07,
|
| 2814 |
+
"loss": 1.802,
|
| 2815 |
+
"step": 804
|
| 2816 |
+
},
|
| 2817 |
+
{
|
| 2818 |
+
"epoch": 0.32,
|
| 2819 |
+
"eval_loss": 1.6640408039093018,
|
| 2820 |
+
"eval_runtime": 0.7498,
|
| 2821 |
+
"eval_samples_per_second": 5.335,
|
| 2822 |
+
"eval_steps_per_second": 1.334,
|
| 2823 |
+
"step": 804
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 0.32,
|
| 2827 |
+
"learning_rate": 2.0303999999999997e-07,
|
| 2828 |
+
"loss": 1.7784,
|
| 2829 |
+
"step": 808
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 0.32,
|
| 2833 |
+
"eval_loss": 1.6603385210037231,
|
| 2834 |
+
"eval_runtime": 0.7501,
|
| 2835 |
+
"eval_samples_per_second": 5.333,
|
| 2836 |
+
"eval_steps_per_second": 1.333,
|
| 2837 |
+
"step": 808
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 0.32,
|
| 2841 |
+
"learning_rate": 2.0256e-07,
|
| 2842 |
+
"loss": 1.7671,
|
| 2843 |
+
"step": 812
|
| 2844 |
+
},
|
| 2845 |
+
{
|
| 2846 |
+
"epoch": 0.32,
|
| 2847 |
+
"eval_loss": 1.6568516492843628,
|
| 2848 |
+
"eval_runtime": 0.5206,
|
| 2849 |
+
"eval_samples_per_second": 7.684,
|
| 2850 |
+
"eval_steps_per_second": 1.921,
|
| 2851 |
+
"step": 812
|
| 2852 |
+
},
|
| 2853 |
+
{
|
| 2854 |
+
"epoch": 0.33,
|
| 2855 |
+
"learning_rate": 2.0208e-07,
|
| 2856 |
+
"loss": 1.7618,
|
| 2857 |
+
"step": 816
|
| 2858 |
+
},
|
| 2859 |
+
{
|
| 2860 |
+
"epoch": 0.33,
|
| 2861 |
+
"eval_loss": 1.653469443321228,
|
| 2862 |
+
"eval_runtime": 0.5354,
|
| 2863 |
+
"eval_samples_per_second": 7.472,
|
| 2864 |
+
"eval_steps_per_second": 1.868,
|
| 2865 |
+
"step": 816
|
| 2866 |
+
},
|
| 2867 |
+
{
|
| 2868 |
+
"epoch": 0.33,
|
| 2869 |
+
"learning_rate": 2.016e-07,
|
| 2870 |
+
"loss": 1.8207,
|
| 2871 |
+
"step": 820
|
| 2872 |
+
},
|
| 2873 |
+
{
|
| 2874 |
+
"epoch": 0.33,
|
| 2875 |
+
"eval_loss": 1.6502578258514404,
|
| 2876 |
+
"eval_runtime": 0.523,
|
| 2877 |
+
"eval_samples_per_second": 7.648,
|
| 2878 |
+
"eval_steps_per_second": 1.912,
|
| 2879 |
+
"step": 820
|
| 2880 |
+
},
|
| 2881 |
+
{
|
| 2882 |
+
"epoch": 0.33,
|
| 2883 |
+
"learning_rate": 2.0112e-07,
|
| 2884 |
+
"loss": 1.7837,
|
| 2885 |
+
"step": 824
|
| 2886 |
+
},
|
| 2887 |
+
{
|
| 2888 |
+
"epoch": 0.33,
|
| 2889 |
+
"eval_loss": 1.6467454433441162,
|
| 2890 |
+
"eval_runtime": 0.5297,
|
| 2891 |
+
"eval_samples_per_second": 7.552,
|
| 2892 |
+
"eval_steps_per_second": 1.888,
|
| 2893 |
+
"step": 824
|
| 2894 |
+
},
|
| 2895 |
+
{
|
| 2896 |
+
"epoch": 0.33,
|
| 2897 |
+
"learning_rate": 2.0063999999999998e-07,
|
| 2898 |
+
"loss": 1.8066,
|
| 2899 |
+
"step": 828
|
| 2900 |
+
},
|
| 2901 |
+
{
|
| 2902 |
+
"epoch": 0.33,
|
| 2903 |
+
"eval_loss": 1.6439214944839478,
|
| 2904 |
+
"eval_runtime": 0.522,
|
| 2905 |
+
"eval_samples_per_second": 7.663,
|
| 2906 |
+
"eval_steps_per_second": 1.916,
|
| 2907 |
+
"step": 828
|
| 2908 |
+
},
|
| 2909 |
+
{
|
| 2910 |
+
"epoch": 0.33,
|
| 2911 |
+
"learning_rate": 2.0016e-07,
|
| 2912 |
+
"loss": 1.7814,
|
| 2913 |
+
"step": 832
|
| 2914 |
+
},
|
| 2915 |
+
{
|
| 2916 |
+
"epoch": 0.33,
|
| 2917 |
+
"eval_loss": 1.6407381296157837,
|
| 2918 |
+
"eval_runtime": 0.5382,
|
| 2919 |
+
"eval_samples_per_second": 7.432,
|
| 2920 |
+
"eval_steps_per_second": 1.858,
|
| 2921 |
+
"step": 832
|
| 2922 |
+
},
|
| 2923 |
+
{
|
| 2924 |
+
"epoch": 0.33,
|
| 2925 |
+
"learning_rate": 1.9967999999999997e-07,
|
| 2926 |
+
"loss": 1.7244,
|
| 2927 |
+
"step": 836
|
| 2928 |
+
},
|
| 2929 |
+
{
|
| 2930 |
+
"epoch": 0.33,
|
| 2931 |
+
"eval_loss": 1.6372514963150024,
|
| 2932 |
+
"eval_runtime": 0.7157,
|
| 2933 |
+
"eval_samples_per_second": 5.589,
|
| 2934 |
+
"eval_steps_per_second": 1.397,
|
| 2935 |
+
"step": 836
|
| 2936 |
+
},
|
| 2937 |
+
{
|
| 2938 |
+
"epoch": 0.34,
|
| 2939 |
+
"learning_rate": 1.992e-07,
|
| 2940 |
+
"loss": 1.7195,
|
| 2941 |
+
"step": 840
|
| 2942 |
+
},
|
| 2943 |
+
{
|
| 2944 |
+
"epoch": 0.34,
|
| 2945 |
+
"eval_loss": 1.634232997894287,
|
| 2946 |
+
"eval_runtime": 0.7254,
|
| 2947 |
+
"eval_samples_per_second": 5.514,
|
| 2948 |
+
"eval_steps_per_second": 1.379,
|
| 2949 |
+
"step": 840
|
| 2950 |
+
},
|
| 2951 |
+
{
|
| 2952 |
+
"epoch": 0.34,
|
| 2953 |
+
"learning_rate": 1.9872e-07,
|
| 2954 |
+
"loss": 1.7524,
|
| 2955 |
+
"step": 844
|
| 2956 |
+
},
|
| 2957 |
+
{
|
| 2958 |
+
"epoch": 0.34,
|
| 2959 |
+
"eval_loss": 1.6310441493988037,
|
| 2960 |
+
"eval_runtime": 0.7839,
|
| 2961 |
+
"eval_samples_per_second": 5.103,
|
| 2962 |
+
"eval_steps_per_second": 1.276,
|
| 2963 |
+
"step": 844
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 0.34,
|
| 2967 |
+
"learning_rate": 1.9824e-07,
|
| 2968 |
+
"loss": 1.7644,
|
| 2969 |
+
"step": 848
|
| 2970 |
+
},
|
| 2971 |
+
{
|
| 2972 |
+
"epoch": 0.34,
|
| 2973 |
+
"eval_loss": 1.6279191970825195,
|
| 2974 |
+
"eval_runtime": 0.5253,
|
| 2975 |
+
"eval_samples_per_second": 7.615,
|
| 2976 |
+
"eval_steps_per_second": 1.904,
|
| 2977 |
+
"step": 848
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 0.34,
|
| 2981 |
+
"learning_rate": 1.9776e-07,
|
| 2982 |
+
"loss": 1.7171,
|
| 2983 |
+
"step": 852
|
| 2984 |
+
},
|
| 2985 |
+
{
|
| 2986 |
+
"epoch": 0.34,
|
| 2987 |
+
"eval_loss": 1.6244579553604126,
|
| 2988 |
+
"eval_runtime": 0.5359,
|
| 2989 |
+
"eval_samples_per_second": 7.464,
|
| 2990 |
+
"eval_steps_per_second": 1.866,
|
| 2991 |
+
"step": 852
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 0.34,
|
| 2995 |
+
"learning_rate": 1.9727999999999998e-07,
|
| 2996 |
+
"loss": 1.7418,
|
| 2997 |
+
"step": 856
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 0.34,
|
| 3001 |
+
"eval_loss": 1.6212078332901,
|
| 3002 |
+
"eval_runtime": 0.5379,
|
| 3003 |
+
"eval_samples_per_second": 7.436,
|
| 3004 |
+
"eval_steps_per_second": 1.859,
|
| 3005 |
+
"step": 856
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 0.34,
|
| 3009 |
+
"learning_rate": 1.968e-07,
|
| 3010 |
+
"loss": 1.7337,
|
| 3011 |
+
"step": 860
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 0.34,
|
| 3015 |
+
"eval_loss": 1.6180227994918823,
|
| 3016 |
+
"eval_runtime": 0.5259,
|
| 3017 |
+
"eval_samples_per_second": 7.606,
|
| 3018 |
+
"eval_steps_per_second": 1.902,
|
| 3019 |
+
"step": 860
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 0.35,
|
| 3023 |
+
"learning_rate": 1.9631999999999997e-07,
|
| 3024 |
+
"loss": 1.7441,
|
| 3025 |
+
"step": 864
|
| 3026 |
+
},
|
| 3027 |
+
{
|
| 3028 |
+
"epoch": 0.35,
|
| 3029 |
+
"eval_loss": 1.61477530002594,
|
| 3030 |
+
"eval_runtime": 0.5216,
|
| 3031 |
+
"eval_samples_per_second": 7.669,
|
| 3032 |
+
"eval_steps_per_second": 1.917,
|
| 3033 |
+
"step": 864
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 0.35,
|
| 3037 |
+
"learning_rate": 1.9584e-07,
|
| 3038 |
+
"loss": 1.694,
|
| 3039 |
+
"step": 868
|
| 3040 |
+
},
|
| 3041 |
+
{
|
| 3042 |
+
"epoch": 0.35,
|
| 3043 |
+
"eval_loss": 1.611538052558899,
|
| 3044 |
+
"eval_runtime": 0.6803,
|
| 3045 |
+
"eval_samples_per_second": 5.88,
|
| 3046 |
+
"eval_steps_per_second": 1.47,
|
| 3047 |
+
"step": 868
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 0.35,
|
| 3051 |
+
"learning_rate": 1.9536e-07,
|
| 3052 |
+
"loss": 1.7601,
|
| 3053 |
+
"step": 872
|
| 3054 |
+
},
|
| 3055 |
+
{
|
| 3056 |
+
"epoch": 0.35,
|
| 3057 |
+
"eval_loss": 1.6083098649978638,
|
| 3058 |
+
"eval_runtime": 0.716,
|
| 3059 |
+
"eval_samples_per_second": 5.586,
|
| 3060 |
+
"eval_steps_per_second": 1.397,
|
| 3061 |
+
"step": 872
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 0.35,
|
| 3065 |
+
"learning_rate": 1.9487999999999998e-07,
|
| 3066 |
+
"loss": 1.7081,
|
| 3067 |
+
"step": 876
|
| 3068 |
+
},
|
| 3069 |
+
{
|
| 3070 |
+
"epoch": 0.35,
|
| 3071 |
+
"eval_loss": 1.6050214767456055,
|
| 3072 |
+
"eval_runtime": 0.7622,
|
| 3073 |
+
"eval_samples_per_second": 5.248,
|
| 3074 |
+
"eval_steps_per_second": 1.312,
|
| 3075 |
+
"step": 876
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 0.35,
|
| 3079 |
+
"learning_rate": 1.944e-07,
|
| 3080 |
+
"loss": 1.7101,
|
| 3081 |
+
"step": 880
|
| 3082 |
+
},
|
| 3083 |
+
{
|
| 3084 |
+
"epoch": 0.35,
|
| 3085 |
+
"eval_loss": 1.6019953489303589,
|
| 3086 |
+
"eval_runtime": 0.7766,
|
| 3087 |
+
"eval_samples_per_second": 5.151,
|
| 3088 |
+
"eval_steps_per_second": 1.288,
|
| 3089 |
+
"step": 880
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 0.35,
|
| 3093 |
+
"learning_rate": 1.9391999999999998e-07,
|
| 3094 |
+
"loss": 1.7271,
|
| 3095 |
+
"step": 884
|
| 3096 |
+
},
|
| 3097 |
+
{
|
| 3098 |
+
"epoch": 0.35,
|
| 3099 |
+
"eval_loss": 1.5990221500396729,
|
| 3100 |
+
"eval_runtime": 0.5153,
|
| 3101 |
+
"eval_samples_per_second": 7.763,
|
| 3102 |
+
"eval_steps_per_second": 1.941,
|
| 3103 |
+
"step": 884
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 0.36,
|
| 3107 |
+
"learning_rate": 1.9344e-07,
|
| 3108 |
+
"loss": 1.7402,
|
| 3109 |
+
"step": 888
|
| 3110 |
+
},
|
| 3111 |
+
{
|
| 3112 |
+
"epoch": 0.36,
|
| 3113 |
+
"eval_loss": 1.5954092741012573,
|
| 3114 |
+
"eval_runtime": 0.5168,
|
| 3115 |
+
"eval_samples_per_second": 7.74,
|
| 3116 |
+
"eval_steps_per_second": 1.935,
|
| 3117 |
+
"step": 888
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 0.36,
|
| 3121 |
+
"learning_rate": 1.9296e-07,
|
| 3122 |
+
"loss": 1.7125,
|
| 3123 |
+
"step": 892
|
| 3124 |
+
},
|
| 3125 |
+
{
|
| 3126 |
+
"epoch": 0.36,
|
| 3127 |
+
"eval_loss": 1.5921534299850464,
|
| 3128 |
+
"eval_runtime": 0.5424,
|
| 3129 |
+
"eval_samples_per_second": 7.375,
|
| 3130 |
+
"eval_steps_per_second": 1.844,
|
| 3131 |
+
"step": 892
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 0.36,
|
| 3135 |
+
"learning_rate": 1.9248e-07,
|
| 3136 |
+
"loss": 1.6949,
|
| 3137 |
+
"step": 896
|
| 3138 |
+
},
|
| 3139 |
+
{
|
| 3140 |
+
"epoch": 0.36,
|
| 3141 |
+
"eval_loss": 1.5888370275497437,
|
| 3142 |
+
"eval_runtime": 0.5307,
|
| 3143 |
+
"eval_samples_per_second": 7.537,
|
| 3144 |
+
"eval_steps_per_second": 1.884,
|
| 3145 |
+
"step": 896
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 0.36,
|
| 3149 |
+
"learning_rate": 1.92e-07,
|
| 3150 |
+
"loss": 1.7145,
|
| 3151 |
+
"step": 900
|
| 3152 |
+
},
|
| 3153 |
+
{
|
| 3154 |
+
"epoch": 0.36,
|
| 3155 |
+
"eval_loss": 1.5858186483383179,
|
| 3156 |
+
"eval_runtime": 0.511,
|
| 3157 |
+
"eval_samples_per_second": 7.828,
|
| 3158 |
+
"eval_steps_per_second": 1.957,
|
| 3159 |
+
"step": 900
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 0.36,
|
| 3163 |
+
"learning_rate": 1.9151999999999998e-07,
|
| 3164 |
+
"loss": 1.6665,
|
| 3165 |
+
"step": 904
|
| 3166 |
+
},
|
| 3167 |
+
{
|
| 3168 |
+
"epoch": 0.36,
|
| 3169 |
+
"eval_loss": 1.5824443101882935,
|
| 3170 |
+
"eval_runtime": 0.6907,
|
| 3171 |
+
"eval_samples_per_second": 5.791,
|
| 3172 |
+
"eval_steps_per_second": 1.448,
|
| 3173 |
+
"step": 904
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 0.36,
|
| 3177 |
+
"learning_rate": 1.9104e-07,
|
| 3178 |
+
"loss": 1.6929,
|
| 3179 |
+
"step": 908
|
| 3180 |
+
},
|
| 3181 |
+
{
|
| 3182 |
+
"epoch": 0.36,
|
| 3183 |
+
"eval_loss": 1.5796196460723877,
|
| 3184 |
+
"eval_runtime": 0.7487,
|
| 3185 |
+
"eval_samples_per_second": 5.342,
|
| 3186 |
+
"eval_steps_per_second": 1.336,
|
| 3187 |
+
"step": 908
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 0.36,
|
| 3191 |
+
"learning_rate": 1.9055999999999998e-07,
|
| 3192 |
+
"loss": 1.7068,
|
| 3193 |
+
"step": 912
|
| 3194 |
+
},
|
| 3195 |
+
{
|
| 3196 |
+
"epoch": 0.36,
|
| 3197 |
+
"eval_loss": 1.5765777826309204,
|
| 3198 |
+
"eval_runtime": 0.7477,
|
| 3199 |
+
"eval_samples_per_second": 5.35,
|
| 3200 |
+
"eval_steps_per_second": 1.337,
|
| 3201 |
+
"step": 912
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 0.37,
|
| 3205 |
+
"learning_rate": 1.9008000000000002e-07,
|
| 3206 |
+
"loss": 1.6877,
|
| 3207 |
+
"step": 916
|
| 3208 |
+
},
|
| 3209 |
+
{
|
| 3210 |
+
"epoch": 0.37,
|
| 3211 |
+
"eval_loss": 1.57340669631958,
|
| 3212 |
+
"eval_runtime": 0.753,
|
| 3213 |
+
"eval_samples_per_second": 5.312,
|
| 3214 |
+
"eval_steps_per_second": 1.328,
|
| 3215 |
+
"step": 916
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 0.37,
|
| 3219 |
+
"learning_rate": 1.896e-07,
|
| 3220 |
+
"loss": 1.6718,
|
| 3221 |
+
"step": 920
|
| 3222 |
+
},
|
| 3223 |
+
{
|
| 3224 |
+
"epoch": 0.37,
|
| 3225 |
+
"eval_loss": 1.5706267356872559,
|
| 3226 |
+
"eval_runtime": 0.514,
|
| 3227 |
+
"eval_samples_per_second": 7.782,
|
| 3228 |
+
"eval_steps_per_second": 1.945,
|
| 3229 |
+
"step": 920
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.37,
|
| 3233 |
+
"learning_rate": 1.8912e-07,
|
| 3234 |
+
"loss": 1.6886,
|
| 3235 |
+
"step": 924
|
| 3236 |
+
},
|
| 3237 |
+
{
|
| 3238 |
+
"epoch": 0.37,
|
| 3239 |
+
"eval_loss": 1.5676339864730835,
|
| 3240 |
+
"eval_runtime": 0.5222,
|
| 3241 |
+
"eval_samples_per_second": 7.66,
|
| 3242 |
+
"eval_steps_per_second": 1.915,
|
| 3243 |
+
"step": 924
|
| 3244 |
+
},
|
| 3245 |
+
{
|
| 3246 |
+
"epoch": 0.37,
|
| 3247 |
+
"learning_rate": 1.8864e-07,
|
| 3248 |
+
"loss": 1.7459,
|
| 3249 |
+
"step": 928
|
| 3250 |
+
},
|
| 3251 |
+
{
|
| 3252 |
+
"epoch": 0.37,
|
| 3253 |
+
"eval_loss": 1.5645827054977417,
|
| 3254 |
+
"eval_runtime": 0.5299,
|
| 3255 |
+
"eval_samples_per_second": 7.548,
|
| 3256 |
+
"eval_steps_per_second": 1.887,
|
| 3257 |
+
"step": 928
|
| 3258 |
+
},
|
| 3259 |
+
{
|
| 3260 |
+
"epoch": 0.37,
|
| 3261 |
+
"learning_rate": 1.8815999999999999e-07,
|
| 3262 |
+
"loss": 1.6596,
|
| 3263 |
+
"step": 932
|
| 3264 |
+
},
|
| 3265 |
+
{
|
| 3266 |
+
"epoch": 0.37,
|
| 3267 |
+
"eval_loss": 1.5616861581802368,
|
| 3268 |
+
"eval_runtime": 0.5303,
|
| 3269 |
+
"eval_samples_per_second": 7.543,
|
| 3270 |
+
"eval_steps_per_second": 1.886,
|
| 3271 |
+
"step": 932
|
| 3272 |
+
},
|
| 3273 |
+
{
|
| 3274 |
+
"epoch": 0.37,
|
| 3275 |
+
"learning_rate": 1.8768e-07,
|
| 3276 |
+
"loss": 1.6689,
|
| 3277 |
+
"step": 936
|
| 3278 |
+
},
|
| 3279 |
+
{
|
| 3280 |
+
"epoch": 0.37,
|
| 3281 |
+
"eval_loss": 1.5588451623916626,
|
| 3282 |
+
"eval_runtime": 0.5236,
|
| 3283 |
+
"eval_samples_per_second": 7.639,
|
| 3284 |
+
"eval_steps_per_second": 1.91,
|
| 3285 |
+
"step": 936
|
| 3286 |
+
},
|
| 3287 |
+
{
|
| 3288 |
+
"epoch": 0.38,
|
| 3289 |
+
"learning_rate": 1.8719999999999998e-07,
|
| 3290 |
+
"loss": 1.6744,
|
| 3291 |
+
"step": 940
|
| 3292 |
+
},
|
| 3293 |
+
{
|
| 3294 |
+
"epoch": 0.38,
|
| 3295 |
+
"eval_loss": 1.5560673475265503,
|
| 3296 |
+
"eval_runtime": 0.7233,
|
| 3297 |
+
"eval_samples_per_second": 5.53,
|
| 3298 |
+
"eval_steps_per_second": 1.383,
|
| 3299 |
+
"step": 940
|
| 3300 |
+
},
|
| 3301 |
+
{
|
| 3302 |
+
"epoch": 0.38,
|
| 3303 |
+
"learning_rate": 1.8671999999999997e-07,
|
| 3304 |
+
"loss": 1.7009,
|
| 3305 |
+
"step": 944
|
| 3306 |
+
},
|
| 3307 |
+
{
|
| 3308 |
+
"epoch": 0.38,
|
| 3309 |
+
"eval_loss": 1.5533243417739868,
|
| 3310 |
+
"eval_runtime": 0.6983,
|
| 3311 |
+
"eval_samples_per_second": 5.728,
|
| 3312 |
+
"eval_steps_per_second": 1.432,
|
| 3313 |
+
"step": 944
|
| 3314 |
+
},
|
| 3315 |
+
{
|
| 3316 |
+
"epoch": 0.38,
|
| 3317 |
+
"learning_rate": 1.8624e-07,
|
| 3318 |
+
"loss": 1.6651,
|
| 3319 |
+
"step": 948
|
| 3320 |
+
},
|
| 3321 |
+
{
|
| 3322 |
+
"epoch": 0.38,
|
| 3323 |
+
"eval_loss": 1.55048668384552,
|
| 3324 |
+
"eval_runtime": 0.7511,
|
| 3325 |
+
"eval_samples_per_second": 5.325,
|
| 3326 |
+
"eval_steps_per_second": 1.331,
|
| 3327 |
+
"step": 948
|
| 3328 |
+
},
|
| 3329 |
+
{
|
| 3330 |
+
"epoch": 0.38,
|
| 3331 |
+
"learning_rate": 1.8576e-07,
|
| 3332 |
+
"loss": 1.6821,
|
| 3333 |
+
"step": 952
|
| 3334 |
+
},
|
| 3335 |
+
{
|
| 3336 |
+
"epoch": 0.38,
|
| 3337 |
+
"eval_loss": 1.547943353652954,
|
| 3338 |
+
"eval_runtime": 0.532,
|
| 3339 |
+
"eval_samples_per_second": 7.519,
|
| 3340 |
+
"eval_steps_per_second": 1.88,
|
| 3341 |
+
"step": 952
|
| 3342 |
+
},
|
| 3343 |
+
{
|
| 3344 |
+
"epoch": 0.38,
|
| 3345 |
+
"learning_rate": 1.8528e-07,
|
| 3346 |
+
"loss": 1.6453,
|
| 3347 |
+
"step": 956
|
| 3348 |
+
},
|
| 3349 |
+
{
|
| 3350 |
+
"epoch": 0.38,
|
| 3351 |
+
"eval_loss": 1.5453405380249023,
|
| 3352 |
+
"eval_runtime": 0.5463,
|
| 3353 |
+
"eval_samples_per_second": 7.322,
|
| 3354 |
+
"eval_steps_per_second": 1.831,
|
| 3355 |
+
"step": 956
|
| 3356 |
+
},
|
| 3357 |
+
{
|
| 3358 |
+
"epoch": 0.38,
|
| 3359 |
+
"learning_rate": 1.848e-07,
|
| 3360 |
+
"loss": 1.6624,
|
| 3361 |
+
"step": 960
|
| 3362 |
+
},
|
| 3363 |
+
{
|
| 3364 |
+
"epoch": 0.38,
|
| 3365 |
+
"eval_loss": 1.542648196220398,
|
| 3366 |
+
"eval_runtime": 0.5288,
|
| 3367 |
+
"eval_samples_per_second": 7.564,
|
| 3368 |
+
"eval_steps_per_second": 1.891,
|
| 3369 |
+
"step": 960
|
| 3370 |
+
},
|
| 3371 |
+
{
|
| 3372 |
+
"epoch": 0.39,
|
| 3373 |
+
"learning_rate": 1.8431999999999997e-07,
|
| 3374 |
+
"loss": 1.6453,
|
| 3375 |
+
"step": 964
|
| 3376 |
+
},
|
| 3377 |
+
{
|
| 3378 |
+
"epoch": 0.39,
|
| 3379 |
+
"eval_loss": 1.5402462482452393,
|
| 3380 |
+
"eval_runtime": 0.5242,
|
| 3381 |
+
"eval_samples_per_second": 7.63,
|
| 3382 |
+
"eval_steps_per_second": 1.908,
|
| 3383 |
+
"step": 964
|
| 3384 |
+
},
|
| 3385 |
+
{
|
| 3386 |
+
"epoch": 0.39,
|
| 3387 |
+
"learning_rate": 1.8383999999999998e-07,
|
| 3388 |
+
"loss": 1.6451,
|
| 3389 |
+
"step": 968
|
| 3390 |
+
},
|
| 3391 |
+
{
|
| 3392 |
+
"epoch": 0.39,
|
| 3393 |
+
"eval_loss": 1.5377165079116821,
|
| 3394 |
+
"eval_runtime": 0.5169,
|
| 3395 |
+
"eval_samples_per_second": 7.738,
|
| 3396 |
+
"eval_steps_per_second": 1.935,
|
| 3397 |
+
"step": 968
|
| 3398 |
+
},
|
| 3399 |
+
{
|
| 3400 |
+
"epoch": 0.39,
|
| 3401 |
+
"learning_rate": 1.8335999999999997e-07,
|
| 3402 |
+
"loss": 1.6627,
|
| 3403 |
+
"step": 972
|
| 3404 |
+
},
|
| 3405 |
+
{
|
| 3406 |
+
"epoch": 0.39,
|
| 3407 |
+
"eval_loss": 1.5353412628173828,
|
| 3408 |
+
"eval_runtime": 0.6797,
|
| 3409 |
+
"eval_samples_per_second": 5.885,
|
| 3410 |
+
"eval_steps_per_second": 1.471,
|
| 3411 |
+
"step": 972
|
| 3412 |
+
},
|
| 3413 |
+
{
|
| 3414 |
+
"epoch": 0.39,
|
| 3415 |
+
"learning_rate": 1.8288e-07,
|
| 3416 |
+
"loss": 1.6423,
|
| 3417 |
+
"step": 976
|
| 3418 |
+
},
|
| 3419 |
+
{
|
| 3420 |
+
"epoch": 0.39,
|
| 3421 |
+
"eval_loss": 1.5325669050216675,
|
| 3422 |
+
"eval_runtime": 0.7175,
|
| 3423 |
+
"eval_samples_per_second": 5.575,
|
| 3424 |
+
"eval_steps_per_second": 1.394,
|
| 3425 |
+
"step": 976
|
| 3426 |
+
},
|
| 3427 |
+
{
|
| 3428 |
+
"epoch": 0.39,
|
| 3429 |
+
"learning_rate": 1.824e-07,
|
| 3430 |
+
"loss": 1.652,
|
| 3431 |
+
"step": 980
|
| 3432 |
+
},
|
| 3433 |
+
{
|
| 3434 |
+
"epoch": 0.39,
|
| 3435 |
+
"eval_loss": 1.530207872390747,
|
| 3436 |
+
"eval_runtime": 0.8099,
|
| 3437 |
+
"eval_samples_per_second": 4.939,
|
| 3438 |
+
"eval_steps_per_second": 1.235,
|
| 3439 |
+
"step": 980
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 0.39,
|
| 3443 |
+
"learning_rate": 1.8192e-07,
|
| 3444 |
+
"loss": 1.6414,
|
| 3445 |
+
"step": 984
|
| 3446 |
+
},
|
| 3447 |
+
{
|
| 3448 |
+
"epoch": 0.39,
|
| 3449 |
+
"eval_loss": 1.5278236865997314,
|
| 3450 |
+
"eval_runtime": 0.7814,
|
| 3451 |
+
"eval_samples_per_second": 5.119,
|
| 3452 |
+
"eval_steps_per_second": 1.28,
|
| 3453 |
+
"step": 984
|
| 3454 |
+
},
|
| 3455 |
+
{
|
| 3456 |
+
"epoch": 0.4,
|
| 3457 |
+
"learning_rate": 1.8144e-07,
|
| 3458 |
+
"loss": 1.6107,
|
| 3459 |
+
"step": 988
|
| 3460 |
+
},
|
| 3461 |
+
{
|
| 3462 |
+
"epoch": 0.4,
|
| 3463 |
+
"eval_loss": 1.5253430604934692,
|
| 3464 |
+
"eval_runtime": 0.5386,
|
| 3465 |
+
"eval_samples_per_second": 7.427,
|
| 3466 |
+
"eval_steps_per_second": 1.857,
|
| 3467 |
+
"step": 988
|
| 3468 |
+
},
|
| 3469 |
+
{
|
| 3470 |
+
"epoch": 0.4,
|
| 3471 |
+
"learning_rate": 1.8095999999999997e-07,
|
| 3472 |
+
"loss": 1.6599,
|
| 3473 |
+
"step": 992
|
| 3474 |
+
},
|
| 3475 |
+
{
|
| 3476 |
+
"epoch": 0.4,
|
| 3477 |
+
"eval_loss": 1.5225120782852173,
|
| 3478 |
+
"eval_runtime": 0.5302,
|
| 3479 |
+
"eval_samples_per_second": 7.544,
|
| 3480 |
+
"eval_steps_per_second": 1.886,
|
| 3481 |
+
"step": 992
|
| 3482 |
+
},
|
| 3483 |
+
{
|
| 3484 |
+
"epoch": 0.4,
|
| 3485 |
+
"learning_rate": 1.8048e-07,
|
| 3486 |
+
"loss": 1.6326,
|
| 3487 |
+
"step": 996
|
| 3488 |
+
},
|
| 3489 |
+
{
|
| 3490 |
+
"epoch": 0.4,
|
| 3491 |
+
"eval_loss": 1.5201939344406128,
|
| 3492 |
+
"eval_runtime": 0.533,
|
| 3493 |
+
"eval_samples_per_second": 7.505,
|
| 3494 |
+
"eval_steps_per_second": 1.876,
|
| 3495 |
+
"step": 996
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 0.4,
|
| 3499 |
+
"learning_rate": 1.8e-07,
|
| 3500 |
+
"loss": 1.6324,
|
| 3501 |
+
"step": 1000
|
| 3502 |
+
},
|
| 3503 |
+
{
|
| 3504 |
+
"epoch": 0.4,
|
| 3505 |
+
"eval_loss": 1.5175316333770752,
|
| 3506 |
+
"eval_runtime": 0.5316,
|
| 3507 |
+
"eval_samples_per_second": 7.525,
|
| 3508 |
+
"eval_steps_per_second": 1.881,
|
| 3509 |
+
"step": 1000
|
| 3510 |
+
}
|
| 3511 |
+
],
|
| 3512 |
+
"logging_steps": 4,
|
| 3513 |
+
"max_steps": 2500,
|
| 3514 |
+
"num_input_tokens_seen": 0,
|
| 3515 |
+
"num_train_epochs": 1,
|
| 3516 |
+
"save_steps": 500,
|
| 3517 |
+
"total_flos": 1.2712088174592e+17,
|
| 3518 |
+
"trial_name": null,
|
| 3519 |
+
"trial_params": null
|
| 3520 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8372290711385a4b881e6c95b154723c812dc21e47ba06376b2d40c72d854043
|
| 3 |
+
size 4600
|
checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "jeff31415/TinyLlama-1.1B-1T-OpenOrca",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 22,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float16",
|
| 25 |
+
"transformers_version": "4.36.0.dev0",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32000
|
| 28 |
+
}
|
checkpoint-1500/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.36.0.dev0"
|
| 7 |
+
}
|
checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:525edbb8253d9e8751dfb98b40d5c1322d80e6053135712ccb5d607a42173c09
|
| 3 |
+
size 2200119664
|
checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c01eabe688c4a4f846ec278e5becd199119686c5b53bd85246907a43788d32f8
|
| 3 |
+
size 2205161786
|
checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86a1bb254b26437c4e13841cb41e250752fc24fe9a2a691897aa76d9627be2a4
|
| 3 |
+
size 14244
|
checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39c9fde66434d6439df51d17de18b3427bf234718a67bcfa43aa9f08271727c1
|
| 3 |
+
size 1064
|
checkpoint-1500/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8372290711385a4b881e6c95b154723c812dc21e47ba06376b2d40c72d854043
|
| 3 |
+
size 4600
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "jeff31415/TinyLlama-1.1B-1T-OpenOrca",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 22,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float16",
|
| 25 |
+
"transformers_version": "4.36.0.dev0",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32000
|
| 28 |
+
}
|
checkpoint-2000/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.36.0.dev0"
|
| 7 |
+
}
|
checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c85bc3b1c807a46bf9fb357ee2581690f90862d3fabee7f79f55d4db0448d82f
|
| 3 |
+
size 2200119664
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9341b02c731e4b58ae1f0df6d333910fc1ac52e2cc801a1e486dd7b5a6188267
|
| 3 |
+
size 2205161786
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f2bfad145875466ac9154ad5b958d1d8736701a98c59c3c7e51562746e63b61
|
| 3 |
+
size 14244
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebe11db143b8cd8a681054d7aeeea2c6b1bc55604d67a16288e39ae1ae3a229d
|
| 3 |
+
size 1064
|
checkpoint-2000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8372290711385a4b881e6c95b154723c812dc21e47ba06376b2d40c72d854043
|
| 3 |
+
size 4600
|
checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "jeff31415/TinyLlama-1.1B-1T-OpenOrca",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 22,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float16",
|
| 25 |
+
"transformers_version": "4.36.0.dev0",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32000
|
| 28 |
+
}
|
checkpoint-2500/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.36.0.dev0"
|
| 7 |
+
}
|
checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7b11a03b8f4bf479692be16f7c59df2b15196416c136498f07860d7a5ae1b27
|
| 3 |
+
size 2200119664
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:307863e6a7fd926c3dbc24b6529e1b1645d1d140a81a5bc15317d2f1d7a1ce4b
|
| 3 |
+
size 2205161786
|
checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7f4b456ed398bdbb5b35cde838e2c4bfedb459f6bc60d190d3a7cb9ce65dc4d
|
| 3 |
+
size 14244
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52edd5aadc973460ef7cecd871f970665a1bfa199d887a28fb329fe3c33d211d
|
| 3 |
+
size 1064
|
checkpoint-2500/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8372290711385a4b881e6c95b154723c812dc21e47ba06376b2d40c72d854043
|
| 3 |
+
size 4600
|
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "jeff31415/TinyLlama-1.1B-1T-OpenOrca",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 22,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float16",
|
| 25 |
+
"transformers_version": "4.36.0.dev0",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32000
|
| 28 |
+
}
|
checkpoint-500/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.36.0.dev0"
|
| 7 |
+
}
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94f823528ac3dcb786f82f9321d0ce743f58597cc968f70240b18820aad26da7
|
| 3 |
+
size 2200119664
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e86b3b0776af39f9191bfd06ede55fa7de86ed005a5b234270c2cd3976e771b
|
| 3 |
+
size 2205161786
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10b0069dee0e4ffb5199dba1cec39acc974730f7326c3b8eb8211cf1a9be16fc
|
| 3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4291caba66a1e6402b8dcd8538ab0a7895ca8ae239f011133b5ba449a8f05296
|
| 3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,1770 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.9646457433700562,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-500",
|
| 4 |
+
"epoch": 0.2,
|
| 5 |
+
"eval_steps": 4,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 2.9951999999999997e-07,
|
| 14 |
+
"loss": 2.6285,
|
| 15 |
+
"step": 4
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"eval_loss": 2.4697508811950684,
|
| 20 |
+
"eval_runtime": 0.485,
|
| 21 |
+
"eval_samples_per_second": 8.248,
|
| 22 |
+
"eval_steps_per_second": 2.062,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.0,
|
| 27 |
+
"learning_rate": 2.9904e-07,
|
| 28 |
+
"loss": 2.6222,
|
| 29 |
+
"step": 8
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.0,
|
| 33 |
+
"eval_loss": 2.465975284576416,
|
| 34 |
+
"eval_runtime": 0.6323,
|
| 35 |
+
"eval_samples_per_second": 6.326,
|
| 36 |
+
"eval_steps_per_second": 1.582,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0,
|
| 41 |
+
"learning_rate": 2.9856e-07,
|
| 42 |
+
"loss": 2.6536,
|
| 43 |
+
"step": 12
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.0,
|
| 47 |
+
"eval_loss": 2.460374116897583,
|
| 48 |
+
"eval_runtime": 0.6478,
|
| 49 |
+
"eval_samples_per_second": 6.175,
|
| 50 |
+
"eval_steps_per_second": 1.544,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"learning_rate": 2.9808e-07,
|
| 56 |
+
"loss": 2.6785,
|
| 57 |
+
"step": 16
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.01,
|
| 61 |
+
"eval_loss": 2.4556970596313477,
|
| 62 |
+
"eval_runtime": 0.6653,
|
| 63 |
+
"eval_samples_per_second": 6.012,
|
| 64 |
+
"eval_steps_per_second": 1.503,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.01,
|
| 69 |
+
"learning_rate": 2.9759999999999996e-07,
|
| 70 |
+
"loss": 2.6085,
|
| 71 |
+
"step": 20
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.01,
|
| 75 |
+
"eval_loss": 2.4514715671539307,
|
| 76 |
+
"eval_runtime": 0.5241,
|
| 77 |
+
"eval_samples_per_second": 7.632,
|
| 78 |
+
"eval_steps_per_second": 1.908,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.01,
|
| 83 |
+
"learning_rate": 2.9711999999999995e-07,
|
| 84 |
+
"loss": 2.5907,
|
| 85 |
+
"step": 24
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.01,
|
| 89 |
+
"eval_loss": 2.4462974071502686,
|
| 90 |
+
"eval_runtime": 0.4689,
|
| 91 |
+
"eval_samples_per_second": 8.53,
|
| 92 |
+
"eval_steps_per_second": 2.133,
|
| 93 |
+
"step": 24
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.01,
|
| 97 |
+
"learning_rate": 2.9664e-07,
|
| 98 |
+
"loss": 2.5942,
|
| 99 |
+
"step": 28
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.01,
|
| 103 |
+
"eval_loss": 2.4415194988250732,
|
| 104 |
+
"eval_runtime": 0.4829,
|
| 105 |
+
"eval_samples_per_second": 8.284,
|
| 106 |
+
"eval_steps_per_second": 2.071,
|
| 107 |
+
"step": 28
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.01,
|
| 111 |
+
"learning_rate": 2.9615999999999997e-07,
|
| 112 |
+
"loss": 2.6101,
|
| 113 |
+
"step": 32
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.01,
|
| 117 |
+
"eval_loss": 2.437161922454834,
|
| 118 |
+
"eval_runtime": 0.4715,
|
| 119 |
+
"eval_samples_per_second": 8.483,
|
| 120 |
+
"eval_steps_per_second": 2.121,
|
| 121 |
+
"step": 32
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.01,
|
| 125 |
+
"learning_rate": 2.9568e-07,
|
| 126 |
+
"loss": 2.5827,
|
| 127 |
+
"step": 36
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.01,
|
| 131 |
+
"eval_loss": 2.432689666748047,
|
| 132 |
+
"eval_runtime": 0.4938,
|
| 133 |
+
"eval_samples_per_second": 8.1,
|
| 134 |
+
"eval_steps_per_second": 2.025,
|
| 135 |
+
"step": 36
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.02,
|
| 139 |
+
"learning_rate": 2.952e-07,
|
| 140 |
+
"loss": 2.5729,
|
| 141 |
+
"step": 40
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.02,
|
| 145 |
+
"eval_loss": 2.4281153678894043,
|
| 146 |
+
"eval_runtime": 0.5021,
|
| 147 |
+
"eval_samples_per_second": 7.966,
|
| 148 |
+
"eval_steps_per_second": 1.991,
|
| 149 |
+
"step": 40
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.02,
|
| 153 |
+
"learning_rate": 2.9472e-07,
|
| 154 |
+
"loss": 2.5856,
|
| 155 |
+
"step": 44
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.02,
|
| 159 |
+
"eval_loss": 2.423053741455078,
|
| 160 |
+
"eval_runtime": 0.593,
|
| 161 |
+
"eval_samples_per_second": 6.746,
|
| 162 |
+
"eval_steps_per_second": 1.686,
|
| 163 |
+
"step": 44
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.02,
|
| 167 |
+
"learning_rate": 2.9423999999999997e-07,
|
| 168 |
+
"loss": 2.589,
|
| 169 |
+
"step": 48
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.02,
|
| 173 |
+
"eval_loss": 2.418571949005127,
|
| 174 |
+
"eval_runtime": 0.6933,
|
| 175 |
+
"eval_samples_per_second": 5.77,
|
| 176 |
+
"eval_steps_per_second": 1.442,
|
| 177 |
+
"step": 48
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.02,
|
| 181 |
+
"learning_rate": 2.9375999999999995e-07,
|
| 182 |
+
"loss": 2.6483,
|
| 183 |
+
"step": 52
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.02,
|
| 187 |
+
"eval_loss": 2.414531946182251,
|
| 188 |
+
"eval_runtime": 0.7167,
|
| 189 |
+
"eval_samples_per_second": 5.581,
|
| 190 |
+
"eval_steps_per_second": 1.395,
|
| 191 |
+
"step": 52
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.02,
|
| 195 |
+
"learning_rate": 2.9328e-07,
|
| 196 |
+
"loss": 2.517,
|
| 197 |
+
"step": 56
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.02,
|
| 201 |
+
"eval_loss": 2.409538745880127,
|
| 202 |
+
"eval_runtime": 0.4826,
|
| 203 |
+
"eval_samples_per_second": 8.289,
|
| 204 |
+
"eval_steps_per_second": 2.072,
|
| 205 |
+
"step": 56
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.02,
|
| 209 |
+
"learning_rate": 2.928e-07,
|
| 210 |
+
"loss": 2.5987,
|
| 211 |
+
"step": 60
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.02,
|
| 215 |
+
"eval_loss": 2.4050426483154297,
|
| 216 |
+
"eval_runtime": 0.4757,
|
| 217 |
+
"eval_samples_per_second": 8.409,
|
| 218 |
+
"eval_steps_per_second": 2.102,
|
| 219 |
+
"step": 60
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.03,
|
| 223 |
+
"learning_rate": 2.9232e-07,
|
| 224 |
+
"loss": 2.5489,
|
| 225 |
+
"step": 64
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.03,
|
| 229 |
+
"eval_loss": 2.400360107421875,
|
| 230 |
+
"eval_runtime": 0.4945,
|
| 231 |
+
"eval_samples_per_second": 8.089,
|
| 232 |
+
"eval_steps_per_second": 2.022,
|
| 233 |
+
"step": 64
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.03,
|
| 237 |
+
"learning_rate": 2.9184e-07,
|
| 238 |
+
"loss": 2.5063,
|
| 239 |
+
"step": 68
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.03,
|
| 243 |
+
"eval_loss": 2.396500587463379,
|
| 244 |
+
"eval_runtime": 0.5,
|
| 245 |
+
"eval_samples_per_second": 8.001,
|
| 246 |
+
"eval_steps_per_second": 2.0,
|
| 247 |
+
"step": 68
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.03,
|
| 251 |
+
"learning_rate": 2.9136e-07,
|
| 252 |
+
"loss": 2.5867,
|
| 253 |
+
"step": 72
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.03,
|
| 257 |
+
"eval_loss": 2.3916146755218506,
|
| 258 |
+
"eval_runtime": 0.4602,
|
| 259 |
+
"eval_samples_per_second": 8.693,
|
| 260 |
+
"eval_steps_per_second": 2.173,
|
| 261 |
+
"step": 72
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.03,
|
| 265 |
+
"learning_rate": 2.9087999999999997e-07,
|
| 266 |
+
"loss": 2.544,
|
| 267 |
+
"step": 76
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.03,
|
| 271 |
+
"eval_loss": 2.3873047828674316,
|
| 272 |
+
"eval_runtime": 0.4731,
|
| 273 |
+
"eval_samples_per_second": 8.456,
|
| 274 |
+
"eval_steps_per_second": 2.114,
|
| 275 |
+
"step": 76
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.03,
|
| 279 |
+
"learning_rate": 2.9039999999999995e-07,
|
| 280 |
+
"loss": 2.5596,
|
| 281 |
+
"step": 80
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.03,
|
| 285 |
+
"eval_loss": 2.382803440093994,
|
| 286 |
+
"eval_runtime": 0.6092,
|
| 287 |
+
"eval_samples_per_second": 6.566,
|
| 288 |
+
"eval_steps_per_second": 1.642,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.03,
|
| 293 |
+
"learning_rate": 2.8992e-07,
|
| 294 |
+
"loss": 2.5744,
|
| 295 |
+
"step": 84
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.03,
|
| 299 |
+
"eval_loss": 2.3786380290985107,
|
| 300 |
+
"eval_runtime": 0.7212,
|
| 301 |
+
"eval_samples_per_second": 5.546,
|
| 302 |
+
"eval_steps_per_second": 1.387,
|
| 303 |
+
"step": 84
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.04,
|
| 307 |
+
"learning_rate": 2.8944e-07,
|
| 308 |
+
"loss": 2.5588,
|
| 309 |
+
"step": 88
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.04,
|
| 313 |
+
"eval_loss": 2.374176502227783,
|
| 314 |
+
"eval_runtime": 0.6826,
|
| 315 |
+
"eval_samples_per_second": 5.86,
|
| 316 |
+
"eval_steps_per_second": 1.465,
|
| 317 |
+
"step": 88
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.04,
|
| 321 |
+
"learning_rate": 2.8895999999999996e-07,
|
| 322 |
+
"loss": 2.5579,
|
| 323 |
+
"step": 92
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.04,
|
| 327 |
+
"eval_loss": 2.3702104091644287,
|
| 328 |
+
"eval_runtime": 0.4896,
|
| 329 |
+
"eval_samples_per_second": 8.169,
|
| 330 |
+
"eval_steps_per_second": 2.042,
|
| 331 |
+
"step": 92
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.04,
|
| 335 |
+
"learning_rate": 2.8848e-07,
|
| 336 |
+
"loss": 2.5245,
|
| 337 |
+
"step": 96
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.04,
|
| 341 |
+
"eval_loss": 2.3660218715667725,
|
| 342 |
+
"eval_runtime": 0.4764,
|
| 343 |
+
"eval_samples_per_second": 8.397,
|
| 344 |
+
"eval_steps_per_second": 2.099,
|
| 345 |
+
"step": 96
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.04,
|
| 349 |
+
"learning_rate": 2.88e-07,
|
| 350 |
+
"loss": 2.5132,
|
| 351 |
+
"step": 100
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.04,
|
| 355 |
+
"eval_loss": 2.36110520362854,
|
| 356 |
+
"eval_runtime": 0.4799,
|
| 357 |
+
"eval_samples_per_second": 8.335,
|
| 358 |
+
"eval_steps_per_second": 2.084,
|
| 359 |
+
"step": 100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.04,
|
| 363 |
+
"learning_rate": 2.8751999999999997e-07,
|
| 364 |
+
"loss": 2.5037,
|
| 365 |
+
"step": 104
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.04,
|
| 369 |
+
"eval_loss": 2.3570125102996826,
|
| 370 |
+
"eval_runtime": 0.4722,
|
| 371 |
+
"eval_samples_per_second": 8.47,
|
| 372 |
+
"eval_steps_per_second": 2.118,
|
| 373 |
+
"step": 104
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.04,
|
| 377 |
+
"learning_rate": 2.8704e-07,
|
| 378 |
+
"loss": 2.4727,
|
| 379 |
+
"step": 108
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.04,
|
| 383 |
+
"eval_loss": 2.3530666828155518,
|
| 384 |
+
"eval_runtime": 0.467,
|
| 385 |
+
"eval_samples_per_second": 8.565,
|
| 386 |
+
"eval_steps_per_second": 2.141,
|
| 387 |
+
"step": 108
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.04,
|
| 391 |
+
"learning_rate": 2.8656e-07,
|
| 392 |
+
"loss": 2.4709,
|
| 393 |
+
"step": 112
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.04,
|
| 397 |
+
"eval_loss": 2.348759412765503,
|
| 398 |
+
"eval_runtime": 0.501,
|
| 399 |
+
"eval_samples_per_second": 7.984,
|
| 400 |
+
"eval_steps_per_second": 1.996,
|
| 401 |
+
"step": 112
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.05,
|
| 405 |
+
"learning_rate": 2.8608e-07,
|
| 406 |
+
"loss": 2.4711,
|
| 407 |
+
"step": 116
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.05,
|
| 411 |
+
"eval_loss": 2.344454050064087,
|
| 412 |
+
"eval_runtime": 0.6607,
|
| 413 |
+
"eval_samples_per_second": 6.054,
|
| 414 |
+
"eval_steps_per_second": 1.513,
|
| 415 |
+
"step": 116
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.05,
|
| 419 |
+
"learning_rate": 2.8559999999999996e-07,
|
| 420 |
+
"loss": 2.5445,
|
| 421 |
+
"step": 120
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 0.05,
|
| 425 |
+
"eval_loss": 2.3402156829833984,
|
| 426 |
+
"eval_runtime": 0.704,
|
| 427 |
+
"eval_samples_per_second": 5.682,
|
| 428 |
+
"eval_steps_per_second": 1.42,
|
| 429 |
+
"step": 120
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.05,
|
| 433 |
+
"learning_rate": 2.8512e-07,
|
| 434 |
+
"loss": 2.4994,
|
| 435 |
+
"step": 124
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.05,
|
| 439 |
+
"eval_loss": 2.3362019062042236,
|
| 440 |
+
"eval_runtime": 0.6849,
|
| 441 |
+
"eval_samples_per_second": 5.84,
|
| 442 |
+
"eval_steps_per_second": 1.46,
|
| 443 |
+
"step": 124
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.05,
|
| 447 |
+
"learning_rate": 2.8464e-07,
|
| 448 |
+
"loss": 2.5036,
|
| 449 |
+
"step": 128
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.05,
|
| 453 |
+
"eval_loss": 2.3319339752197266,
|
| 454 |
+
"eval_runtime": 0.4864,
|
| 455 |
+
"eval_samples_per_second": 8.223,
|
| 456 |
+
"eval_steps_per_second": 2.056,
|
| 457 |
+
"step": 128
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.05,
|
| 461 |
+
"learning_rate": 2.8416e-07,
|
| 462 |
+
"loss": 2.5525,
|
| 463 |
+
"step": 132
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.05,
|
| 467 |
+
"eval_loss": 2.3276522159576416,
|
| 468 |
+
"eval_runtime": 0.4783,
|
| 469 |
+
"eval_samples_per_second": 8.364,
|
| 470 |
+
"eval_steps_per_second": 2.091,
|
| 471 |
+
"step": 132
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.05,
|
| 475 |
+
"learning_rate": 2.8368e-07,
|
| 476 |
+
"loss": 2.5245,
|
| 477 |
+
"step": 136
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.05,
|
| 481 |
+
"eval_loss": 2.3241090774536133,
|
| 482 |
+
"eval_runtime": 0.4805,
|
| 483 |
+
"eval_samples_per_second": 8.324,
|
| 484 |
+
"eval_steps_per_second": 2.081,
|
| 485 |
+
"step": 136
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.06,
|
| 489 |
+
"learning_rate": 2.832e-07,
|
| 490 |
+
"loss": 2.4946,
|
| 491 |
+
"step": 140
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.06,
|
| 495 |
+
"eval_loss": 2.3198165893554688,
|
| 496 |
+
"eval_runtime": 0.473,
|
| 497 |
+
"eval_samples_per_second": 8.457,
|
| 498 |
+
"eval_steps_per_second": 2.114,
|
| 499 |
+
"step": 140
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.06,
|
| 503 |
+
"learning_rate": 2.8272e-07,
|
| 504 |
+
"loss": 2.5142,
|
| 505 |
+
"step": 144
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 0.06,
|
| 509 |
+
"eval_loss": 2.3152613639831543,
|
| 510 |
+
"eval_runtime": 0.4858,
|
| 511 |
+
"eval_samples_per_second": 8.234,
|
| 512 |
+
"eval_steps_per_second": 2.058,
|
| 513 |
+
"step": 144
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.06,
|
| 517 |
+
"learning_rate": 2.8223999999999997e-07,
|
| 518 |
+
"loss": 2.4639,
|
| 519 |
+
"step": 148
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.06,
|
| 523 |
+
"eval_loss": 2.3112645149230957,
|
| 524 |
+
"eval_runtime": 0.488,
|
| 525 |
+
"eval_samples_per_second": 8.196,
|
| 526 |
+
"eval_steps_per_second": 2.049,
|
| 527 |
+
"step": 148
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.06,
|
| 531 |
+
"learning_rate": 2.8176e-07,
|
| 532 |
+
"loss": 2.4796,
|
| 533 |
+
"step": 152
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.06,
|
| 537 |
+
"eval_loss": 2.307020902633667,
|
| 538 |
+
"eval_runtime": 0.6163,
|
| 539 |
+
"eval_samples_per_second": 6.49,
|
| 540 |
+
"eval_steps_per_second": 1.623,
|
| 541 |
+
"step": 152
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.06,
|
| 545 |
+
"learning_rate": 2.8128e-07,
|
| 546 |
+
"loss": 2.4529,
|
| 547 |
+
"step": 156
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 0.06,
|
| 551 |
+
"eval_loss": 2.303062915802002,
|
| 552 |
+
"eval_runtime": 0.6764,
|
| 553 |
+
"eval_samples_per_second": 5.913,
|
| 554 |
+
"eval_steps_per_second": 1.478,
|
| 555 |
+
"step": 156
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.06,
|
| 559 |
+
"learning_rate": 2.808e-07,
|
| 560 |
+
"loss": 2.4823,
|
| 561 |
+
"step": 160
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.06,
|
| 565 |
+
"eval_loss": 2.2993311882019043,
|
| 566 |
+
"eval_runtime": 0.6854,
|
| 567 |
+
"eval_samples_per_second": 5.836,
|
| 568 |
+
"eval_steps_per_second": 1.459,
|
| 569 |
+
"step": 160
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.07,
|
| 573 |
+
"learning_rate": 2.8032e-07,
|
| 574 |
+
"loss": 2.4439,
|
| 575 |
+
"step": 164
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.07,
|
| 579 |
+
"eval_loss": 2.2947850227355957,
|
| 580 |
+
"eval_runtime": 0.4745,
|
| 581 |
+
"eval_samples_per_second": 8.429,
|
| 582 |
+
"eval_steps_per_second": 2.107,
|
| 583 |
+
"step": 164
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.07,
|
| 587 |
+
"learning_rate": 2.7984e-07,
|
| 588 |
+
"loss": 2.4652,
|
| 589 |
+
"step": 168
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.07,
|
| 593 |
+
"eval_loss": 2.2908992767333984,
|
| 594 |
+
"eval_runtime": 0.4759,
|
| 595 |
+
"eval_samples_per_second": 8.406,
|
| 596 |
+
"eval_steps_per_second": 2.101,
|
| 597 |
+
"step": 168
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.07,
|
| 601 |
+
"learning_rate": 2.7936e-07,
|
| 602 |
+
"loss": 2.4574,
|
| 603 |
+
"step": 172
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.07,
|
| 607 |
+
"eval_loss": 2.2867026329040527,
|
| 608 |
+
"eval_runtime": 0.4973,
|
| 609 |
+
"eval_samples_per_second": 8.043,
|
| 610 |
+
"eval_steps_per_second": 2.011,
|
| 611 |
+
"step": 172
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.07,
|
| 615 |
+
"learning_rate": 2.7887999999999997e-07,
|
| 616 |
+
"loss": 2.4557,
|
| 617 |
+
"step": 176
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.07,
|
| 621 |
+
"eval_loss": 2.283027172088623,
|
| 622 |
+
"eval_runtime": 0.4719,
|
| 623 |
+
"eval_samples_per_second": 8.477,
|
| 624 |
+
"eval_steps_per_second": 2.119,
|
| 625 |
+
"step": 176
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.07,
|
| 629 |
+
"learning_rate": 2.784e-07,
|
| 630 |
+
"loss": 2.4462,
|
| 631 |
+
"step": 180
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 0.07,
|
| 635 |
+
"eval_loss": 2.2787420749664307,
|
| 636 |
+
"eval_runtime": 0.472,
|
| 637 |
+
"eval_samples_per_second": 8.474,
|
| 638 |
+
"eval_steps_per_second": 2.119,
|
| 639 |
+
"step": 180
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.07,
|
| 643 |
+
"learning_rate": 2.7792e-07,
|
| 644 |
+
"loss": 2.3962,
|
| 645 |
+
"step": 184
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.07,
|
| 649 |
+
"eval_loss": 2.2745461463928223,
|
| 650 |
+
"eval_runtime": 0.6328,
|
| 651 |
+
"eval_samples_per_second": 6.322,
|
| 652 |
+
"eval_steps_per_second": 1.58,
|
| 653 |
+
"step": 184
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.08,
|
| 657 |
+
"learning_rate": 2.7744e-07,
|
| 658 |
+
"loss": 2.3666,
|
| 659 |
+
"step": 188
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.08,
|
| 663 |
+
"eval_loss": 2.2705912590026855,
|
| 664 |
+
"eval_runtime": 0.6375,
|
| 665 |
+
"eval_samples_per_second": 6.274,
|
| 666 |
+
"eval_steps_per_second": 1.569,
|
| 667 |
+
"step": 188
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.08,
|
| 671 |
+
"learning_rate": 2.7696e-07,
|
| 672 |
+
"loss": 2.5024,
|
| 673 |
+
"step": 192
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 0.08,
|
| 677 |
+
"eval_loss": 2.266995906829834,
|
| 678 |
+
"eval_runtime": 0.6984,
|
| 679 |
+
"eval_samples_per_second": 5.727,
|
| 680 |
+
"eval_steps_per_second": 1.432,
|
| 681 |
+
"step": 192
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.08,
|
| 685 |
+
"learning_rate": 2.7648e-07,
|
| 686 |
+
"loss": 2.4419,
|
| 687 |
+
"step": 196
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.08,
|
| 691 |
+
"eval_loss": 2.2626519203186035,
|
| 692 |
+
"eval_runtime": 0.7334,
|
| 693 |
+
"eval_samples_per_second": 5.454,
|
| 694 |
+
"eval_steps_per_second": 1.363,
|
| 695 |
+
"step": 196
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.08,
|
| 699 |
+
"learning_rate": 2.76e-07,
|
| 700 |
+
"loss": 2.4246,
|
| 701 |
+
"step": 200
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.08,
|
| 705 |
+
"eval_loss": 2.2583603858947754,
|
| 706 |
+
"eval_runtime": 0.48,
|
| 707 |
+
"eval_samples_per_second": 8.333,
|
| 708 |
+
"eval_steps_per_second": 2.083,
|
| 709 |
+
"step": 200
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.08,
|
| 713 |
+
"learning_rate": 2.7551999999999997e-07,
|
| 714 |
+
"loss": 2.3853,
|
| 715 |
+
"step": 204
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 0.08,
|
| 719 |
+
"eval_loss": 2.2551512718200684,
|
| 720 |
+
"eval_runtime": 0.4939,
|
| 721 |
+
"eval_samples_per_second": 8.098,
|
| 722 |
+
"eval_steps_per_second": 2.025,
|
| 723 |
+
"step": 204
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.08,
|
| 727 |
+
"learning_rate": 2.7503999999999995e-07,
|
| 728 |
+
"loss": 2.4032,
|
| 729 |
+
"step": 208
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.08,
|
| 733 |
+
"eval_loss": 2.251105785369873,
|
| 734 |
+
"eval_runtime": 0.46,
|
| 735 |
+
"eval_samples_per_second": 8.695,
|
| 736 |
+
"eval_steps_per_second": 2.174,
|
| 737 |
+
"step": 208
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.08,
|
| 741 |
+
"learning_rate": 2.7456e-07,
|
| 742 |
+
"loss": 2.4444,
|
| 743 |
+
"step": 212
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.08,
|
| 747 |
+
"eval_loss": 2.247025489807129,
|
| 748 |
+
"eval_runtime": 0.4948,
|
| 749 |
+
"eval_samples_per_second": 8.084,
|
| 750 |
+
"eval_steps_per_second": 2.021,
|
| 751 |
+
"step": 212
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.09,
|
| 755 |
+
"learning_rate": 2.7408e-07,
|
| 756 |
+
"loss": 2.2932,
|
| 757 |
+
"step": 216
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 0.09,
|
| 761 |
+
"eval_loss": 2.242764472961426,
|
| 762 |
+
"eval_runtime": 0.4897,
|
| 763 |
+
"eval_samples_per_second": 8.168,
|
| 764 |
+
"eval_steps_per_second": 2.042,
|
| 765 |
+
"step": 216
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.09,
|
| 769 |
+
"learning_rate": 2.736e-07,
|
| 770 |
+
"loss": 2.3929,
|
| 771 |
+
"step": 220
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.09,
|
| 775 |
+
"eval_loss": 2.2391483783721924,
|
| 776 |
+
"eval_runtime": 0.6128,
|
| 777 |
+
"eval_samples_per_second": 6.528,
|
| 778 |
+
"eval_steps_per_second": 1.632,
|
| 779 |
+
"step": 220
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.09,
|
| 783 |
+
"learning_rate": 2.7312e-07,
|
| 784 |
+
"loss": 2.4112,
|
| 785 |
+
"step": 224
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.09,
|
| 789 |
+
"eval_loss": 2.234977960586548,
|
| 790 |
+
"eval_runtime": 0.648,
|
| 791 |
+
"eval_samples_per_second": 6.172,
|
| 792 |
+
"eval_steps_per_second": 1.543,
|
| 793 |
+
"step": 224
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.09,
|
| 797 |
+
"learning_rate": 2.7264e-07,
|
| 798 |
+
"loss": 2.4191,
|
| 799 |
+
"step": 228
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 0.09,
|
| 803 |
+
"eval_loss": 2.231099843978882,
|
| 804 |
+
"eval_runtime": 0.6862,
|
| 805 |
+
"eval_samples_per_second": 5.829,
|
| 806 |
+
"eval_steps_per_second": 1.457,
|
| 807 |
+
"step": 228
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.09,
|
| 811 |
+
"learning_rate": 2.7215999999999997e-07,
|
| 812 |
+
"loss": 2.4408,
|
| 813 |
+
"step": 232
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.09,
|
| 817 |
+
"eval_loss": 2.2272462844848633,
|
| 818 |
+
"eval_runtime": 0.7076,
|
| 819 |
+
"eval_samples_per_second": 5.653,
|
| 820 |
+
"eval_steps_per_second": 1.413,
|
| 821 |
+
"step": 232
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.09,
|
| 825 |
+
"learning_rate": 2.7167999999999996e-07,
|
| 826 |
+
"loss": 2.3884,
|
| 827 |
+
"step": 236
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 0.09,
|
| 831 |
+
"eval_loss": 2.223376750946045,
|
| 832 |
+
"eval_runtime": 0.5169,
|
| 833 |
+
"eval_samples_per_second": 7.738,
|
| 834 |
+
"eval_steps_per_second": 1.935,
|
| 835 |
+
"step": 236
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.1,
|
| 839 |
+
"learning_rate": 2.712e-07,
|
| 840 |
+
"loss": 2.3689,
|
| 841 |
+
"step": 240
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 0.1,
|
| 845 |
+
"eval_loss": 2.2195653915405273,
|
| 846 |
+
"eval_runtime": 0.4793,
|
| 847 |
+
"eval_samples_per_second": 8.346,
|
| 848 |
+
"eval_steps_per_second": 2.086,
|
| 849 |
+
"step": 240
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.1,
|
| 853 |
+
"learning_rate": 2.7072e-07,
|
| 854 |
+
"loss": 2.3689,
|
| 855 |
+
"step": 244
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.1,
|
| 859 |
+
"eval_loss": 2.2153775691986084,
|
| 860 |
+
"eval_runtime": 0.4771,
|
| 861 |
+
"eval_samples_per_second": 8.384,
|
| 862 |
+
"eval_steps_per_second": 2.096,
|
| 863 |
+
"step": 244
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.1,
|
| 867 |
+
"learning_rate": 2.7024e-07,
|
| 868 |
+
"loss": 2.3249,
|
| 869 |
+
"step": 248
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.1,
|
| 873 |
+
"eval_loss": 2.211355209350586,
|
| 874 |
+
"eval_runtime": 0.4778,
|
| 875 |
+
"eval_samples_per_second": 8.372,
|
| 876 |
+
"eval_steps_per_second": 2.093,
|
| 877 |
+
"step": 248
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.1,
|
| 881 |
+
"learning_rate": 2.6976e-07,
|
| 882 |
+
"loss": 2.4286,
|
| 883 |
+
"step": 252
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.1,
|
| 887 |
+
"eval_loss": 2.207773208618164,
|
| 888 |
+
"eval_runtime": 0.4873,
|
| 889 |
+
"eval_samples_per_second": 8.209,
|
| 890 |
+
"eval_steps_per_second": 2.052,
|
| 891 |
+
"step": 252
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.1,
|
| 895 |
+
"learning_rate": 2.6928e-07,
|
| 896 |
+
"loss": 2.3497,
|
| 897 |
+
"step": 256
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.1,
|
| 901 |
+
"eval_loss": 2.203867197036743,
|
| 902 |
+
"eval_runtime": 0.6281,
|
| 903 |
+
"eval_samples_per_second": 6.368,
|
| 904 |
+
"eval_steps_per_second": 1.592,
|
| 905 |
+
"step": 256
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.1,
|
| 909 |
+
"learning_rate": 2.6879999999999997e-07,
|
| 910 |
+
"loss": 2.284,
|
| 911 |
+
"step": 260
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.1,
|
| 915 |
+
"eval_loss": 2.199937582015991,
|
| 916 |
+
"eval_runtime": 0.6885,
|
| 917 |
+
"eval_samples_per_second": 5.81,
|
| 918 |
+
"eval_steps_per_second": 1.452,
|
| 919 |
+
"step": 260
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.11,
|
| 923 |
+
"learning_rate": 2.6831999999999996e-07,
|
| 924 |
+
"loss": 2.3333,
|
| 925 |
+
"step": 264
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 0.11,
|
| 929 |
+
"eval_loss": 2.1958465576171875,
|
| 930 |
+
"eval_runtime": 0.6799,
|
| 931 |
+
"eval_samples_per_second": 5.883,
|
| 932 |
+
"eval_steps_per_second": 1.471,
|
| 933 |
+
"step": 264
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.11,
|
| 937 |
+
"learning_rate": 2.6784e-07,
|
| 938 |
+
"loss": 2.3305,
|
| 939 |
+
"step": 268
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.11,
|
| 943 |
+
"eval_loss": 2.192072868347168,
|
| 944 |
+
"eval_runtime": 0.7165,
|
| 945 |
+
"eval_samples_per_second": 5.583,
|
| 946 |
+
"eval_steps_per_second": 1.396,
|
| 947 |
+
"step": 268
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.11,
|
| 951 |
+
"learning_rate": 2.6736e-07,
|
| 952 |
+
"loss": 2.3465,
|
| 953 |
+
"step": 272
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.11,
|
| 957 |
+
"eval_loss": 2.1882476806640625,
|
| 958 |
+
"eval_runtime": 0.485,
|
| 959 |
+
"eval_samples_per_second": 8.247,
|
| 960 |
+
"eval_steps_per_second": 2.062,
|
| 961 |
+
"step": 272
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.11,
|
| 965 |
+
"learning_rate": 2.6687999999999997e-07,
|
| 966 |
+
"loss": 2.3274,
|
| 967 |
+
"step": 276
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.11,
|
| 971 |
+
"eval_loss": 2.1841320991516113,
|
| 972 |
+
"eval_runtime": 0.4767,
|
| 973 |
+
"eval_samples_per_second": 8.391,
|
| 974 |
+
"eval_steps_per_second": 2.098,
|
| 975 |
+
"step": 276
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.11,
|
| 979 |
+
"learning_rate": 2.664e-07,
|
| 980 |
+
"loss": 2.3641,
|
| 981 |
+
"step": 280
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.11,
|
| 985 |
+
"eval_loss": 2.1803271770477295,
|
| 986 |
+
"eval_runtime": 0.5146,
|
| 987 |
+
"eval_samples_per_second": 7.774,
|
| 988 |
+
"eval_steps_per_second": 1.943,
|
| 989 |
+
"step": 280
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.11,
|
| 993 |
+
"learning_rate": 2.6592e-07,
|
| 994 |
+
"loss": 2.3089,
|
| 995 |
+
"step": 284
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.11,
|
| 999 |
+
"eval_loss": 2.176274538040161,
|
| 1000 |
+
"eval_runtime": 0.488,
|
| 1001 |
+
"eval_samples_per_second": 8.196,
|
| 1002 |
+
"eval_steps_per_second": 2.049,
|
| 1003 |
+
"step": 284
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.12,
|
| 1007 |
+
"learning_rate": 2.6543999999999997e-07,
|
| 1008 |
+
"loss": 2.2645,
|
| 1009 |
+
"step": 288
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.12,
|
| 1013 |
+
"eval_loss": 2.1720588207244873,
|
| 1014 |
+
"eval_runtime": 0.4973,
|
| 1015 |
+
"eval_samples_per_second": 8.043,
|
| 1016 |
+
"eval_steps_per_second": 2.011,
|
| 1017 |
+
"step": 288
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.12,
|
| 1021 |
+
"learning_rate": 2.6495999999999996e-07,
|
| 1022 |
+
"loss": 2.3439,
|
| 1023 |
+
"step": 292
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.12,
|
| 1027 |
+
"eval_loss": 2.1687240600585938,
|
| 1028 |
+
"eval_runtime": 0.6283,
|
| 1029 |
+
"eval_samples_per_second": 6.366,
|
| 1030 |
+
"eval_steps_per_second": 1.592,
|
| 1031 |
+
"step": 292
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.12,
|
| 1035 |
+
"learning_rate": 2.6448e-07,
|
| 1036 |
+
"loss": 2.3285,
|
| 1037 |
+
"step": 296
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 0.12,
|
| 1041 |
+
"eval_loss": 2.1649253368377686,
|
| 1042 |
+
"eval_runtime": 0.6996,
|
| 1043 |
+
"eval_samples_per_second": 5.718,
|
| 1044 |
+
"eval_steps_per_second": 1.429,
|
| 1045 |
+
"step": 296
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.12,
|
| 1049 |
+
"learning_rate": 2.64e-07,
|
| 1050 |
+
"loss": 2.3126,
|
| 1051 |
+
"step": 300
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 0.12,
|
| 1055 |
+
"eval_loss": 2.160398483276367,
|
| 1056 |
+
"eval_runtime": 0.6904,
|
| 1057 |
+
"eval_samples_per_second": 5.794,
|
| 1058 |
+
"eval_steps_per_second": 1.448,
|
| 1059 |
+
"step": 300
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.12,
|
| 1063 |
+
"learning_rate": 2.6351999999999997e-07,
|
| 1064 |
+
"loss": 2.3356,
|
| 1065 |
+
"step": 304
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.12,
|
| 1069 |
+
"eval_loss": 2.1570284366607666,
|
| 1070 |
+
"eval_runtime": 0.4953,
|
| 1071 |
+
"eval_samples_per_second": 8.076,
|
| 1072 |
+
"eval_steps_per_second": 2.019,
|
| 1073 |
+
"step": 304
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.12,
|
| 1077 |
+
"learning_rate": 2.6304e-07,
|
| 1078 |
+
"loss": 2.3396,
|
| 1079 |
+
"step": 308
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.12,
|
| 1083 |
+
"eval_loss": 2.1527013778686523,
|
| 1084 |
+
"eval_runtime": 0.4977,
|
| 1085 |
+
"eval_samples_per_second": 8.037,
|
| 1086 |
+
"eval_steps_per_second": 2.009,
|
| 1087 |
+
"step": 308
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.12,
|
| 1091 |
+
"learning_rate": 2.6256e-07,
|
| 1092 |
+
"loss": 2.2972,
|
| 1093 |
+
"step": 312
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 0.12,
|
| 1097 |
+
"eval_loss": 2.148724317550659,
|
| 1098 |
+
"eval_runtime": 0.4939,
|
| 1099 |
+
"eval_samples_per_second": 8.099,
|
| 1100 |
+
"eval_steps_per_second": 2.025,
|
| 1101 |
+
"step": 312
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.13,
|
| 1105 |
+
"learning_rate": 2.6208e-07,
|
| 1106 |
+
"loss": 2.3321,
|
| 1107 |
+
"step": 316
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.13,
|
| 1111 |
+
"eval_loss": 2.1449663639068604,
|
| 1112 |
+
"eval_runtime": 0.4784,
|
| 1113 |
+
"eval_samples_per_second": 8.362,
|
| 1114 |
+
"eval_steps_per_second": 2.09,
|
| 1115 |
+
"step": 316
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.13,
|
| 1119 |
+
"learning_rate": 2.616e-07,
|
| 1120 |
+
"loss": 2.3348,
|
| 1121 |
+
"step": 320
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 0.13,
|
| 1125 |
+
"eval_loss": 2.1414906978607178,
|
| 1126 |
+
"eval_runtime": 0.4949,
|
| 1127 |
+
"eval_samples_per_second": 8.082,
|
| 1128 |
+
"eval_steps_per_second": 2.021,
|
| 1129 |
+
"step": 320
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.13,
|
| 1133 |
+
"learning_rate": 2.6112e-07,
|
| 1134 |
+
"loss": 2.2728,
|
| 1135 |
+
"step": 324
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 0.13,
|
| 1139 |
+
"eval_loss": 2.1374001502990723,
|
| 1140 |
+
"eval_runtime": 0.6321,
|
| 1141 |
+
"eval_samples_per_second": 6.328,
|
| 1142 |
+
"eval_steps_per_second": 1.582,
|
| 1143 |
+
"step": 324
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.13,
|
| 1147 |
+
"learning_rate": 2.6064e-07,
|
| 1148 |
+
"loss": 2.287,
|
| 1149 |
+
"step": 328
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.13,
|
| 1153 |
+
"eval_loss": 2.1333529949188232,
|
| 1154 |
+
"eval_runtime": 0.6547,
|
| 1155 |
+
"eval_samples_per_second": 6.109,
|
| 1156 |
+
"eval_steps_per_second": 1.527,
|
| 1157 |
+
"step": 328
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.13,
|
| 1161 |
+
"learning_rate": 2.6015999999999997e-07,
|
| 1162 |
+
"loss": 2.2474,
|
| 1163 |
+
"step": 332
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 0.13,
|
| 1167 |
+
"eval_loss": 2.1297547817230225,
|
| 1168 |
+
"eval_runtime": 0.7093,
|
| 1169 |
+
"eval_samples_per_second": 5.639,
|
| 1170 |
+
"eval_steps_per_second": 1.41,
|
| 1171 |
+
"step": 332
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.13,
|
| 1175 |
+
"learning_rate": 2.5968e-07,
|
| 1176 |
+
"loss": 2.3214,
|
| 1177 |
+
"step": 336
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.13,
|
| 1181 |
+
"eval_loss": 2.126392364501953,
|
| 1182 |
+
"eval_runtime": 0.6909,
|
| 1183 |
+
"eval_samples_per_second": 5.789,
|
| 1184 |
+
"eval_steps_per_second": 1.447,
|
| 1185 |
+
"step": 336
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.14,
|
| 1189 |
+
"learning_rate": 2.592e-07,
|
| 1190 |
+
"loss": 2.2725,
|
| 1191 |
+
"step": 340
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.14,
|
| 1195 |
+
"eval_loss": 2.122309923171997,
|
| 1196 |
+
"eval_runtime": 0.4823,
|
| 1197 |
+
"eval_samples_per_second": 8.293,
|
| 1198 |
+
"eval_steps_per_second": 2.073,
|
| 1199 |
+
"step": 340
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.14,
|
| 1203 |
+
"learning_rate": 2.5872000000000003e-07,
|
| 1204 |
+
"loss": 2.3114,
|
| 1205 |
+
"step": 344
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.14,
|
| 1209 |
+
"eval_loss": 2.118303060531616,
|
| 1210 |
+
"eval_runtime": 0.4954,
|
| 1211 |
+
"eval_samples_per_second": 8.075,
|
| 1212 |
+
"eval_steps_per_second": 2.019,
|
| 1213 |
+
"step": 344
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.14,
|
| 1217 |
+
"learning_rate": 2.5824e-07,
|
| 1218 |
+
"loss": 2.2333,
|
| 1219 |
+
"step": 348
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 0.14,
|
| 1223 |
+
"eval_loss": 2.114621162414551,
|
| 1224 |
+
"eval_runtime": 0.4856,
|
| 1225 |
+
"eval_samples_per_second": 8.238,
|
| 1226 |
+
"eval_steps_per_second": 2.059,
|
| 1227 |
+
"step": 348
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.14,
|
| 1231 |
+
"learning_rate": 2.5776e-07,
|
| 1232 |
+
"loss": 2.2812,
|
| 1233 |
+
"step": 352
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.14,
|
| 1237 |
+
"eval_loss": 2.11067795753479,
|
| 1238 |
+
"eval_runtime": 0.4778,
|
| 1239 |
+
"eval_samples_per_second": 8.372,
|
| 1240 |
+
"eval_steps_per_second": 2.093,
|
| 1241 |
+
"step": 352
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.14,
|
| 1245 |
+
"learning_rate": 2.5728e-07,
|
| 1246 |
+
"loss": 2.2454,
|
| 1247 |
+
"step": 356
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 0.14,
|
| 1251 |
+
"eval_loss": 2.106940746307373,
|
| 1252 |
+
"eval_runtime": 0.4945,
|
| 1253 |
+
"eval_samples_per_second": 8.089,
|
| 1254 |
+
"eval_steps_per_second": 2.022,
|
| 1255 |
+
"step": 356
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.14,
|
| 1259 |
+
"learning_rate": 2.5679999999999997e-07,
|
| 1260 |
+
"loss": 2.2261,
|
| 1261 |
+
"step": 360
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 0.14,
|
| 1265 |
+
"eval_loss": 2.1031668186187744,
|
| 1266 |
+
"eval_runtime": 0.6521,
|
| 1267 |
+
"eval_samples_per_second": 6.134,
|
| 1268 |
+
"eval_steps_per_second": 1.533,
|
| 1269 |
+
"step": 360
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.15,
|
| 1273 |
+
"learning_rate": 2.5632e-07,
|
| 1274 |
+
"loss": 2.2841,
|
| 1275 |
+
"step": 364
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.15,
|
| 1279 |
+
"eval_loss": 2.0989203453063965,
|
| 1280 |
+
"eval_runtime": 0.6249,
|
| 1281 |
+
"eval_samples_per_second": 6.401,
|
| 1282 |
+
"eval_steps_per_second": 1.6,
|
| 1283 |
+
"step": 364
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.15,
|
| 1287 |
+
"learning_rate": 2.5584e-07,
|
| 1288 |
+
"loss": 2.2481,
|
| 1289 |
+
"step": 368
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 0.15,
|
| 1293 |
+
"eval_loss": 2.095189332962036,
|
| 1294 |
+
"eval_runtime": 0.6855,
|
| 1295 |
+
"eval_samples_per_second": 5.835,
|
| 1296 |
+
"eval_steps_per_second": 1.459,
|
| 1297 |
+
"step": 368
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.15,
|
| 1301 |
+
"learning_rate": 2.5536e-07,
|
| 1302 |
+
"loss": 2.278,
|
| 1303 |
+
"step": 372
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 0.15,
|
| 1307 |
+
"eval_loss": 2.0912463665008545,
|
| 1308 |
+
"eval_runtime": 0.7393,
|
| 1309 |
+
"eval_samples_per_second": 5.411,
|
| 1310 |
+
"eval_steps_per_second": 1.353,
|
| 1311 |
+
"step": 372
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.15,
|
| 1315 |
+
"learning_rate": 2.5488e-07,
|
| 1316 |
+
"loss": 2.2765,
|
| 1317 |
+
"step": 376
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.15,
|
| 1321 |
+
"eval_loss": 2.087336301803589,
|
| 1322 |
+
"eval_runtime": 0.4793,
|
| 1323 |
+
"eval_samples_per_second": 8.345,
|
| 1324 |
+
"eval_steps_per_second": 2.086,
|
| 1325 |
+
"step": 376
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.15,
|
| 1329 |
+
"learning_rate": 2.544e-07,
|
| 1330 |
+
"loss": 2.2232,
|
| 1331 |
+
"step": 380
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 0.15,
|
| 1335 |
+
"eval_loss": 2.0833120346069336,
|
| 1336 |
+
"eval_runtime": 0.487,
|
| 1337 |
+
"eval_samples_per_second": 8.214,
|
| 1338 |
+
"eval_steps_per_second": 2.053,
|
| 1339 |
+
"step": 380
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.15,
|
| 1343 |
+
"learning_rate": 2.5392e-07,
|
| 1344 |
+
"loss": 2.306,
|
| 1345 |
+
"step": 384
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 0.15,
|
| 1349 |
+
"eval_loss": 2.079479932785034,
|
| 1350 |
+
"eval_runtime": 0.4722,
|
| 1351 |
+
"eval_samples_per_second": 8.471,
|
| 1352 |
+
"eval_steps_per_second": 2.118,
|
| 1353 |
+
"step": 384
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.16,
|
| 1357 |
+
"learning_rate": 2.5343999999999997e-07,
|
| 1358 |
+
"loss": 2.2126,
|
| 1359 |
+
"step": 388
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.16,
|
| 1363 |
+
"eval_loss": 2.0760295391082764,
|
| 1364 |
+
"eval_runtime": 0.4958,
|
| 1365 |
+
"eval_samples_per_second": 8.068,
|
| 1366 |
+
"eval_steps_per_second": 2.017,
|
| 1367 |
+
"step": 388
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.16,
|
| 1371 |
+
"learning_rate": 2.5295999999999996e-07,
|
| 1372 |
+
"loss": 2.2557,
|
| 1373 |
+
"step": 392
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.16,
|
| 1377 |
+
"eval_loss": 2.072136402130127,
|
| 1378 |
+
"eval_runtime": 0.469,
|
| 1379 |
+
"eval_samples_per_second": 8.529,
|
| 1380 |
+
"eval_steps_per_second": 2.132,
|
| 1381 |
+
"step": 392
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.16,
|
| 1385 |
+
"learning_rate": 2.5248e-07,
|
| 1386 |
+
"loss": 2.1988,
|
| 1387 |
+
"step": 396
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 0.16,
|
| 1391 |
+
"eval_loss": 2.0683670043945312,
|
| 1392 |
+
"eval_runtime": 0.6385,
|
| 1393 |
+
"eval_samples_per_second": 6.264,
|
| 1394 |
+
"eval_steps_per_second": 1.566,
|
| 1395 |
+
"step": 396
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.16,
|
| 1399 |
+
"learning_rate": 2.52e-07,
|
| 1400 |
+
"loss": 2.1917,
|
| 1401 |
+
"step": 400
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.16,
|
| 1405 |
+
"eval_loss": 2.0638906955718994,
|
| 1406 |
+
"eval_runtime": 0.6834,
|
| 1407 |
+
"eval_samples_per_second": 5.853,
|
| 1408 |
+
"eval_steps_per_second": 1.463,
|
| 1409 |
+
"step": 400
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.16,
|
| 1413 |
+
"learning_rate": 2.5152e-07,
|
| 1414 |
+
"loss": 2.2479,
|
| 1415 |
+
"step": 404
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 0.16,
|
| 1419 |
+
"eval_loss": 2.0599253177642822,
|
| 1420 |
+
"eval_runtime": 0.7261,
|
| 1421 |
+
"eval_samples_per_second": 5.509,
|
| 1422 |
+
"eval_steps_per_second": 1.377,
|
| 1423 |
+
"step": 404
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.16,
|
| 1427 |
+
"learning_rate": 2.5104e-07,
|
| 1428 |
+
"loss": 2.1484,
|
| 1429 |
+
"step": 408
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 0.16,
|
| 1433 |
+
"eval_loss": 2.055751085281372,
|
| 1434 |
+
"eval_runtime": 0.7367,
|
| 1435 |
+
"eval_samples_per_second": 5.429,
|
| 1436 |
+
"eval_steps_per_second": 1.357,
|
| 1437 |
+
"step": 408
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.16,
|
| 1441 |
+
"learning_rate": 2.5056e-07,
|
| 1442 |
+
"loss": 2.1886,
|
| 1443 |
+
"step": 412
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.16,
|
| 1447 |
+
"eval_loss": 2.052119016647339,
|
| 1448 |
+
"eval_runtime": 0.4808,
|
| 1449 |
+
"eval_samples_per_second": 8.319,
|
| 1450 |
+
"eval_steps_per_second": 2.08,
|
| 1451 |
+
"step": 412
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.17,
|
| 1455 |
+
"learning_rate": 2.5007999999999997e-07,
|
| 1456 |
+
"loss": 2.2026,
|
| 1457 |
+
"step": 416
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 0.17,
|
| 1461 |
+
"eval_loss": 2.0482354164123535,
|
| 1462 |
+
"eval_runtime": 0.4856,
|
| 1463 |
+
"eval_samples_per_second": 8.238,
|
| 1464 |
+
"eval_steps_per_second": 2.059,
|
| 1465 |
+
"step": 416
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.17,
|
| 1469 |
+
"learning_rate": 2.4959999999999996e-07,
|
| 1470 |
+
"loss": 2.1572,
|
| 1471 |
+
"step": 420
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.17,
|
| 1475 |
+
"eval_loss": 2.0441887378692627,
|
| 1476 |
+
"eval_runtime": 0.4779,
|
| 1477 |
+
"eval_samples_per_second": 8.37,
|
| 1478 |
+
"eval_steps_per_second": 2.093,
|
| 1479 |
+
"step": 420
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.17,
|
| 1483 |
+
"learning_rate": 2.4912e-07,
|
| 1484 |
+
"loss": 2.1931,
|
| 1485 |
+
"step": 424
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.17,
|
| 1489 |
+
"eval_loss": 2.0399935245513916,
|
| 1490 |
+
"eval_runtime": 0.4803,
|
| 1491 |
+
"eval_samples_per_second": 8.329,
|
| 1492 |
+
"eval_steps_per_second": 2.082,
|
| 1493 |
+
"step": 424
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.17,
|
| 1497 |
+
"learning_rate": 2.4864e-07,
|
| 1498 |
+
"loss": 2.161,
|
| 1499 |
+
"step": 428
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.17,
|
| 1503 |
+
"eval_loss": 2.03645920753479,
|
| 1504 |
+
"eval_runtime": 0.4924,
|
| 1505 |
+
"eval_samples_per_second": 8.123,
|
| 1506 |
+
"eval_steps_per_second": 2.031,
|
| 1507 |
+
"step": 428
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.17,
|
| 1511 |
+
"learning_rate": 2.4816e-07,
|
| 1512 |
+
"loss": 2.1115,
|
| 1513 |
+
"step": 432
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 0.17,
|
| 1517 |
+
"eval_loss": 2.032196044921875,
|
| 1518 |
+
"eval_runtime": 0.6345,
|
| 1519 |
+
"eval_samples_per_second": 6.304,
|
| 1520 |
+
"eval_steps_per_second": 1.576,
|
| 1521 |
+
"step": 432
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.17,
|
| 1525 |
+
"learning_rate": 2.4768e-07,
|
| 1526 |
+
"loss": 2.173,
|
| 1527 |
+
"step": 436
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.17,
|
| 1531 |
+
"eval_loss": 2.028397560119629,
|
| 1532 |
+
"eval_runtime": 0.6625,
|
| 1533 |
+
"eval_samples_per_second": 6.038,
|
| 1534 |
+
"eval_steps_per_second": 1.509,
|
| 1535 |
+
"step": 436
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.18,
|
| 1539 |
+
"learning_rate": 2.472e-07,
|
| 1540 |
+
"loss": 2.1491,
|
| 1541 |
+
"step": 440
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 0.18,
|
| 1545 |
+
"eval_loss": 2.0247464179992676,
|
| 1546 |
+
"eval_runtime": 0.6969,
|
| 1547 |
+
"eval_samples_per_second": 5.74,
|
| 1548 |
+
"eval_steps_per_second": 1.435,
|
| 1549 |
+
"step": 440
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.18,
|
| 1553 |
+
"learning_rate": 2.4672e-07,
|
| 1554 |
+
"loss": 2.1716,
|
| 1555 |
+
"step": 444
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 0.18,
|
| 1559 |
+
"eval_loss": 2.0203933715820312,
|
| 1560 |
+
"eval_runtime": 0.7311,
|
| 1561 |
+
"eval_samples_per_second": 5.471,
|
| 1562 |
+
"eval_steps_per_second": 1.368,
|
| 1563 |
+
"step": 444
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.18,
|
| 1567 |
+
"learning_rate": 2.4623999999999996e-07,
|
| 1568 |
+
"loss": 2.2031,
|
| 1569 |
+
"step": 448
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.18,
|
| 1573 |
+
"eval_loss": 2.016533374786377,
|
| 1574 |
+
"eval_runtime": 0.4875,
|
| 1575 |
+
"eval_samples_per_second": 8.206,
|
| 1576 |
+
"eval_steps_per_second": 2.051,
|
| 1577 |
+
"step": 448
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.18,
|
| 1581 |
+
"learning_rate": 2.4576e-07,
|
| 1582 |
+
"loss": 2.1466,
|
| 1583 |
+
"step": 452
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 0.18,
|
| 1587 |
+
"eval_loss": 2.012568473815918,
|
| 1588 |
+
"eval_runtime": 0.4897,
|
| 1589 |
+
"eval_samples_per_second": 8.168,
|
| 1590 |
+
"eval_steps_per_second": 2.042,
|
| 1591 |
+
"step": 452
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.18,
|
| 1595 |
+
"learning_rate": 2.4528e-07,
|
| 1596 |
+
"loss": 2.1384,
|
| 1597 |
+
"step": 456
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 0.18,
|
| 1601 |
+
"eval_loss": 2.0088417530059814,
|
| 1602 |
+
"eval_runtime": 0.4969,
|
| 1603 |
+
"eval_samples_per_second": 8.05,
|
| 1604 |
+
"eval_steps_per_second": 2.013,
|
| 1605 |
+
"step": 456
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.18,
|
| 1609 |
+
"learning_rate": 2.4479999999999997e-07,
|
| 1610 |
+
"loss": 2.1824,
|
| 1611 |
+
"step": 460
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.18,
|
| 1615 |
+
"eval_loss": 2.0047850608825684,
|
| 1616 |
+
"eval_runtime": 0.4897,
|
| 1617 |
+
"eval_samples_per_second": 8.168,
|
| 1618 |
+
"eval_steps_per_second": 2.042,
|
| 1619 |
+
"step": 460
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.19,
|
| 1623 |
+
"learning_rate": 2.4432e-07,
|
| 1624 |
+
"loss": 2.1401,
|
| 1625 |
+
"step": 464
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 0.19,
|
| 1629 |
+
"eval_loss": 2.0006463527679443,
|
| 1630 |
+
"eval_runtime": 0.4882,
|
| 1631 |
+
"eval_samples_per_second": 8.193,
|
| 1632 |
+
"eval_steps_per_second": 2.048,
|
| 1633 |
+
"step": 464
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.19,
|
| 1637 |
+
"learning_rate": 2.4384e-07,
|
| 1638 |
+
"loss": 2.2086,
|
| 1639 |
+
"step": 468
|
| 1640 |
+
},
|
| 1641 |
+
{
|
| 1642 |
+
"epoch": 0.19,
|
| 1643 |
+
"eval_loss": 1.9969314336776733,
|
| 1644 |
+
"eval_runtime": 0.6612,
|
| 1645 |
+
"eval_samples_per_second": 6.049,
|
| 1646 |
+
"eval_steps_per_second": 1.512,
|
| 1647 |
+
"step": 468
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.19,
|
| 1651 |
+
"learning_rate": 2.4336e-07,
|
| 1652 |
+
"loss": 2.1687,
|
| 1653 |
+
"step": 472
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 0.19,
|
| 1657 |
+
"eval_loss": 1.9925954341888428,
|
| 1658 |
+
"eval_runtime": 0.6804,
|
| 1659 |
+
"eval_samples_per_second": 5.879,
|
| 1660 |
+
"eval_steps_per_second": 1.47,
|
| 1661 |
+
"step": 472
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.19,
|
| 1665 |
+
"learning_rate": 2.4287999999999996e-07,
|
| 1666 |
+
"loss": 2.145,
|
| 1667 |
+
"step": 476
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 0.19,
|
| 1671 |
+
"eval_loss": 1.9888066053390503,
|
| 1672 |
+
"eval_runtime": 0.6955,
|
| 1673 |
+
"eval_samples_per_second": 5.752,
|
| 1674 |
+
"eval_steps_per_second": 1.438,
|
| 1675 |
+
"step": 476
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.19,
|
| 1679 |
+
"learning_rate": 2.424e-07,
|
| 1680 |
+
"loss": 2.2007,
|
| 1681 |
+
"step": 480
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 0.19,
|
| 1685 |
+
"eval_loss": 1.9850127696990967,
|
| 1686 |
+
"eval_runtime": 0.7558,
|
| 1687 |
+
"eval_samples_per_second": 5.292,
|
| 1688 |
+
"eval_steps_per_second": 1.323,
|
| 1689 |
+
"step": 480
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.19,
|
| 1693 |
+
"learning_rate": 2.4192e-07,
|
| 1694 |
+
"loss": 2.1367,
|
| 1695 |
+
"step": 484
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.19,
|
| 1699 |
+
"eval_loss": 1.9808437824249268,
|
| 1700 |
+
"eval_runtime": 0.4706,
|
| 1701 |
+
"eval_samples_per_second": 8.499,
|
| 1702 |
+
"eval_steps_per_second": 2.125,
|
| 1703 |
+
"step": 484
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.2,
|
| 1707 |
+
"learning_rate": 2.4143999999999997e-07,
|
| 1708 |
+
"loss": 2.1291,
|
| 1709 |
+
"step": 488
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 0.2,
|
| 1713 |
+
"eval_loss": 1.9767786264419556,
|
| 1714 |
+
"eval_runtime": 0.4803,
|
| 1715 |
+
"eval_samples_per_second": 8.327,
|
| 1716 |
+
"eval_steps_per_second": 2.082,
|
| 1717 |
+
"step": 488
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.2,
|
| 1721 |
+
"learning_rate": 2.4096e-07,
|
| 1722 |
+
"loss": 2.1124,
|
| 1723 |
+
"step": 492
|
| 1724 |
+
},
|
| 1725 |
+
{
|
| 1726 |
+
"epoch": 0.2,
|
| 1727 |
+
"eval_loss": 1.9728602170944214,
|
| 1728 |
+
"eval_runtime": 0.4802,
|
| 1729 |
+
"eval_samples_per_second": 8.33,
|
| 1730 |
+
"eval_steps_per_second": 2.082,
|
| 1731 |
+
"step": 492
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.2,
|
| 1735 |
+
"learning_rate": 2.4048e-07,
|
| 1736 |
+
"loss": 2.0738,
|
| 1737 |
+
"step": 496
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.2,
|
| 1741 |
+
"eval_loss": 1.968900203704834,
|
| 1742 |
+
"eval_runtime": 0.4884,
|
| 1743 |
+
"eval_samples_per_second": 8.189,
|
| 1744 |
+
"eval_steps_per_second": 2.047,
|
| 1745 |
+
"step": 496
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.2,
|
| 1749 |
+
"learning_rate": 2.4e-07,
|
| 1750 |
+
"loss": 2.1048,
|
| 1751 |
+
"step": 500
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 0.2,
|
| 1755 |
+
"eval_loss": 1.9646457433700562,
|
| 1756 |
+
"eval_runtime": 0.5026,
|
| 1757 |
+
"eval_samples_per_second": 7.959,
|
| 1758 |
+
"eval_steps_per_second": 1.99,
|
| 1759 |
+
"step": 500
|
| 1760 |
+
}
|
| 1761 |
+
],
|
| 1762 |
+
"logging_steps": 4,
|
| 1763 |
+
"max_steps": 2500,
|
| 1764 |
+
"num_input_tokens_seen": 0,
|
| 1765 |
+
"num_train_epochs": 1,
|
| 1766 |
+
"save_steps": 500,
|
| 1767 |
+
"total_flos": 6.356044087296e+16,
|
| 1768 |
+
"trial_name": null,
|
| 1769 |
+
"trial_params": null
|
| 1770 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8372290711385a4b881e6c95b154723c812dc21e47ba06376b2d40c72d854043
|
| 3 |
+
size 4600
|