Upload folder using huggingface_hub

Untitled.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "127668ee-44f0-4438-9337-e7c4a486aea3",
    "metadata": {},
    "outputs": [
@@ -16,278 +16,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5f308b1ddb654821afe650b708175cc2",
+       "model_id": "2529d1e8ef8c41e7acffc3b4b361e2d1",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6aaef8ad6f75454991e62a4d1e8ff05e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "43f479d5951b4c08848897dbda7a9483",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "scheduler.pt:   0%|          | 0.00/627 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "491a2b982ebe4269a0a1b302938fd82f",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Upload 43 LFS files:   0%|          | 0/43 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "de17bf15a4df42fea8781b73b667c4e7",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "rng_state.pth:   0%|          | 0.00/14.6k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ca5035dfd1e146138cdea7b14d3af6c8",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "optimizer.pt:   0%|          | 0.00/251M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "47a61e2634844e1ca0c556626ff249c2",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "training_args.bin:   0%|          | 0.00/4.22k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6a9b2c58d70b4ecfa879aaf3caea5edc",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "1d48ef30c59244f09a69b208b000ceee",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "94b212b03565444e8f7cedf2688feb24",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "optimizer.pt:   0%|          | 0.00/251M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0ba7f609f57b4cc5af970e364bb3ee27",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "rng_state.pth:   0%|          | 0.00/14.6k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "8be371a76bb14e2caa2ec672c112e23e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "scheduler.pt:   0%|          | 0.00/627 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "555efd66b20c49eab3edd2518af34f57",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "training_args.bin:   0%|          | 0.00/4.22k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "dd48f67cda094c958349a2f0a3107a3e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bdf4c85a50c54a1d8ee0c4805538cedc",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6294a1cf6111457ab2722f5570eaf5e9",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "optimizer.pt:   0%|          | 0.00/251M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "8d444fba036549dc8d5a86c9678c6f10",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "rng_state.pth:   0%|          | 0.00/14.6k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c042cf944dde4b6ab62fb374b4525c6e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "scheduler.pt:   0%|          | 0.00/627 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "1068ab04d0274c03904d387bdcdf5de7",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "training_args.bin:   0%|          | 0.00/4.22k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2a95d0b7842748dabd9fc1f8c18deb39",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
+       "Upload 5 LFS files:   0%|          | 0/5 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -296,7 +30,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f7797fab17a3420f95232a252c8d772c",
+       "model_id": "829fa95283aa4168978a8e583d10f286",
        "version_major": 2,
        "version_minor": 0
       },
@@ -310,7 +44,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "1bafc37d5dca444bb7c6ef711f7861ae",
+       "model_id": "3c2f0437b42a4fa997c9427f891609a6",
        "version_major": 2,
        "version_minor": 0
       },
@@ -324,63 +58,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "293fda7d9cd14487b770342136ed25d0",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "rng_state.pth:   0%|          | 0.00/14.6k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c36233f77fb14c2698087dd20522d4eb",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "scheduler.pt:   0%|          | 0.00/627 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3cef58ea84be4f3dae5e848ff5a6f27c",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "training_args.bin:   0%|          | 0.00/4.22k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e952241ba9be4c9fa8c9b2eeb1e3d9e4",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c0dce134d40942ab999de97456fe9b32",
+       "model_id": "4ecfcef382ee44a1acc18a868e3dbef3",
        "version_major": 2,
        "version_minor": 0
       },
@@ -394,21 +72,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "23a3b1c6a43f497b815f163b35460238",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "optimizer.pt:   0%|          | 0.00/251M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "1b971333e98e46ba9a10b38349a51f8f",
+       "model_id": "818bf55fe9124089b9378164fcb70319",
        "version_major": 2,
        "version_minor": 0
       },
@@ -422,7 +86,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bf03b21ac07a4980aecb4de18e18827c",
+       "model_id": "a067333d049c449b9b1a31a7eba92b40",
        "version_major": 2,
        "version_minor": 0
       },
@@ -433,209 +97,13 @@
      "metadata": {},
      "output_type": "display_data"
     },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9fb30b3564964dc796e0499f15d99c34",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "training_args.bin:   0%|          | 0.00/4.22k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "64204effaf14419f9519fa67dbcdffac",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d904d221326142dab018eef1e192ece5",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "b378d36e28dd4d3b8624b25461fd74a6",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "optimizer.pt:   0%|          | 0.00/251M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "df37b47bf87746de81f69960f9cfe4e8",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "rng_state.pth:   0%|          | 0.00/14.6k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "20da2b3cbbe44b2e8da8435d693d28f2",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "scheduler.pt:   0%|          | 0.00/627 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "953085469ce34c21b5d9f55849780e25",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "training_args.bin:   0%|          | 0.00/4.22k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4b4a15ec387b4ec3a2bcb652daa81651",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "b3beba6e06114e45891d074c1df6bfc8",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "adapter_model.bin:   0%|          | 0.00/62.8M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "902a27cfae9843b5968b145adf334838",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "optimizer.pt:   0%|          | 0.00/251M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "34bf777998ea4384841e047233995bd4",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "rng_state.pth:   0%|          | 0.00/14.6k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2be773b9220844fdbaf85ae04bcf6b5c",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "scheduler.pt:   0%|          | 0.00/627 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "b651756e28e8438a921ab786a3b4ca68",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "training_args.bin:   0%|          | 0.00/4.22k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "382b072e12f347de8318abac597ae873",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "tokenizer.model:   0%|          | 0.00/500k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "data": {
       "text/plain": [
        "'https://huggingface.co/nRuaif/Blind-test01/tree/main/'"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }

checkpoint-90/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-90/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-90/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab80d580d2473359497c3477b018ceeeea5cc05dea5431d27aa4603c281d9485
+size 62788109

checkpoint-90/adapter_model/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-90/adapter_model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-90/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab80d580d2473359497c3477b018ceeeea5cc05dea5431d27aa4603c281d9485
+size 62788109

checkpoint-90/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8316370ea618cc284e1ae2c314512562c3104ec39229694b796724e1b84f85
+size 250681597

checkpoint-90/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b128c0e1005d711adf0a8fefe90fdd8507d128f203b84f36d690b97c27d739
+size 14575

checkpoint-90/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1973c9badcac6f2b6522a65b2ddc2c01351eef8d7355ffdf2f6e10ecab6ff1
+size 627

checkpoint-90/trainer_state.json

@@ -0,0 +1,631 @@
+{
+  "best_metric": 2.0155017375946045,
+  "best_model_checkpoint": "./qlora-out-kimiko-test2/checkpoint-90",
+  "epoch": 2.3263327948303716,
+  "eval_steps": 10,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1e-05,
+      "loss": 1.5707,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2e-05,
+      "loss": 1.5621,
+      "step": 2
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3e-05,
+      "loss": 1.4812,
+      "step": 3
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4e-05,
+      "loss": 1.5197,
+      "step": 4
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5e-05,
+      "loss": 1.5567,
+      "step": 5
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5e-05,
+      "loss": 1.4645,
+      "step": 6
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 5e-05,
+      "loss": 1.6122,
+      "step": 7
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 5e-05,
+      "loss": 1.5596,
+      "step": 8
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 5e-05,
+      "loss": 1.5608,
+      "step": 9
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5e-05,
+      "loss": 1.5456,
+      "step": 10
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 2.098437547683716,
+      "eval_runtime": 119.6161,
+      "eval_samples_per_second": 1.555,
+      "eval_steps_per_second": 0.777,
+      "step": 10
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5e-05,
+      "loss": 1.5645,
+      "step": 11
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5e-05,
+      "loss": 1.538,
+      "step": 12
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 5e-05,
+      "loss": 1.6388,
+      "step": 13
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 5e-05,
+      "loss": 1.4943,
+      "step": 14
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 5e-05,
+      "loss": 1.5469,
+      "step": 15
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 5e-05,
+      "loss": 1.6149,
+      "step": 16
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 5e-05,
+      "loss": 1.5345,
+      "step": 17
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 5e-05,
+      "loss": 1.4903,
+      "step": 18
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5e-05,
+      "loss": 1.5499,
+      "step": 19
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5e-05,
+      "loss": 1.5934,
+      "step": 20
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 2.066981077194214,
+      "eval_runtime": 119.5781,
+      "eval_samples_per_second": 1.555,
+      "eval_steps_per_second": 0.778,
+      "step": 20
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5e-05,
+      "loss": 1.4554,
+      "step": 21
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5e-05,
+      "loss": 1.5512,
+      "step": 22
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 5e-05,
+      "loss": 1.4636,
+      "step": 23
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 5e-05,
+      "loss": 1.5398,
+      "step": 24
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5e-05,
+      "loss": 1.5623,
+      "step": 25
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5e-05,
+      "loss": 1.4658,
+      "step": 26
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5e-05,
+      "loss": 1.4723,
+      "step": 27
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5e-05,
+      "loss": 1.432,
+      "step": 28
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5e-05,
+      "loss": 1.4814,
+      "step": 29
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5e-05,
+      "loss": 1.4924,
+      "step": 30
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 2.046339750289917,
+      "eval_runtime": 119.5771,
+      "eval_samples_per_second": 1.555,
+      "eval_steps_per_second": 0.778,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5e-05,
+      "loss": 1.5809,
+      "step": 31
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5e-05,
+      "loss": 1.4803,
+      "step": 32
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5e-05,
+      "loss": 1.4878,
+      "step": 33
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5e-05,
+      "loss": 1.3871,
+      "step": 34
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5e-05,
+      "loss": 1.5151,
+      "step": 35
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5e-05,
+      "loss": 1.4212,
+      "step": 36
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5e-05,
+      "loss": 1.6284,
+      "step": 37
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 5e-05,
+      "loss": 1.5002,
+      "step": 38
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 5e-05,
+      "loss": 1.4452,
+      "step": 39
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 5e-05,
+      "loss": 1.4399,
+      "step": 40
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 2.0354697704315186,
+      "eval_runtime": 119.5875,
+      "eval_samples_per_second": 1.555,
+      "eval_steps_per_second": 0.778,
+      "step": 40
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 5e-05,
+      "loss": 1.465,
+      "step": 41
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 5e-05,
+      "loss": 1.4199,
+      "step": 42
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 5e-05,
+      "loss": 1.5403,
+      "step": 43
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 5e-05,
+      "loss": 1.4499,
+      "step": 44
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 5e-05,
+      "loss": 1.5751,
+      "step": 45
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 5e-05,
+      "loss": 1.4809,
+      "step": 46
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 5e-05,
+      "loss": 1.5022,
+      "step": 47
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 5e-05,
+      "loss": 1.4663,
+      "step": 48
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5e-05,
+      "loss": 1.4435,
+      "step": 49
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 5e-05,
+      "loss": 1.4246,
+      "step": 50
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 2.0276732444763184,
+      "eval_runtime": 119.5811,
+      "eval_samples_per_second": 1.555,
+      "eval_steps_per_second": 0.778,
+      "step": 50
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5e-05,
+      "loss": 1.4877,
+      "step": 51
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5e-05,
+      "loss": 1.4066,
+      "step": 52
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 5e-05,
+      "loss": 1.3559,
+      "step": 53
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 5e-05,
+      "loss": 1.5591,
+      "step": 54
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5e-05,
+      "loss": 1.4942,
+      "step": 55
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5e-05,
+      "loss": 1.4685,
+      "step": 56
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5e-05,
+      "loss": 1.4165,
+      "step": 57
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 5e-05,
+      "loss": 1.3995,
+      "step": 58
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 5e-05,
+      "loss": 1.3931,
+      "step": 59
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 5e-05,
+      "loss": 1.4234,
+      "step": 60
+    },
+    {
+      "epoch": 1.55,
+      "eval_loss": 2.0228564739227295,
+      "eval_runtime": 119.5715,
+      "eval_samples_per_second": 1.556,
+      "eval_steps_per_second": 0.778,
+      "step": 60
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5e-05,
+      "loss": 1.4732,
+      "step": 61
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 5e-05,
+      "loss": 1.4349,
+      "step": 62
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5e-05,
+      "loss": 1.4548,
+      "step": 63
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 5e-05,
+      "loss": 1.48,
+      "step": 64
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 5e-05,
+      "loss": 1.3789,
+      "step": 65
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 5e-05,
+      "loss": 1.3915,
+      "step": 66
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 5e-05,
+      "loss": 1.3789,
+      "step": 67
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 5e-05,
+      "loss": 1.5206,
+      "step": 68
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 5e-05,
+      "loss": 1.4851,
+      "step": 69
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 5e-05,
+      "loss": 1.5251,
+      "step": 70
+    },
+    {
+      "epoch": 1.81,
+      "eval_loss": 2.0199856758117676,
+      "eval_runtime": 119.5994,
+      "eval_samples_per_second": 1.555,
+      "eval_steps_per_second": 0.778,
+      "step": 70
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 5e-05,
+      "loss": 1.4152,
+      "step": 71
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 5e-05,
+      "loss": 1.4262,
+      "step": 72
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 5e-05,
+      "loss": 1.5563,
+      "step": 73
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 5e-05,
+      "loss": 1.42,
+      "step": 74
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5e-05,
+      "loss": 1.4407,
+      "step": 75
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5e-05,
+      "loss": 1.3953,
+      "step": 76
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5e-05,
+      "loss": 1.4186,
+      "step": 77
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5e-05,
+      "loss": 1.3863,
+      "step": 78
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 5e-05,
+      "loss": 1.3907,
+      "step": 79
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 5e-05,
+      "loss": 1.5147,
+      "step": 80
+    },
+    {
+      "epoch": 2.07,
+      "eval_loss": 2.0174262523651123,
+      "eval_runtime": 119.6245,
+      "eval_samples_per_second": 1.555,
+      "eval_steps_per_second": 0.777,
+      "step": 80
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 5e-05,
+      "loss": 1.3683,
+      "step": 81
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 5e-05,
+      "loss": 1.4289,
+      "step": 82
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 5e-05,
+      "loss": 1.4033,
+      "step": 83
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 5e-05,
+      "loss": 1.384,
+      "step": 84
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5e-05,
+      "loss": 1.3379,
+      "step": 85
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 5e-05,
+      "loss": 1.3916,
+      "step": 86
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 5e-05,
+      "loss": 1.5267,
+      "step": 87
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 5e-05,
+      "loss": 1.4465,
+      "step": 88
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 5e-05,
+      "loss": 1.4349,
+      "step": 89
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 5e-05,
+      "loss": 1.4927,
+      "step": 90
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 2.0155017375946045,
+      "eval_runtime": 119.6021,
+      "eval_samples_per_second": 1.555,
+      "eval_steps_per_second": 0.778,
+      "step": 90
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 114,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "total_flos": 4.119054979969843e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-90/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca362c6e6a1bbe2523b2190a501c92d6dbb3db6186bef551619d83852cca3df1
+size 4219