checkpoint-2000 | step 2000 | loss 0.4383 | 5.0% complete

.gitattributes

@@ -37,3 +37,4 @@ checkpoint-42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-538/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-1797/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-2000/README.md

@@ -0,0 +1,124 @@
+# ScriptSwiftAI v12 (Dikshan)
+
+> QLoRA fine-tuned full-stack code generation model by **Dikshan** (India).
+> Covers Python, Django, Flask, FastAPI, React, Next.js, TypeScript, SQL, Docker.
+
+---
+
+## License
+
+**CC BY-NC 4.0** — Non-commercial use only. Must credit Dikshan / ScriptSwiftAI.
+https://creativecommons.org/licenses/by-nc/4.0/
+
+**Copyright © 2026 Dikshan. All rights reserved.**
+
+---
+
+## Model Details
+
+| Property | Value |
+|---|---|
+| **Base Model** | Qwen2.5-Coder-7B-Instruct |
+| **Method** | QLoRA (4-bit, r=64) |
+| **Hardware** | NVIDIA RTX 5070 Ti 16GB |
+| **Target Steps** | 40,000 |
+| **Dataset** | ~450-500k samples (17 datasets) |
+| **Max Length** | 1536 tokens |
+| **Developer** | Dikshan (India) |
+| **Training Started** | June 2026 |
+
+---
+
+## Changelog / Training Timeline
+
+*Auto-updated by train_v12.py on every checkpoint save.*
+*Append-only — entries never overwritten. HuggingFace commit history provides timestamps.*
+
+
+---
+
+### 🔵 Checkpoint — Step 13
+**Date:** June 22, 2026 at 18:44 IST
+**Checkpoint:** checkpoint-13
+**Step:** 13 / 40,000 (0.0% complete)
+**Loss:** 0.6164
+**Epoch:** 0.000
+**Zone:** 📚 Learning
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 25
+**Date:** June 22, 2026 at 18:50 IST
+**Checkpoint:** checkpoint-25
+**Step:** 25 / 40,000 (0.1% complete)
+**Loss:** 0.6057
+**Epoch:** 0.001
+**Zone:** 📚 Learning
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 36
+**Date:** June 22, 2026 at 18:58 IST
+**Checkpoint:** checkpoint-36
+**Step:** 36 / 40,000 (0.1% complete)
+**Loss:** 0.5508
+**Epoch:** 0.001
+**Zone:** 📚 Learning
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 42
+**Date:** June 22, 2026 at 19:08 IST
+**Checkpoint:** checkpoint-42
+**Step:** 42 / 40,000 (0.1% complete)
+**Loss:** 0.5525
+**Epoch:** 0.001
+**Zone:** 📚 Learning
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 538
+**Date:** June 22, 2026 at 23:38 IST
+**Checkpoint:** checkpoint-538
+**Step:** 538 / 40,000 (1.3% complete)
+**Loss:** 0.4087
+**Epoch:** 0.015
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 1,000
+**Date:** June 23, 2026 at 03:05 IST
+**Checkpoint:** checkpoint-1000
+**Step:** 1,000 / 40,000 (2.5% complete)
+**Loss:** 0.4174
+**Epoch:** 0.029
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 1,797
+**Date:** June 23, 2026 at 08:26 IST
+**Checkpoint:** checkpoint-1797
+**Step:** 1,797 / 40,000 (4.5% complete)
+**Loss:** 0.3927
+**Epoch:** 0.052
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py
+
+---
+
+### 🔵 Checkpoint — Step 2,000
+**Date:** June 23, 2026 at 09:52 IST
+**Checkpoint:** checkpoint-2000
+**Step:** 2,000 / 40,000 (5.0% complete)
+**Loss:** 0.4383
+**Epoch:** 0.058
+**Zone:** 📈 Good
+**Status:** Training ongoing — auto-uploaded via train_v12.py

checkpoint-2000/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d136ee377aacb77cb9482d99ed1c06a9ea5276360a19ee2d760ee002a38eab
+size 645975704

checkpoint-2000/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba4aa529e09202e7e244066f76ea9be6a1008e2b19b49ecdd7555e7b626c5eba
+size 329492947

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae7f1cb0377540e6ff5583100c9e6f34564381eba1188d66f6dfd51182860123
+size 14645

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:740717492a76c39840f8a2726daa4f145936784b7f89e9e569b8360762e8aeb1
+size 1465

checkpoint-2000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.057403716700674616,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0002922796166022129,
+      "grad_norm": 0.3604201674461365,
+      "learning_rate": 1.8e-06,
+      "loss": 0.6163836479187011,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005845592332044258,
+      "grad_norm": 0.307494193315506,
+      "learning_rate": 3.8e-06,
+      "loss": 0.6056640148162842,
+      "step": 20
+    },
+    {
+      "epoch": 0.00014613980830110646,
+      "grad_norm": 0.1861964464187622,
+      "learning_rate": 5.8e-06,
+      "loss": 0.5507771968841553,
+      "step": 30
+    },
+    {
+      "epoch": 0.00011691184664088517,
+      "grad_norm": 0.18063770234584808,
+      "learning_rate": 7.8e-06,
+      "loss": 0.5524736642837524,
+      "step": 40
+    },
+    {
+      "epoch": 0.0004091914632430981,
+      "grad_norm": 0.1831495314836502,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 0.5550893783569336,
+      "step": 50
+    },
+    {
+      "epoch": 0.000701471079845311,
+      "grad_norm": 0.2708336412906647,
+      "learning_rate": 1.18e-05,
+      "loss": 0.5027066707611084,
+      "step": 60
+    },
+    {
+      "epoch": 0.0009937506964475238,
+      "grad_norm": 0.16506414115428925,
+      "learning_rate": 1.3800000000000002e-05,
+      "loss": 0.5025710105895996,
+      "step": 70
+    },
+    {
+      "epoch": 0.0012860303130497368,
+      "grad_norm": 0.7222521305084229,
+      "learning_rate": 1.58e-05,
+      "loss": 0.44574794769287107,
+      "step": 80
+    },
+    {
+      "epoch": 0.0015783099296519498,
+      "grad_norm": 0.3094443678855896,
+      "learning_rate": 1.78e-05,
+      "loss": 0.463105583190918,
+      "step": 90
+    },
+    {
+      "epoch": 0.0018705895462541628,
+      "grad_norm": 0.22881925106048584,
+      "learning_rate": 1.9800000000000004e-05,
+      "loss": 0.47495498657226565,
+      "step": 100
+    },
+    {
+      "epoch": 0.0021628691628563755,
+      "grad_norm": 0.2994537055492401,
+      "learning_rate": 2.18e-05,
+      "loss": 0.44906439781188967,
+      "step": 110
+    },
+    {
+      "epoch": 0.0024551487794585887,
+      "grad_norm": 0.22821807861328125,
+      "learning_rate": 2.38e-05,
+      "loss": 0.4511695384979248,
+      "step": 120
+    },
+    {
+      "epoch": 0.0027474283960608015,
+      "grad_norm": 0.23172526061534882,
+      "learning_rate": 2.58e-05,
+      "loss": 0.45236430168151853,
+      "step": 130
+    },
+    {
+      "epoch": 0.003039708012663014,
+      "grad_norm": 0.25378280878067017,
+      "learning_rate": 2.7800000000000005e-05,
+      "loss": 0.49311389923095705,
+      "step": 140
+    },
+    {
+      "epoch": 0.0033319876292652274,
+      "grad_norm": 0.30715328454971313,
+      "learning_rate": 2.98e-05,
+      "loss": 0.45659761428833007,
+      "step": 150
+    },
+    {
+      "epoch": 0.00362426724586744,
+      "grad_norm": 0.2318553328514099,
+      "learning_rate": 3.18e-05,
+      "loss": 0.48353352546691897,
+      "step": 160
+    },
+    {
+      "epoch": 0.003916546862469653,
+      "grad_norm": 0.3422481417655945,
+      "learning_rate": 3.38e-05,
+      "loss": 0.48243284225463867,
+      "step": 170
+    },
+    {
+      "epoch": 0.004208826479071866,
+      "grad_norm": 0.2627033591270447,
+      "learning_rate": 3.58e-05,
+      "loss": 0.44968676567077637,
+      "step": 180
+    },
+    {
+      "epoch": 0.004501106095674079,
+      "grad_norm": 0.270560622215271,
+      "learning_rate": 3.7800000000000004e-05,
+      "loss": 0.43050732612609866,
+      "step": 190
+    },
+    {
+      "epoch": 0.004793385712276292,
+      "grad_norm": 0.29916077852249146,
+      "learning_rate": 3.9800000000000005e-05,
+      "loss": 0.38156795501708984,
+      "step": 200
+    },
+    {
+      "epoch": 0.005085665328878505,
+      "grad_norm": 0.29618600010871887,
+      "learning_rate": 4.18e-05,
+      "loss": 0.41876654624938964,
+      "step": 210
+    },
+    {
+      "epoch": 0.005377944945480718,
+      "grad_norm": 0.24618731439113617,
+      "learning_rate": 4.38e-05,
+      "loss": 0.4200754642486572,
+      "step": 220
+    },
+    {
+      "epoch": 0.00567022456208293,
+      "grad_norm": 0.4028846323490143,
+      "learning_rate": 4.58e-05,
+      "loss": 0.4128837585449219,
+      "step": 230
+    },
+    {
+      "epoch": 0.0059625041786851435,
+      "grad_norm": 0.2899196445941925,
+      "learning_rate": 4.78e-05,
+      "loss": 0.4727485656738281,
+      "step": 240
+    },
+    {
+      "epoch": 0.006254783795287357,
+      "grad_norm": 0.372092068195343,
+      "learning_rate": 4.9800000000000004e-05,
+      "loss": 0.3837599754333496,
+      "step": 250
+    },
+    {
+      "epoch": 0.00654706341188957,
+      "grad_norm": 0.27367591857910156,
+      "learning_rate": 5.1800000000000005e-05,
+      "loss": 0.4533690929412842,
+      "step": 260
+    },
+    {
+      "epoch": 0.006839343028491782,
+      "grad_norm": 0.2826191782951355,
+      "learning_rate": 5.380000000000001e-05,
+      "loss": 0.5056231021881104,
+      "step": 270
+    },
+    {
+      "epoch": 0.007131622645093995,
+      "grad_norm": 0.34035593271255493,
+      "learning_rate": 5.580000000000001e-05,
+      "loss": 0.4258269309997559,
+      "step": 280
+    },
+    {
+      "epoch": 0.0074239022616962086,
+      "grad_norm": 0.2767459750175476,
+      "learning_rate": 5.7799999999999995e-05,
+      "loss": 0.3629124641418457,
+      "step": 290
+    },
+    {
+      "epoch": 0.007716181878298421,
+      "grad_norm": 0.2805218994617462,
+      "learning_rate": 5.9800000000000003e-05,
+      "loss": 0.35598738193511964,
+      "step": 300
+    },
+    {
+      "epoch": 0.008008461494900634,
+      "grad_norm": 0.32115164399147034,
+      "learning_rate": 6.18e-05,
+      "loss": 0.45623183250427246,
+      "step": 310
+    },
+    {
+      "epoch": 0.008300741111502847,
+      "grad_norm": 0.25464335083961487,
+      "learning_rate": 6.38e-05,
+      "loss": 0.3766467809677124,
+      "step": 320
+    },
+    {
+      "epoch": 0.00859302072810506,
+      "grad_norm": 0.240229070186615,
+      "learning_rate": 6.58e-05,
+      "loss": 0.4206503391265869,
+      "step": 330
+    },
+    {
+      "epoch": 0.008885300344707274,
+      "grad_norm": 0.24640053510665894,
+      "learning_rate": 6.780000000000001e-05,
+      "loss": 0.42534866333007815,
+      "step": 340
+    },
+    {
+      "epoch": 0.009177579961309485,
+      "grad_norm": 0.22595764696598053,
+      "learning_rate": 6.98e-05,
+      "loss": 0.4169299602508545,
+      "step": 350
+    },
+    {
+      "epoch": 0.009469859577911698,
+      "grad_norm": 0.2035064995288849,
+      "learning_rate": 7.18e-05,
+      "loss": 0.36454784870147705,
+      "step": 360
+    },
+    {
+      "epoch": 0.009762139194513911,
+      "grad_norm": 0.21908830106258392,
+      "learning_rate": 7.38e-05,
+      "loss": 0.39443838596343994,
+      "step": 370
+    },
+    {
+      "epoch": 0.010054418811116125,
+      "grad_norm": 0.2039889395236969,
+      "learning_rate": 7.58e-05,
+      "loss": 0.4549224853515625,
+      "step": 380
+    },
+    {
+      "epoch": 0.010346698427718338,
+      "grad_norm": 0.24606066942214966,
+      "learning_rate": 7.780000000000001e-05,
+      "loss": 0.3763291835784912,
+      "step": 390
+    },
+    {
+      "epoch": 0.010638978044320551,
+      "grad_norm": 0.4349507689476013,
+      "learning_rate": 7.98e-05,
+      "loss": 0.42160859107971194,
+      "step": 400
+    },
+    {
+      "epoch": 0.010931257660922762,
+      "grad_norm": 0.2086913138628006,
+      "learning_rate": 8.18e-05,
+      "loss": 0.4335451126098633,
+      "step": 410
+    },
+    {
+      "epoch": 0.011223537277524976,
+      "grad_norm": 0.21672461926937103,
+      "learning_rate": 8.38e-05,
+      "loss": 0.39824934005737306,
+      "step": 420
+    },
+    {
+      "epoch": 0.011515816894127189,
+      "grad_norm": 0.34380897879600525,
+      "learning_rate": 8.58e-05,
+      "loss": 0.4544211387634277,
+      "step": 430
+    },
+    {
+      "epoch": 0.011808096510729402,
+      "grad_norm": 0.2024194449186325,
+      "learning_rate": 8.78e-05,
+      "loss": 0.4060193061828613,
+      "step": 440
+    },
+    {
+      "epoch": 0.012100376127331615,
+      "grad_norm": 0.22563715279102325,
+      "learning_rate": 8.98e-05,
+      "loss": 0.3707286834716797,
+      "step": 450
+    },
+    {
+      "epoch": 0.012392655743933828,
+      "grad_norm": 0.20325998961925507,
+      "learning_rate": 9.180000000000001e-05,
+      "loss": 0.37896702289581297,
+      "step": 460
+    },
+    {
+      "epoch": 0.012684935360536042,
+      "grad_norm": 0.20927369594573975,
+      "learning_rate": 9.38e-05,
+      "loss": 0.4257774829864502,
+      "step": 470
+    },
+    {
+      "epoch": 0.012977214977138253,
+      "grad_norm": 0.2156561017036438,
+      "learning_rate": 9.58e-05,
+      "loss": 0.33562607765197755,
+      "step": 480
+    },
+    {
+      "epoch": 0.013269494593740466,
+      "grad_norm": 0.17501753568649292,
+      "learning_rate": 9.78e-05,
+      "loss": 0.4147501945495605,
+      "step": 490
+    },
+    {
+      "epoch": 0.01356177421034268,
+      "grad_norm": 0.243160679936409,
+      "learning_rate": 9.98e-05,
+      "loss": 0.411363410949707,
+      "step": 500
+    },
+    {
+      "epoch": 0.013854053826944893,
+      "grad_norm": 0.2272544652223587,
+      "learning_rate": 0.00010180000000000001,
+      "loss": 0.36809728145599363,
+      "step": 510
+    },
+    {
+      "epoch": 0.014146333443547106,
+      "grad_norm": 0.2265583574771881,
+      "learning_rate": 0.0001038,
+      "loss": 0.352154016494751,
+      "step": 520
+    },
+    {
+      "epoch": 0.014438613060149319,
+      "grad_norm": 0.21968695521354675,
+      "learning_rate": 0.00010580000000000001,
+      "loss": 0.40874533653259276,
+      "step": 530
+    },
+    {
+      "epoch": 0.01473089267675153,
+      "grad_norm": 0.20146295428276062,
+      "learning_rate": 0.00010780000000000002,
+      "loss": 0.4024982452392578,
+      "step": 540
+    },
+    {
+      "epoch": 0.015023172293353744,
+      "grad_norm": 0.22711141407489777,
+      "learning_rate": 0.00010980000000000001,
+      "loss": 0.412246561050415,
+      "step": 550
+    },
+    {
+      "epoch": 0.015315451909955957,
+      "grad_norm": 0.2056141048669815,
+      "learning_rate": 0.00011180000000000002,
+      "loss": 0.4331079006195068,
+      "step": 560
+    },
+    {
+      "epoch": 0.01560773152655817,
+      "grad_norm": 0.18964128196239471,
+      "learning_rate": 0.0001138,
+      "loss": 0.4245738506317139,
+      "step": 570
+    },
+    {
+      "epoch": 0.01590001114316038,
+      "grad_norm": 0.18264859914779663,
+      "learning_rate": 0.0001158,
+      "loss": 0.3981050491333008,
+      "step": 580
+    },
+    {
+      "epoch": 0.016192290759762595,
+      "grad_norm": 0.198320671916008,
+      "learning_rate": 0.0001178,
+      "loss": 0.44843344688415526,
+      "step": 590
+    },
+    {
+      "epoch": 0.016484570376364808,
+      "grad_norm": 0.20583713054656982,
+      "learning_rate": 0.0001198,
+      "loss": 0.45852208137512207,
+      "step": 600
+    },
+    {
+      "epoch": 0.01677684999296702,
+      "grad_norm": 0.18764640390872955,
+      "learning_rate": 0.0001218,
+      "loss": 0.39210479259490966,
+      "step": 610
+    },
+    {
+      "epoch": 0.017069129609569234,
+      "grad_norm": 0.22744227945804596,
+      "learning_rate": 0.0001238,
+      "loss": 0.48337244987487793,
+      "step": 620
+    },
+    {
+      "epoch": 0.017361409226171447,
+      "grad_norm": 0.25332197546958923,
+      "learning_rate": 0.0001258,
+      "loss": 0.47956342697143556,
+      "step": 630
+    },
+    {
+      "epoch": 0.01765368884277366,
+      "grad_norm": 0.18094617128372192,
+      "learning_rate": 0.00012780000000000002,
+      "loss": 0.36708922386169435,
+      "step": 640
+    },
+    {
+      "epoch": 0.017945968459375874,
+      "grad_norm": 0.2056637406349182,
+      "learning_rate": 0.0001298,
+      "loss": 0.45494647026062013,
+      "step": 650
+    },
+    {
+      "epoch": 0.018238248075978087,
+      "grad_norm": 0.18681053817272186,
+      "learning_rate": 0.0001318,
+      "loss": 0.39863851070404055,
+      "step": 660
+    },
+    {
+      "epoch": 0.0185305276925803,
+      "grad_norm": 0.18398210406303406,
+      "learning_rate": 0.00013380000000000003,
+      "loss": 0.42660346031188967,
+      "step": 670
+    },
+    {
+      "epoch": 0.018822807309182513,
+      "grad_norm": 0.2018873244524002,
+      "learning_rate": 0.00013580000000000002,
+      "loss": 0.41592912673950194,
+      "step": 680
+    },
+    {
+      "epoch": 0.019115086925784727,
+      "grad_norm": 0.20749719440937042,
+      "learning_rate": 0.0001378,
+      "loss": 0.4529616355895996,
+      "step": 690
+    },
+    {
+      "epoch": 0.01940736654238694,
+      "grad_norm": 0.17765171825885773,
+      "learning_rate": 0.0001398,
+      "loss": 0.4367457389831543,
+      "step": 700
+    },
+    {
+      "epoch": 0.01969964615898915,
+      "grad_norm": 0.24419377744197845,
+      "learning_rate": 0.0001418,
+      "loss": 0.4324330806732178,
+      "step": 710
+    },
+    {
+      "epoch": 0.019991925775591363,
+      "grad_norm": 0.1319461613893509,
+      "learning_rate": 0.0001438,
+      "loss": 0.38980741500854493,
+      "step": 720
+    },
+    {
+      "epoch": 0.020284205392193576,
+      "grad_norm": 0.18414747714996338,
+      "learning_rate": 0.0001458,
+      "loss": 0.45140395164489744,
+      "step": 730
+    },
+    {
+      "epoch": 0.02057648500879579,
+      "grad_norm": 0.19065886735916138,
+      "learning_rate": 0.00014780000000000001,
+      "loss": 0.34149444103240967,
+      "step": 740
+    },
+    {
+      "epoch": 0.020868764625398002,
+      "grad_norm": 0.3047577738761902,
+      "learning_rate": 0.0001498,
+      "loss": 0.39748594760894773,
+      "step": 750
+    },
+    {
+      "epoch": 0.021161044242000215,
+      "grad_norm": 0.20547902584075928,
+      "learning_rate": 0.0001518,
+      "loss": 0.35707693099975585,
+      "step": 760
+    },
+    {
+      "epoch": 0.02145332385860243,
+      "grad_norm": 0.1835167109966278,
+      "learning_rate": 0.0001538,
+      "loss": 0.3866844177246094,
+      "step": 770
+    },
+    {
+      "epoch": 0.021745603475204642,
+      "grad_norm": 0.12297193706035614,
+      "learning_rate": 0.00015580000000000002,
+      "loss": 0.3809194803237915,
+      "step": 780
+    },
+    {
+      "epoch": 0.022037883091806855,
+      "grad_norm": 0.23474228382110596,
+      "learning_rate": 0.00015780000000000001,
+      "loss": 0.40447239875793456,
+      "step": 790
+    },
+    {
+      "epoch": 0.022330162708409068,
+      "grad_norm": 0.1950707882642746,
+      "learning_rate": 0.0001598,
+      "loss": 0.36057252883911134,
+      "step": 800
+    },
+    {
+      "epoch": 0.02262244232501128,
+      "grad_norm": 0.19598263502120972,
+      "learning_rate": 0.00016180000000000003,
+      "loss": 0.3532793760299683,
+      "step": 810
+    },
+    {
+      "epoch": 0.022914721941613495,
+      "grad_norm": 0.21619845926761627,
+      "learning_rate": 0.0001638,
+      "loss": 0.33423144817352296,
+      "step": 820
+    },
+    {
+      "epoch": 0.023207001558215708,
+      "grad_norm": 0.1934775710105896,
+      "learning_rate": 0.0001658,
+      "loss": 0.4006977558135986,
+      "step": 830
+    },
+    {
+      "epoch": 0.023499281174817917,
+      "grad_norm": 0.2345370650291443,
+      "learning_rate": 0.0001678,
+      "loss": 0.42209348678588865,
+      "step": 840
+    },
+    {
+      "epoch": 0.02379156079142013,
+      "grad_norm": 0.2699654698371887,
+      "learning_rate": 0.0001698,
+      "loss": 0.3334143400192261,
+      "step": 850
+    },
+    {
+      "epoch": 0.024083840408022344,
+      "grad_norm": 0.1839752197265625,
+      "learning_rate": 0.0001718,
+      "loss": 0.42084970474243166,
+      "step": 860
+    },
+    {
+      "epoch": 0.024376120024624557,
+      "grad_norm": 0.22491669654846191,
+      "learning_rate": 0.0001738,
+      "loss": 0.420766544342041,
+      "step": 870
+    },
+    {
+      "epoch": 0.02466839964122677,
+      "grad_norm": 0.18370424211025238,
+      "learning_rate": 0.00017580000000000002,
+      "loss": 0.3486522912979126,
+      "step": 880
+    },
+    {
+      "epoch": 0.024960679257828983,
+      "grad_norm": 0.23166073858737946,
+      "learning_rate": 0.0001778,
+      "loss": 0.42749767303466796,
+      "step": 890
+    },
+    {
+      "epoch": 0.025252958874431197,
+      "grad_norm": 0.22481808066368103,
+      "learning_rate": 0.0001798,
+      "loss": 0.380033016204834,
+      "step": 900
+    },
+    {
+      "epoch": 0.02554523849103341,
+      "grad_norm": 0.24065051972866058,
+      "learning_rate": 0.00018180000000000003,
+      "loss": 0.45965576171875,
+      "step": 910
+    },
+    {
+      "epoch": 0.025837518107635623,
+      "grad_norm": 0.190377876162529,
+      "learning_rate": 0.00018380000000000002,
+      "loss": 0.3290415287017822,
+      "step": 920
+    },
+    {
+      "epoch": 0.026129797724237836,
+      "grad_norm": 0.2699977159500122,
+      "learning_rate": 0.00018580000000000002,
+      "loss": 0.4352889537811279,
+      "step": 930
+    },
+    {
+      "epoch": 0.02642207734084005,
+      "grad_norm": 0.2756347060203552,
+      "learning_rate": 0.0001878,
+      "loss": 0.4288458347320557,
+      "step": 940
+    },
+    {
+      "epoch": 0.026714356957442262,
+      "grad_norm": 0.23565548658370972,
+      "learning_rate": 0.0001898,
+      "loss": 0.29646151065826415,
+      "step": 950
+    },
+    {
+      "epoch": 0.027006636574044476,
+      "grad_norm": 0.18665672838687897,
+      "learning_rate": 0.0001918,
+      "loss": 0.39093432426452634,
+      "step": 960
+    },
+    {
+      "epoch": 0.027298916190646685,
+      "grad_norm": 0.24153801798820496,
+      "learning_rate": 0.0001938,
+      "loss": 0.42369751930236815,
+      "step": 970
+    },
+    {
+      "epoch": 0.0275911958072489,
+      "grad_norm": 0.18671485781669617,
+      "learning_rate": 0.00019580000000000002,
+      "loss": 0.38338029384613037,
+      "step": 980
+    },
+    {
+      "epoch": 0.027883475423851112,
+      "grad_norm": 0.2615300118923187,
+      "learning_rate": 0.0001978,
+      "loss": 0.36945343017578125,
+      "step": 990
+    },
+    {
+      "epoch": 0.028175755040453325,
+      "grad_norm": 0.2992021143436432,
+      "learning_rate": 0.0001998,
+      "loss": 0.4174357891082764,
+      "step": 1000
+    },
+    {
+      "epoch": 0.028468034657055538,
+      "grad_norm": 0.27294614911079407,
+      "learning_rate": 0.00019999997371998945,
+      "loss": 0.38078644275665285,
+      "step": 1010
+    },
+    {
+      "epoch": 0.02876031427365775,
+      "grad_norm": 0.22782108187675476,
+      "learning_rate": 0.0001999998828755262,
+      "loss": 0.41697354316711427,
+      "step": 1020
+    },
+    {
+      "epoch": 0.029052593890259965,
+      "grad_norm": 0.20225366950035095,
+      "learning_rate": 0.00019999972714222465,
+      "loss": 0.38390820026397704,
+      "step": 1030
+    },
+    {
+      "epoch": 0.029344873506862178,
+      "grad_norm": 0.22823745012283325,
+      "learning_rate": 0.00019999950652018584,
+      "loss": 0.41745734214782715,
+      "step": 1040
+    },
+    {
+      "epoch": 0.02963715312346439,
+      "grad_norm": 0.2649468183517456,
+      "learning_rate": 0.0001999992210095529,
+      "loss": 0.4053181648254395,
+      "step": 1050
+    },
+    {
+      "epoch": 0.029929432740066604,
+      "grad_norm": 0.21082913875579834,
+      "learning_rate": 0.00019999887061051115,
+      "loss": 0.41599574089050295,
+      "step": 1060
+    },
+    {
+      "epoch": 0.030221712356668817,
+      "grad_norm": 0.2594168782234192,
+      "learning_rate": 0.00019999845532328792,
+      "loss": 0.4727328777313232,
+      "step": 1070
+    },
+    {
+      "epoch": 0.03051399197327103,
+      "grad_norm": 0.19130517542362213,
+      "learning_rate": 0.0001999979751481527,
+      "loss": 0.42589612007141114,
+      "step": 1080
+    },
+    {
+      "epoch": 0.030806271589873244,
+      "grad_norm": 0.2338467836380005,
+      "learning_rate": 0.00019999743008541709,
+      "loss": 0.3404257774353027,
+      "step": 1090
+    },
+    {
+      "epoch": 0.031098551206475453,
+      "grad_norm": 0.2450529932975769,
+      "learning_rate": 0.00019999682013543474,
+      "loss": 0.35564963817596434,
+      "step": 1100
+    },
+    {
+      "epoch": 0.03139083082307767,
+      "grad_norm": 0.24461933970451355,
+      "learning_rate": 0.00019999614529860144,
+      "loss": 0.39687209129333495,
+      "step": 1110
+    },
+    {
+      "epoch": 0.03168311043967988,
+      "grad_norm": 0.23187988996505737,
+      "learning_rate": 0.0001999954055753551,
+      "loss": 0.41315088272094724,
+      "step": 1120
+    },
+    {
+      "epoch": 0.031975390056282096,
+      "grad_norm": 0.22851324081420898,
+      "learning_rate": 0.00019999460096617572,
+      "loss": 0.32306632995605467,
+      "step": 1130
+    },
+    {
+      "epoch": 0.03226766967288431,
+      "grad_norm": 0.18886074423789978,
+      "learning_rate": 0.00019999373147158543,
+      "loss": 0.3556957244873047,
+      "step": 1140
+    },
+    {
+      "epoch": 0.03255994928948652,
+      "grad_norm": 0.1941390335559845,
+      "learning_rate": 0.00019999279709214838,
+      "loss": 0.42602267265319826,
+      "step": 1150
+    },
+    {
+      "epoch": 0.03285222890608873,
+      "grad_norm": 0.2191803753376007,
+      "learning_rate": 0.00019999179782847088,
+      "loss": 0.3481628656387329,
+      "step": 1160
+    },
+    {
+      "epoch": 0.03314450852269094,
+      "grad_norm": 0.27078554034233093,
+      "learning_rate": 0.0001999907336812014,
+      "loss": 0.3957390785217285,
+      "step": 1170
+    },
+    {
+      "epoch": 0.033436788139293155,
+      "grad_norm": 0.31014931201934814,
+      "learning_rate": 0.00019998960465103042,
+      "loss": 0.3879474878311157,
+      "step": 1180
+    },
+    {
+      "epoch": 0.03372906775589537,
+      "grad_norm": 0.1903751790523529,
+      "learning_rate": 0.00019998841073869055,
+      "loss": 0.42315473556518557,
+      "step": 1190
+    },
+    {
+      "epoch": 0.03402134737249758,
+      "grad_norm": 0.2546682357788086,
+      "learning_rate": 0.0001999871519449565,
+      "loss": 0.36317920684814453,
+      "step": 1200
+    },
+    {
+      "epoch": 0.034313626989099795,
+      "grad_norm": 0.1552298665046692,
+      "learning_rate": 0.0001999858282706451,
+      "loss": 0.36159753799438477,
+      "step": 1210
+    },
+    {
+      "epoch": 0.03460590660570201,
+      "grad_norm": 0.19712704420089722,
+      "learning_rate": 0.00019998443971661525,
+      "loss": 0.3884085416793823,
+      "step": 1220
+    },
+    {
+      "epoch": 0.03489818622230422,
+      "grad_norm": 0.2729942500591278,
+      "learning_rate": 0.000199982986283768,
+      "loss": 0.4681094169616699,
+      "step": 1230
+    },
+    {
+      "epoch": 0.035190465838906435,
+      "grad_norm": 0.1953604519367218,
+      "learning_rate": 0.00019998146797304642,
+      "loss": 0.34714839458465574,
+      "step": 1240
+    },
+    {
+      "epoch": 0.03548274545550865,
+      "grad_norm": 0.2132028043270111,
+      "learning_rate": 0.0001999798847854358,
+      "loss": 0.4187171936035156,
+      "step": 1250
+    },
+    {
+      "epoch": 0.03577502507211086,
+      "grad_norm": 0.21808749437332153,
+      "learning_rate": 0.0001999782367219634,
+      "loss": 0.4529675006866455,
+      "step": 1260
+    },
+    {
+      "epoch": 0.036067304688713074,
+      "grad_norm": 0.2665892541408539,
+      "learning_rate": 0.0001999765237836986,
+      "loss": 0.40354113578796386,
+      "step": 1270
+    },
+    {
+      "epoch": 0.03635958430531529,
+      "grad_norm": 0.18756791949272156,
+      "learning_rate": 0.00019997474597175302,
+      "loss": 0.33424665927886965,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0366518639219175,
+      "grad_norm": 0.23514626920223236,
+      "learning_rate": 0.00019997290328728013,
+      "loss": 0.34480867385864256,
+      "step": 1290
+    },
+    {
+      "epoch": 0.036944143538519714,
+      "grad_norm": 0.24087919294834137,
+      "learning_rate": 0.0001999709957314757,
+      "loss": 0.40560035705566405,
+      "step": 1300
+    },
+    {
+      "epoch": 0.03723642315512193,
+      "grad_norm": 0.1967712640762329,
+      "learning_rate": 0.0001999690233055775,
+      "loss": 0.4166306495666504,
+      "step": 1310
+    },
+    {
+      "epoch": 0.03752870277172414,
+      "grad_norm": 0.22088399529457092,
+      "learning_rate": 0.00019996698601086545,
+      "loss": 0.4286780834197998,
+      "step": 1320
+    },
+    {
+      "epoch": 0.03782098238832635,
+      "grad_norm": 0.21077096462249756,
+      "learning_rate": 0.0001999648838486615,
+      "loss": 0.3549200534820557,
+      "step": 1330
+    },
+    {
+      "epoch": 0.038113262004928566,
+      "grad_norm": 0.2842172682285309,
+      "learning_rate": 0.0001999627168203297,
+      "loss": 0.4626432418823242,
+      "step": 1340
+    },
+    {
+      "epoch": 0.03840554162153078,
+      "grad_norm": 0.23517769575119019,
+      "learning_rate": 0.00019996048492727626,
+      "loss": 0.39797124862670896,
+      "step": 1350
+    },
+    {
+      "epoch": 0.03869782123813299,
+      "grad_norm": 0.22531968355178833,
+      "learning_rate": 0.0001999581881709494,
+      "loss": 0.39006221294403076,
+      "step": 1360
+    },
+    {
+      "epoch": 0.038990100854735206,
+      "grad_norm": 0.1859465092420578,
+      "learning_rate": 0.00019995582655283944,
+      "loss": 0.3752875804901123,
+      "step": 1370
+    },
+    {
+      "epoch": 0.03928238047133742,
+      "grad_norm": 0.1793965846300125,
+      "learning_rate": 0.00019995340007447884,
+      "loss": 0.3678503751754761,
+      "step": 1380
+    },
+    {
+      "epoch": 0.03957466008793963,
+      "grad_norm": 0.1874365508556366,
+      "learning_rate": 0.00019995090873744213,
+      "loss": 0.40687713623046873,
+      "step": 1390
+    },
+    {
+      "epoch": 0.039866939704541846,
+      "grad_norm": 0.22492875158786774,
+      "learning_rate": 0.00019994835254334592,
+      "loss": 0.3897545337677002,
+      "step": 1400
+    },
+    {
+      "epoch": 0.04015921932114406,
+      "grad_norm": 0.29545730352401733,
+      "learning_rate": 0.00019994573149384882,
+      "loss": 0.4935605049133301,
+      "step": 1410
+    },
+    {
+      "epoch": 0.040451498937746265,
+      "grad_norm": 0.20854443311691284,
+      "learning_rate": 0.00019994304559065168,
+      "loss": 0.33220815658569336,
+      "step": 1420
+    },
+    {
+      "epoch": 0.04074377855434848,
+      "grad_norm": 0.20468345284461975,
+      "learning_rate": 0.0001999402948354973,
+      "loss": 0.3795356035232544,
+      "step": 1430
+    },
+    {
+      "epoch": 0.04103605817095069,
+      "grad_norm": 0.29992666840553284,
+      "learning_rate": 0.00019993747923017065,
+      "loss": 0.43836030960083006,
+      "step": 1440
+    },
+    {
+      "epoch": 0.041328337787552905,
+      "grad_norm": 0.27834489941596985,
+      "learning_rate": 0.0001999345987764987,
+      "loss": 0.3854727029800415,
+      "step": 1450
+    },
+    {
+      "epoch": 0.04162061740415512,
+      "grad_norm": 0.19028784334659576,
+      "learning_rate": 0.00019993165347635062,
+      "loss": 0.48855161666870117,
+      "step": 1460
+    },
+    {
+      "epoch": 0.04191289702075733,
+      "grad_norm": 0.2719208002090454,
+      "learning_rate": 0.00019992864333163754,
+      "loss": 0.34480597972869875,
+      "step": 1470
+    },
+    {
+      "epoch": 0.042205176637359544,
+      "grad_norm": 0.2201714962720871,
+      "learning_rate": 0.0001999255683443127,
+      "loss": 0.45578484535217284,
+      "step": 1480
+    },
+    {
+      "epoch": 0.04249745625396176,
+      "grad_norm": 0.2917408049106598,
+      "learning_rate": 0.00019992242851637145,
+      "loss": 0.45635452270507815,
+      "step": 1490
+    },
+    {
+      "epoch": 0.04278973587056397,
+      "grad_norm": 0.20707593858242035,
+      "learning_rate": 0.00019991922384985115,
+      "loss": 0.4358846187591553,
+      "step": 1500
+    },
+    {
+      "epoch": 0.043082015487166184,
+      "grad_norm": 0.2693732976913452,
+      "learning_rate": 0.00019991595434683132,
+      "loss": 0.393514084815979,
+      "step": 1510
+    },
+    {
+      "epoch": 0.0433742951037684,
+      "grad_norm": 0.192472904920578,
+      "learning_rate": 0.0001999126200094335,
+      "loss": 0.36677262783050535,
+      "step": 1520
+    },
+    {
+      "epoch": 0.04366657472037061,
+      "grad_norm": 0.1903146505355835,
+      "learning_rate": 0.00019990922083982127,
+      "loss": 0.3809571504592896,
+      "step": 1530
+    },
+    {
+      "epoch": 0.04395885433697282,
+      "grad_norm": 0.18778850138187408,
+      "learning_rate": 0.00019990575684020035,
+      "loss": 0.3991628885269165,
+      "step": 1540
+    },
+    {
+      "epoch": 0.044251133953575036,
+      "grad_norm": 0.17295020818710327,
+      "learning_rate": 0.00019990222801281844,
+      "loss": 0.34786784648895264,
+      "step": 1550
+    },
+    {
+      "epoch": 0.04454341357017725,
+      "grad_norm": 0.21790063381195068,
+      "learning_rate": 0.00019989863435996544,
+      "loss": 0.4168230533599854,
+      "step": 1560
+    },
+    {
+      "epoch": 0.04483569318677946,
+      "grad_norm": 0.1902916580438614,
+      "learning_rate": 0.00019989497588397318,
+      "loss": 0.3928706169128418,
+      "step": 1570
+    },
+    {
+      "epoch": 0.045127972803381676,
+      "grad_norm": 0.21699456870555878,
+      "learning_rate": 0.0001998912525872156,
+      "loss": 0.27401630878448485,
+      "step": 1580
+    },
+    {
+      "epoch": 0.04542025241998389,
+      "grad_norm": 0.2811727821826935,
+      "learning_rate": 0.00019988746447210872,
+      "loss": 0.37927000522613524,
+      "step": 1590
+    },
+    {
+      "epoch": 0.0457125320365861,
+      "grad_norm": 0.2877182364463806,
+      "learning_rate": 0.0001998836115411106,
+      "loss": 0.37084925174713135,
+      "step": 1600
+    },
+    {
+      "epoch": 0.046004811653188316,
+      "grad_norm": 0.30798202753067017,
+      "learning_rate": 0.00019987969379672138,
+      "loss": 0.3814183950424194,
+      "step": 1610
+    },
+    {
+      "epoch": 0.04629709126979053,
+      "grad_norm": 0.23142924904823303,
+      "learning_rate": 0.00019987571124148326,
+      "loss": 0.4828189849853516,
+      "step": 1620
+    },
+    {
+      "epoch": 0.04658937088639274,
+      "grad_norm": 0.26372772455215454,
+      "learning_rate": 0.00019987166387798043,
+      "loss": 0.40070490837097167,
+      "step": 1630
+    },
+    {
+      "epoch": 0.046881650502994955,
+      "grad_norm": 0.20170119404792786,
+      "learning_rate": 0.00019986755170883918,
+      "loss": 0.4609227657318115,
+      "step": 1640
+    },
+    {
+      "epoch": 0.04717393011959717,
+      "grad_norm": 0.22828887403011322,
+      "learning_rate": 0.0001998633747367279,
+      "loss": 0.3876612186431885,
+      "step": 1650
+    },
+    {
+      "epoch": 0.04746620973619938,
+      "grad_norm": 0.28497815132141113,
+      "learning_rate": 0.00019985913296435693,
+      "loss": 0.4488811016082764,
+      "step": 1660
+    },
+    {
+      "epoch": 0.047758489352801595,
+      "grad_norm": 0.2250206023454666,
+      "learning_rate": 0.00019985482639447874,
+      "loss": 0.3711233615875244,
+      "step": 1670
+    },
+    {
+      "epoch": 0.0480507689694038,
+      "grad_norm": 0.2564453184604645,
+      "learning_rate": 0.00019985045502988785,
+      "loss": 0.4409325122833252,
+      "step": 1680
+    },
+    {
+      "epoch": 0.048343048586006014,
+      "grad_norm": 0.22390565276145935,
+      "learning_rate": 0.00019984601887342073,
+      "loss": 0.3880199432373047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.04863532820260823,
+      "grad_norm": 0.18111835420131683,
+      "learning_rate": 0.00019984151792795595,
+      "loss": 0.3191307783126831,
+      "step": 1700
+    },
+    {
+      "epoch": 0.04892760781921044,
+      "grad_norm": 0.27317941188812256,
+      "learning_rate": 0.00019983695219641417,
+      "loss": 0.36649317741394044,
+      "step": 1710
+    },
+    {
+      "epoch": 0.049219887435812654,
+      "grad_norm": 0.23256099224090576,
+      "learning_rate": 0.000199832321681758,
+      "loss": 0.4021451950073242,
+      "step": 1720
+    },
+    {
+      "epoch": 0.04951216705241487,
+      "grad_norm": 0.20527933537960052,
+      "learning_rate": 0.00019982762638699218,
+      "loss": 0.36731953620910646,
+      "step": 1730
+    },
+    {
+      "epoch": 0.04980444666901708,
+      "grad_norm": 0.2149372100830078,
+      "learning_rate": 0.00019982286631516343,
+      "loss": 0.38255355358123777,
+      "step": 1740
+    },
+    {
+      "epoch": 0.05009672628561929,
+      "grad_norm": 0.1913089156150818,
+      "learning_rate": 0.00019981804146936046,
+      "loss": 0.4117907524108887,
+      "step": 1750
+    },
+    {
+      "epoch": 0.050389005902221506,
+      "grad_norm": 0.2972666621208191,
+      "learning_rate": 0.0001998131518527141,
+      "loss": 0.39761054515838623,
+      "step": 1760
+    },
+    {
+      "epoch": 0.05068128551882372,
+      "grad_norm": 0.21348360180854797,
+      "learning_rate": 0.00019980819746839715,
+      "loss": 0.4208479404449463,
+      "step": 1770
+    },
+    {
+      "epoch": 0.05097356513542593,
+      "grad_norm": 0.21910355985164642,
+      "learning_rate": 0.00019980317831962447,
+      "loss": 0.45781354904174804,
+      "step": 1780
+    },
+    {
+      "epoch": 0.051265844752028146,
+      "grad_norm": 0.29217293858528137,
+      "learning_rate": 0.00019979809440965292,
+      "loss": 0.392667555809021,
+      "step": 1790
+    },
+    {
+      "epoch": 0.05155812436863036,
+      "grad_norm": 0.2685600221157074,
+      "learning_rate": 0.0001997929457417814,
+      "loss": 0.3381932020187378,
+      "step": 1800
+    },
+    {
+      "epoch": 0.05185040398523257,
+      "grad_norm": 0.208404079079628,
+      "learning_rate": 0.00019978773231935085,
+      "loss": 0.3530620574951172,
+      "step": 1810
+    },
+    {
+      "epoch": 0.052142683601834786,
+      "grad_norm": 0.23994538187980652,
+      "learning_rate": 0.00019978245414574417,
+      "loss": 0.38266212940216066,
+      "step": 1820
+    },
+    {
+      "epoch": 0.052434963218437,
+      "grad_norm": 0.3314270079135895,
+      "learning_rate": 0.0001997771112243863,
+      "loss": 0.37249245643615725,
+      "step": 1830
+    },
+    {
+      "epoch": 0.05272724283503921,
+      "grad_norm": 0.3160709738731384,
+      "learning_rate": 0.0001997717035587442,
+      "loss": 0.4115762233734131,
+      "step": 1840
+    },
+    {
+      "epoch": 0.053019522451641425,
+      "grad_norm": 0.20398829877376556,
+      "learning_rate": 0.00019976623115232692,
+      "loss": 0.4115797996520996,
+      "step": 1850
+    },
+    {
+      "epoch": 0.05331180206824364,
+      "grad_norm": 0.24112626910209656,
+      "learning_rate": 0.00019976069400868534,
+      "loss": 0.3800527811050415,
+      "step": 1860
+    },
+    {
+      "epoch": 0.05360408168484585,
+      "grad_norm": 0.3240782618522644,
+      "learning_rate": 0.00019975509213141255,
+      "loss": 0.4142290115356445,
+      "step": 1870
+    },
+    {
+      "epoch": 0.053896361301448065,
+      "grad_norm": 0.27430611848831177,
+      "learning_rate": 0.0001997494255241435,
+      "loss": 0.42593750953674314,
+      "step": 1880
+    },
+    {
+      "epoch": 0.05418864091805028,
+      "grad_norm": 0.2675989270210266,
+      "learning_rate": 0.00019974369419055514,
+      "loss": 0.35791664123535155,
+      "step": 1890
+    },
+    {
+      "epoch": 0.05448092053465249,
+      "grad_norm": 0.217862069606781,
+      "learning_rate": 0.00019973789813436656,
+      "loss": 0.42203755378723146,
+      "step": 1900
+    },
+    {
+      "epoch": 0.054773200151254704,
+      "grad_norm": 0.20300687849521637,
+      "learning_rate": 0.00019973203735933873,
+      "loss": 0.3735295534133911,
+      "step": 1910
+    },
+    {
+      "epoch": 0.05506547976785692,
+      "grad_norm": 0.24305196106433868,
+      "learning_rate": 0.0001997261118692746,
+      "loss": 0.3854319334030151,
+      "step": 1920
+    },
+    {
+      "epoch": 0.05535775938445913,
+      "grad_norm": 0.17744389176368713,
+      "learning_rate": 0.0001997201216680192,
+      "loss": 0.3821631908416748,
+      "step": 1930
+    },
+    {
+      "epoch": 0.055650039001061344,
+      "grad_norm": 0.28994235396385193,
+      "learning_rate": 0.0001997140667594595,
+      "loss": 0.36383843421936035,
+      "step": 1940
+    },
+    {
+      "epoch": 0.05594231861766355,
+      "grad_norm": 0.21803227066993713,
+      "learning_rate": 0.00019970794714752445,
+      "loss": 0.4005745410919189,
+      "step": 1950
+    },
+    {
+      "epoch": 0.05623459823426576,
+      "grad_norm": 0.22061172127723694,
+      "learning_rate": 0.00019970176283618503,
+      "loss": 0.42282872200012206,
+      "step": 1960
+    },
+    {
+      "epoch": 0.056526877850867976,
+      "grad_norm": 0.20922382175922394,
+      "learning_rate": 0.00019969551382945414,
+      "loss": 0.34180996417999265,
+      "step": 1970
+    },
+    {
+      "epoch": 0.05681915746747019,
+      "grad_norm": 0.21188782155513763,
+      "learning_rate": 0.00019968920013138671,
+      "loss": 0.3581382751464844,
+      "step": 1980
+    },
+    {
+      "epoch": 0.0571114370840724,
+      "grad_norm": 0.19657376408576965,
+      "learning_rate": 0.00019968282174607962,
+      "loss": 0.35428762435913086,
+      "step": 1990
+    },
+    {
+      "epoch": 0.057403716700674616,
+      "grad_norm": 0.20557129383087158,
+      "learning_rate": 0.00019967637867767172,
+      "loss": 0.4382596969604492,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 40000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.13283302801408e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ab51bd599651344f26a67a1d940a2b6432da90051bdf388dcef2423ea1342d
+size 5329