Upload folder using huggingface_hub

.gitattributes

@@ -51,3 +51,4 @@ g1_cleanup_code__edit/pre-anneal/500M/tokenizer.json filter=lfs diff=lfs merge=l
 g1_cleanup_code__edit/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g1_cleanup_code/pre-anneal/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g1_cleanup_code__edit/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+g1_jupyter_notebook/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text

g1_jupyter_notebook/500M/.launching

@@ -0,0 +1 @@
+8830938 2026-09-21 04:38:36 x4704c6s4b0n0 636->700

g1_jupyter_notebook/500M/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.4095962551199532,
+    "total_flos": 4821608300544000.0,
+    "train_loss": 0.039095867361341206,
+    "train_runtime": 2660.3321,
+    "train_samples_per_second": 25.26,
+    "train_steps_per_second": 0.263
+}

g1_jupyter_notebook/500M/chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '<eos>' }}{% endif %}{% endfor %}

g1_jupyter_notebook/500M/config.json

@@ -0,0 +1,178 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": null,
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": 1,
+  "hidden_size": 5376,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "pad_token_id": 0,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": true,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 5376,
+    "hidden_size_per_layer_input": 0,
+    "initializer_range": 0.02,
+    "intermediate_size": 21504,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 262144,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 32,
+    "num_experts": null,
+    "num_global_key_value_heads": 4,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 16,
+    "num_kv_shared_layers": 0,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 1024,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": "vision",
+    "use_cache": false,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.0",
+  "use_cache": false,
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 72,
+    "head_dim": 72,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "num_key_value_heads": 16,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": true,
+    "use_clipped_linears": false
+  },
+  "vision_soft_tokens_per_image": 280
+}

g1_jupyter_notebook/500M/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    1
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.10.0"
+}

g1_jupyter_notebook/500M/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2dfe1aa8ab4edb1328f829c1595c217abcce843636e1fdcb3ac0d034f8aa77
+size 49923154850

g1_jupyter_notebook/500M/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590d79026305a4a3acf7fb5e4f606aa5fe429e98688d31b3e9d988e64efe0da4
+size 12623183414

g1_jupyter_notebook/500M/processor_config.json

@@ -0,0 +1,75 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "Gemma4VideoProcessor"
+  }
+}

g1_jupyter_notebook/500M/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
+size 32170070

g1_jupyter_notebook/500M/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": true,
+  "local_files_only": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "processor_class": "Gemma4Processor",
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "split_special_tokens": false,
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

g1_jupyter_notebook/500M/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.4095962551199532,
+    "total_flos": 4821608300544000.0,
+    "train_loss": 0.039095867361341206,
+    "train_runtime": 2660.3321,
+    "train_samples_per_second": 25.26,
+    "train_steps_per_second": 0.263
+}

g1_jupyter_notebook/500M/trainer_log.jsonl

@@ -0,0 +1,8 @@
+{"current_steps": 640, "total_steps": 700, "loss": 0.44627851247787476, "lr": 1.9892306274149575e-05, "epoch": 0.37448800468110005, "percentage": 91.43, "elapsed_time": "0:02:53", "remaining_time": "0:00:16"}
+{"current_steps": 650, "total_steps": 700, "loss": 0.42882070541381834, "lr": 1.8041914938232418e-05, "epoch": 0.38033937975424226, "percentage": 92.86, "elapsed_time": "0:09:37", "remaining_time": "0:00:44"}
+{"current_steps": 660, "total_steps": 700, "loss": 0.434341287612915, "lr": 1.430417317963131e-05, "epoch": 0.3861907548273844, "percentage": 94.29, "elapsed_time": "0:16:21", "remaining_time": "0:00:59"}
+{"current_steps": 670, "total_steps": 700, "loss": 0.4225472450256348, "lr": 9.561776640442192e-06, "epoch": 0.3920421299005266, "percentage": 95.71, "elapsed_time": "0:23:04", "remaining_time": "0:01:01"}
+{"current_steps": 680, "total_steps": 700, "loss": 0.4186511993408203, "lr": 4.934677695277445e-06, "epoch": 0.3978935049736688, "percentage": 97.14, "elapsed_time": "0:29:47", "remaining_time": "0:00:52"}
+{"current_steps": 690, "total_steps": 700, "loss": 0.4262665271759033, "lr": 1.5156003304972938e-06, "epoch": 0.403744880046811, "percentage": 98.57, "elapsed_time": "0:36:31", "remaining_time": "0:00:31"}
+{"current_steps": 700, "total_steps": 700, "loss": 0.42757234573364256, "lr": 1.1198521075853458e-07, "epoch": 0.4095962551199532, "percentage": 100.0, "elapsed_time": "0:43:16", "remaining_time": "0:00:00"}
+{"current_steps": 700, "total_steps": 700, "epoch": 0.4095962551199532, "percentage": 100.0, "elapsed_time": "0:44:20", "remaining_time": "0:00:00"}

g1_jupyter_notebook/500M/trainer_state.json

@@ -0,0 +1,533 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4095962551199532,
+  "eval_steps": 500,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005851375073142188,
+      "grad_norm": 722.3047506884299,
+      "learning_rate": 8.240909090909092e-06,
+      "loss": 0.815431022644043,
+      "step": 10
+    },
+    {
+      "epoch": 0.011702750146284377,
+      "grad_norm": 145.4011608176478,
+      "learning_rate": 1.728636363636364e-05,
+      "loss": 0.4873072624206543,
+      "step": 20
+    },
+    {
+      "epoch": 0.017554125219426564,
+      "grad_norm": 34.7425918176051,
+      "learning_rate": 2e-05,
+      "loss": 0.47413363456726076,
+      "step": 30
+    },
+    {
+      "epoch": 0.023405500292568753,
+      "grad_norm": 627.6113988831149,
+      "learning_rate": 2e-05,
+      "loss": 0.5241857051849366,
+      "step": 40
+    },
+    {
+      "epoch": 0.029256875365710942,
+      "grad_norm": 9.333282061786075,
+      "learning_rate": 2e-05,
+      "loss": 0.5261882781982422,
+      "step": 50
+    },
+    {
+      "epoch": 0.03510825043885313,
+      "grad_norm": 10.258378288452999,
+      "learning_rate": 2e-05,
+      "loss": 0.5006448745727539,
+      "step": 60
+    },
+    {
+      "epoch": 0.04095962551199532,
+      "grad_norm": 13.916482807305034,
+      "learning_rate": 2e-05,
+      "loss": 0.48270502090454104,
+      "step": 70
+    },
+    {
+      "epoch": 0.046811000585137506,
+      "grad_norm": 7.448753281691261,
+      "learning_rate": 2e-05,
+      "loss": 0.5237825393676758,
+      "step": 80
+    },
+    {
+      "epoch": 0.0526623756582797,
+      "grad_norm": 13.959049034574702,
+      "learning_rate": 2e-05,
+      "loss": 0.4954239845275879,
+      "step": 90
+    },
+    {
+      "epoch": 0.058513750731421885,
+      "grad_norm": 6.419507595225647,
+      "learning_rate": 2e-05,
+      "loss": 0.47747349739074707,
+      "step": 100
+    },
+    {
+      "epoch": 0.06436512580456408,
+      "grad_norm": 10.333527235184453,
+      "learning_rate": 2e-05,
+      "loss": 0.46398019790649414,
+      "step": 110
+    },
+    {
+      "epoch": 0.07021650087770626,
+      "grad_norm": 4.7743767265565715,
+      "learning_rate": 2e-05,
+      "loss": 0.45823111534118655,
+      "step": 120
+    },
+    {
+      "epoch": 0.07606787595084845,
+      "grad_norm": 35.948840970822566,
+      "learning_rate": 2e-05,
+      "loss": 0.47070822715759275,
+      "step": 130
+    },
+    {
+      "epoch": 0.08191925102399064,
+      "grad_norm": 14.441710239001834,
+      "learning_rate": 2e-05,
+      "loss": 0.4741715908050537,
+      "step": 140
+    },
+    {
+      "epoch": 0.08777062609713282,
+      "grad_norm": 19.748869955541718,
+      "learning_rate": 2e-05,
+      "loss": 0.4672824859619141,
+      "step": 150
+    },
+    {
+      "epoch": 0.09362200117027501,
+      "grad_norm": 5.376095253416546,
+      "learning_rate": 2e-05,
+      "loss": 0.4619298458099365,
+      "step": 160
+    },
+    {
+      "epoch": 0.0994733762434172,
+      "grad_norm": 3.5447746494342622,
+      "learning_rate": 2e-05,
+      "loss": 0.4703338146209717,
+      "step": 170
+    },
+    {
+      "epoch": 0.1053247513165594,
+      "grad_norm": 22.237367801418927,
+      "learning_rate": 2e-05,
+      "loss": 0.4801036834716797,
+      "step": 180
+    },
+    {
+      "epoch": 0.11117612638970158,
+      "grad_norm": 10.469269003466454,
+      "learning_rate": 2e-05,
+      "loss": 0.4776778221130371,
+      "step": 190
+    },
+    {
+      "epoch": 0.11702750146284377,
+      "grad_norm": 69.00024674808894,
+      "learning_rate": 2e-05,
+      "loss": 0.4732304573059082,
+      "step": 200
+    },
+    {
+      "epoch": 0.12287887653598596,
+      "grad_norm": 4.008167284876325,
+      "learning_rate": 2e-05,
+      "loss": 0.4633647441864014,
+      "step": 210
+    },
+    {
+      "epoch": 0.12873025160912815,
+      "grad_norm": 4.12037159490575,
+      "learning_rate": 2e-05,
+      "loss": 0.4576042652130127,
+      "step": 220
+    },
+    {
+      "epoch": 0.13458162668227033,
+      "grad_norm": 10.02371679111215,
+      "learning_rate": 2e-05,
+      "loss": 0.4506582260131836,
+      "step": 230
+    },
+    {
+      "epoch": 0.1404330017554125,
+      "grad_norm": 145.26436740003052,
+      "learning_rate": 2e-05,
+      "loss": 0.4545659065246582,
+      "step": 240
+    },
+    {
+      "epoch": 0.14628437682855472,
+      "grad_norm": 1.1636166760298137,
+      "learning_rate": 2e-05,
+      "loss": 0.46163148880004884,
+      "step": 250
+    },
+    {
+      "epoch": 0.1521357519016969,
+      "grad_norm": 2.4689908414338637,
+      "learning_rate": 2e-05,
+      "loss": 0.4646605491638184,
+      "step": 260
+    },
+    {
+      "epoch": 0.15798712697483908,
+      "grad_norm": 7.311694985604752,
+      "learning_rate": 2e-05,
+      "loss": 0.4644497871398926,
+      "step": 270
+    },
+    {
+      "epoch": 0.16383850204798128,
+      "grad_norm": 120.76111223511168,
+      "learning_rate": 2e-05,
+      "loss": 0.45812482833862306,
+      "step": 280
+    },
+    {
+      "epoch": 0.16968987712112346,
+      "grad_norm": 7.432860843908352,
+      "learning_rate": 2e-05,
+      "loss": 0.4690185546875,
+      "step": 290
+    },
+    {
+      "epoch": 0.17554125219426564,
+      "grad_norm": 3.5063397185454206,
+      "learning_rate": 2e-05,
+      "loss": 0.47104778289794924,
+      "step": 300
+    },
+    {
+      "epoch": 0.18139262726740785,
+      "grad_norm": 1.7161368671120483,
+      "learning_rate": 2e-05,
+      "loss": 0.47832560539245605,
+      "step": 310
+    },
+    {
+      "epoch": 0.18724400234055003,
+      "grad_norm": 2.7995694136387734,
+      "learning_rate": 2e-05,
+      "loss": 0.4722126007080078,
+      "step": 320
+    },
+    {
+      "epoch": 0.1930953774136922,
+      "grad_norm": 10.80819931602094,
+      "learning_rate": 2e-05,
+      "loss": 0.46016683578491213,
+      "step": 330
+    },
+    {
+      "epoch": 0.1989467524868344,
+      "grad_norm": 1.364105506206788,
+      "learning_rate": 2e-05,
+      "loss": 0.4547887802124023,
+      "step": 340
+    },
+    {
+      "epoch": 0.2047981275599766,
+      "grad_norm": 1.657602624234001,
+      "learning_rate": 2e-05,
+      "loss": 0.4447385311126709,
+      "step": 350
+    },
+    {
+      "epoch": 0.2106495026331188,
+      "grad_norm": 6.984782890612126,
+      "learning_rate": 2e-05,
+      "loss": 0.4384812831878662,
+      "step": 360
+    },
+    {
+      "epoch": 0.21650087770626097,
+      "grad_norm": 5.233046035168877,
+      "learning_rate": 2e-05,
+      "loss": 0.44702463150024413,
+      "step": 370
+    },
+    {
+      "epoch": 0.22235225277940315,
+      "grad_norm": 1.209529576166064,
+      "learning_rate": 2e-05,
+      "loss": 0.44935851626926,
+      "step": 380
+    },
+    {
+      "epoch": 0.22820362785254536,
+      "grad_norm": 10.9279502257516,
+      "learning_rate": 2e-05,
+      "loss": 0.44748721122741697,
+      "step": 390
+    },
+    {
+      "epoch": 0.23405500292568754,
+      "grad_norm": 7.470557475551403,
+      "learning_rate": 2e-05,
+      "loss": 0.45525145530700684,
+      "step": 400
+    },
+    {
+      "epoch": 0.23990637799882972,
+      "grad_norm": 2.059197815167869,
+      "learning_rate": 2e-05,
+      "loss": 0.4523183822631836,
+      "step": 410
+    },
+    {
+      "epoch": 0.24575775307197192,
+      "grad_norm": 8.618618633793242,
+      "learning_rate": 2e-05,
+      "loss": 0.45379066467285156,
+      "step": 420
+    },
+    {
+      "epoch": 0.2516091281451141,
+      "grad_norm": 2.805939217260095,
+      "learning_rate": 2e-05,
+      "loss": 0.4506677786509196,
+      "step": 430
+    },
+    {
+      "epoch": 0.2574605032182563,
+      "grad_norm": 2.9649350106279253,
+      "learning_rate": 2e-05,
+      "loss": 0.45397562980651857,
+      "step": 440
+    },
+    {
+      "epoch": 0.26331187829139846,
+      "grad_norm": 1.2882383449845194,
+      "learning_rate": 2e-05,
+      "loss": 0.4674218654632568,
+      "step": 450
+    },
+    {
+      "epoch": 0.26916325336454067,
+      "grad_norm": 2.498448492094687,
+      "learning_rate": 2e-05,
+      "loss": 0.4801971912384033,
+      "step": 460
+    },
+    {
+      "epoch": 0.2750146284376829,
+      "grad_norm": 4.1544402071454645,
+      "learning_rate": 2e-05,
+      "loss": 0.45485677719116213,
+      "step": 470
+    },
+    {
+      "epoch": 0.280866003510825,
+      "grad_norm": 12.647271506037224,
+      "learning_rate": 2e-05,
+      "loss": 0.45079994201660156,
+      "step": 480
+    },
+    {
+      "epoch": 0.28671737858396723,
+      "grad_norm": 4.910636891464567,
+      "learning_rate": 2e-05,
+      "loss": 0.44969873428344725,
+      "step": 490
+    },
+    {
+      "epoch": 0.29256875365710944,
+      "grad_norm": 1.8609845979795288,
+      "learning_rate": 2e-05,
+      "loss": 0.43883328437805175,
+      "step": 500
+    },
+    {
+      "epoch": 0.2984201287302516,
+      "grad_norm": 1.7542751511057226,
+      "learning_rate": 2e-05,
+      "loss": 0.4447303295135498,
+      "step": 510
+    },
+    {
+      "epoch": 0.3042715038033938,
+      "grad_norm": 1.0135283772570185,
+      "learning_rate": 2e-05,
+      "loss": 0.4480525016784668,
+      "step": 520
+    },
+    {
+      "epoch": 0.310122878876536,
+      "grad_norm": 1.0019226878150138,
+      "learning_rate": 2e-05,
+      "loss": 0.4496911525726318,
+      "step": 530
+    },
+    {
+      "epoch": 0.31597425394967815,
+      "grad_norm": 0.8128881881211669,
+      "learning_rate": 2e-05,
+      "loss": 0.4464526653289795,
+      "step": 540
+    },
+    {
+      "epoch": 0.32182562902282036,
+      "grad_norm": 2.2177233161225653,
+      "learning_rate": 2e-05,
+      "loss": 0.43948893547058104,
+      "step": 550
+    },
+    {
+      "epoch": 0.32767700409596257,
+      "grad_norm": 10.900543579060534,
+      "learning_rate": 2e-05,
+      "loss": 0.44472250938415525,
+      "step": 560
+    },
+    {
+      "epoch": 0.3335283791691047,
+      "grad_norm": 2.1356515208509332,
+      "learning_rate": 2e-05,
+      "loss": 0.43558540344238283,
+      "step": 570
+    },
+    {
+      "epoch": 0.3393797542422469,
+      "grad_norm": 1.3374263807054463,
+      "learning_rate": 2e-05,
+      "loss": 0.44030489921569826,
+      "step": 580
+    },
+    {
+      "epoch": 0.34523112931538913,
+      "grad_norm": 25.135467104722675,
+      "learning_rate": 2e-05,
+      "loss": 0.4326209545135498,
+      "step": 590
+    },
+    {
+      "epoch": 0.3510825043885313,
+      "grad_norm": 2.1580634731529167,
+      "learning_rate": 2e-05,
+      "loss": 0.4280872344970703,
+      "step": 600
+    },
+    {
+      "epoch": 0.3569338794616735,
+      "grad_norm": 4.127553728499885,
+      "learning_rate": 2e-05,
+      "loss": 0.42243247032165526,
+      "step": 610
+    },
+    {
+      "epoch": 0.3627852545348157,
+      "grad_norm": 14.048209030626133,
+      "learning_rate": 2e-05,
+      "loss": 0.4255032539367676,
+      "step": 620
+    },
+    {
+      "epoch": 0.36863662960795784,
+      "grad_norm": 4.178781966521355,
+      "learning_rate": 2e-05,
+      "loss": 0.43591742515563964,
+      "step": 630
+    },
+    {
+      "epoch": 0.37448800468110005,
+      "grad_norm": 1.994470465668841,
+      "learning_rate": 1.9892306274149575e-05,
+      "loss": 0.44627851247787476,
+      "step": 640
+    },
+    {
+      "epoch": 0.38033937975424226,
+      "grad_norm": 13.282126521384157,
+      "learning_rate": 1.8041914938232418e-05,
+      "loss": 0.42882070541381834,
+      "step": 650
+    },
+    {
+      "epoch": 0.3861907548273844,
+      "grad_norm": 2.3650714056808746,
+      "learning_rate": 1.430417317963131e-05,
+      "loss": 0.434341287612915,
+      "step": 660
+    },
+    {
+      "epoch": 0.3920421299005266,
+      "grad_norm": 3.8698654531415233,
+      "learning_rate": 9.561776640442192e-06,
+      "loss": 0.4225472450256348,
+      "step": 670
+    },
+    {
+      "epoch": 0.3978935049736688,
+      "grad_norm": 4.245759234905024,
+      "learning_rate": 4.934677695277445e-06,
+      "loss": 0.4186511993408203,
+      "step": 680
+    },
+    {
+      "epoch": 0.403744880046811,
+      "grad_norm": 4.249533551125241,
+      "learning_rate": 1.5156003304972938e-06,
+      "loss": 0.4262665271759033,
+      "step": 690
+    },
+    {
+      "epoch": 0.4095962551199532,
+      "grad_norm": 6.489441960690249,
+      "learning_rate": 1.1198521075853458e-07,
+      "loss": 0.42757234573364256,
+      "step": 700
+    },
+    {
+      "epoch": 0.4095962551199532,
+      "step": 700,
+      "total_flos": 4821608300544000.0,
+      "train_loss": 0.039095867361341206,
+      "train_runtime": 2660.3321,
+      "train_samples_per_second": 25.26,
+      "train_steps_per_second": 0.263
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4821608300544000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

g1_jupyter_notebook/500M/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b659b8b4abe79b3d34743a66e8c4a52dfa23907e83a69df2e85878a17cc4d0
+size 8209