Upload folder using huggingface_hub

.gitattributes

@@ -71,3 +71,4 @@ g2_4_plan_cm_oldcode_newcode/250M/tokenizer.json filter=lfs diff=lfs merge=lfs -
 g2_4_plan_cm_oldcode_newcode/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g2_4_plan_cm_oldcode_newcode/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g2_5_plan_newcode/250M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+g2_5_plan_newcode/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text

g2_5_plan_newcode/500M/README.md

@@ -0,0 +1,59 @@
+---
+library_name: transformers
+license: other
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: 500M
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# 500M
+
+This model is a fine-tuned version of [/lus/flare/projects/MultiModalLLM/model-weights/gemma_base](https://huggingface.co//lus/flare/projects/MultiModalLLM/model-weights/gemma_base) on the rv5_g2_5_plan_newcode and the instruct_replay_gemma datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 12
+- total_train_batch_size: 12
+- total_eval_batch_size: 96
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: warmup_stable_decay
+- lr_scheduler_warmup_steps: 178
+- training_steps: 5597
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.10.0
+- Pytorch 2.10.0a0+git449b176
+- Datasets 4.5.0
+- Tokenizers 0.22.2

g2_5_plan_newcode/500M/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.43000921942224957,
+    "total_flos": 2650292248117248.0,
+    "train_loss": 0.060991441818013754,
+    "train_runtime": 7300.1756,
+    "train_samples_per_second": 9.2,
+    "train_steps_per_second": 0.767
+}

g2_5_plan_newcode/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 %}

g2_5_plan_newcode/500M/config.json

@@ -0,0 +1,170 @@
+{
+  "architectures": [
+    "Gemma4UnifiedForConditionalGeneration"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "audio_embed_dim": 640,
+    "chunk_size_feed_forward": 0,
+    "dtype": "bfloat16",
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_unified_audio",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": 1,
+  "hidden_size": 3840,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4_unified",
+  "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,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "hidden_size_per_layer_input": 0,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "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"
+    ],
+    "max_position_embeddings": 262144,
+    "model_type": "gemma4_unified_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 16,
+    "num_experts": null,
+    "num_global_key_value_heads": 1,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "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,
+    "chunk_size_feed_forward": 0,
+    "dtype": "bfloat16",
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "mm_embed_dim": 3840,
+    "mm_posemb_size": 1120,
+    "model_type": "gemma4_unified_vision",
+    "num_soft_tokens": 280,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 3840,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06
+  }
+}

g2_5_plan_newcode/500M/generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    1
+  ],
+  "pad_token_id": 0,
+  "suppress_tokens": [
+    258883,
+    258882
+  ],
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.10.0"
+}

g2_5_plan_newcode/500M/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5144ec009ebf3ebfafd7823d1f26f16a938b95ae38e524d52049ab4a6590aea
+size 23919549408

g2_5_plan_newcode/500M/processor_config.json

@@ -0,0 +1,62 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "feature_extractor": {
+    "audio_samples_per_token": 640,
+    "feature_extractor_type": "Gemma4UnifiedAudioFeatureExtractor",
+    "feature_size": 640,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "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": "Gemma4UnifiedImageProcessor",
+    "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": "Gemma4UnifiedProcessor",
+  "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": "Gemma4UnifiedVideoProcessor"
+  }
+}

g2_5_plan_newcode/500M/tokenizer.json

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

g2_5_plan_newcode/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": "Gemma4UnifiedProcessor",
+  "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>"
+}

g2_5_plan_newcode/500M/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.43000921942224957,
+    "total_flos": 2650292248117248.0,
+    "train_loss": 0.060991441818013754,
+    "train_runtime": 7300.1756,
+    "train_samples_per_second": 9.2,
+    "train_steps_per_second": 0.767
+}

g2_5_plan_newcode/500M/trainer_log.jsonl

@@ -0,0 +1,52 @@
+{"current_steps": 5090, "total_steps": 5597, "loss": 0.6690911054611206, "lr": 1.9999810479633703e-05, "epoch": 0.39105716041794714, "percentage": 90.94, "elapsed_time": "0:00:32", "remaining_time": "0:00:03"}
+{"current_steps": 5100, "total_steps": 5597, "loss": 0.6685787200927734, "lr": 1.997707677020786e-05, "epoch": 0.3918254456054087, "percentage": 91.12, "elapsed_time": "0:02:55", "remaining_time": "0:00:17"}
+{"current_steps": 5110, "total_steps": 5597, "loss": 0.7027465343475342, "lr": 1.9916538196124637e-05, "epoch": 0.3925937307928703, "percentage": 91.3, "elapsed_time": "0:05:18", "remaining_time": "0:00:30"}
+{"current_steps": 5120, "total_steps": 5597, "loss": 0.6937995910644531, "lr": 1.9818425303863402e-05, "epoch": 0.3933620159803319, "percentage": 91.48, "elapsed_time": "0:07:41", "remaining_time": "0:00:42"}
+{"current_steps": 5130, "total_steps": 5597, "loss": 0.6941290855407715, "lr": 1.9683111732582887e-05, "epoch": 0.39413030116779346, "percentage": 91.66, "elapsed_time": "0:10:04", "remaining_time": "0:00:55"}
+{"current_steps": 5140, "total_steps": 5597, "loss": 0.6732465744018554, "lr": 1.951111279120706e-05, "epoch": 0.39489858635525504, "percentage": 91.83, "elapsed_time": "0:12:26", "remaining_time": "0:01:06"}
+{"current_steps": 5150, "total_steps": 5597, "loss": 0.6888145446777344, "lr": 1.9303083495996028e-05, "epoch": 0.3956668715427167, "percentage": 92.01, "elapsed_time": "0:14:49", "remaining_time": "0:01:17"}
+{"current_steps": 5160, "total_steps": 5597, "loss": 0.6734145641326904, "lr": 1.9059816076075482e-05, "epoch": 0.39643515673017826, "percentage": 92.19, "elapsed_time": "0:17:13", "remaining_time": "0:01:27"}
+{"current_steps": 5170, "total_steps": 5597, "loss": 0.6933045387268066, "lr": 1.8782236956424142e-05, "epoch": 0.39720344191763984, "percentage": 92.37, "elapsed_time": "0:19:36", "remaining_time": "0:01:37"}
+{"current_steps": 5180, "total_steps": 5597, "loss": 0.6687453746795654, "lr": 1.8471403229808897e-05, "epoch": 0.3979717271051014, "percentage": 92.55, "elapsed_time": "0:21:58", "remaining_time": "0:01:46"}
+{"current_steps": 5190, "total_steps": 5597, "loss": 0.6582549095153809, "lr": 1.8128498631103333e-05, "epoch": 0.398740012292563, "percentage": 92.73, "elapsed_time": "0:24:21", "remaining_time": "0:01:54"}
+{"current_steps": 5200, "total_steps": 5597, "loss": 0.6683650493621827, "lr": 1.7754829029320507e-05, "epoch": 0.3995082974800246, "percentage": 92.91, "elapsed_time": "0:26:44", "remaining_time": "0:02:02"}
+{"current_steps": 5210, "total_steps": 5597, "loss": 0.7031188488006592, "lr": 1.7351817454527473e-05, "epoch": 0.40027658266748617, "percentage": 93.09, "elapsed_time": "0:29:07", "remaining_time": "0:02:09"}
+{"current_steps": 5220, "total_steps": 5597, "loss": 0.6709388732910156, "lr": 1.6920998678580345e-05, "epoch": 0.40104486785494775, "percentage": 93.26, "elapsed_time": "0:31:29", "remaining_time": "0:02:16"}
+{"current_steps": 5230, "total_steps": 5597, "loss": 0.6938288688659668, "lr": 1.6464013370317854e-05, "epoch": 0.40181315304240933, "percentage": 93.44, "elapsed_time": "0:33:53", "remaining_time": "0:02:22"}
+{"current_steps": 5240, "total_steps": 5597, "loss": 0.6993258953094482, "lr": 1.5982601847471915e-05, "epoch": 0.4025814382298709, "percentage": 93.62, "elapsed_time": "0:36:16", "remaining_time": "0:02:28"}
+{"current_steps": 5250, "total_steps": 5597, "loss": 0.6870141506195069, "lr": 1.5478597449089553e-05, "epoch": 0.4033497234173325, "percentage": 93.8, "elapsed_time": "0:38:39", "remaining_time": "0:02:33"}
+{"current_steps": 5260, "total_steps": 5597, "loss": 0.6781243801116943, "lr": 1.4953919553705725e-05, "epoch": 0.4041180086047941, "percentage": 93.98, "elapsed_time": "0:41:01", "remaining_time": "0:02:37"}
+{"current_steps": 5270, "total_steps": 5597, "loss": 0.6663007736206055, "lr": 1.441056626985559e-05, "epoch": 0.40488629379225566, "percentage": 94.16, "elapsed_time": "0:43:24", "remaining_time": "0:02:41"}
+{"current_steps": 5280, "total_steps": 5597, "loss": 0.6912947654724121, "lr": 1.3850606826762668e-05, "epoch": 0.4056545789797173, "percentage": 94.34, "elapsed_time": "0:45:47", "remaining_time": "0:02:44"}
+{"current_steps": 5290, "total_steps": 5597, "loss": 0.6673799514770508, "lr": 1.3276173694181128e-05, "epoch": 0.4064228641671789, "percentage": 94.51, "elapsed_time": "0:48:10", "remaining_time": "0:02:47"}
+{"current_steps": 5300, "total_steps": 5597, "loss": 0.6723287105560303, "lr": 1.2689454461401822e-05, "epoch": 0.40719114935464046, "percentage": 94.69, "elapsed_time": "0:50:34", "remaining_time": "0:02:50"}
+{"current_steps": 5310, "total_steps": 5597, "loss": 0.6676998138427734, "lr": 1.2092683506348939e-05, "epoch": 0.40795943454210204, "percentage": 94.87, "elapsed_time": "0:52:56", "remaining_time": "0:02:51"}
+{"current_steps": 5320, "total_steps": 5597, "loss": 0.6732924461364747, "lr": 1.14881334864935e-05, "epoch": 0.4087277197295636, "percentage": 95.05, "elapsed_time": "0:55:19", "remaining_time": "0:02:52"}
+{"current_steps": 5330, "total_steps": 5597, "loss": 0.6952274322509766, "lr": 1.0878106683988481e-05, "epoch": 0.4094960049170252, "percentage": 95.23, "elapsed_time": "0:57:42", "remaining_time": "0:02:53"}
+{"current_steps": 5340, "total_steps": 5597, "loss": 0.661638593673706, "lr": 1.026492623798551e-05, "epoch": 0.4102642901044868, "percentage": 95.41, "elapsed_time": "1:00:05", "remaining_time": "0:02:53"}
+{"current_steps": 5350, "total_steps": 5597, "loss": 0.6591861724853516, "lr": 9.650927297522743e-06, "epoch": 0.41103257529194837, "percentage": 95.59, "elapsed_time": "1:02:28", "remaining_time": "0:02:53"}
+{"current_steps": 5360, "total_steps": 5597, "loss": 0.6714771270751954, "lr": 9.038448128676012e-06, "epoch": 0.41180086047940995, "percentage": 95.77, "elapsed_time": "1:04:50", "remaining_time": "0:02:52"}
+{"current_steps": 5370, "total_steps": 5597, "loss": 0.6702570915222168, "lr": 8.42982120983949e-06, "epoch": 0.41256914566687153, "percentage": 95.94, "elapsed_time": "1:07:14", "remaining_time": "0:02:50"}
+{"current_steps": 5380, "total_steps": 5597, "loss": 0.661563491821289, "lr": 7.827364349047303e-06, "epoch": 0.4133374308543331, "percentage": 96.12, "elapsed_time": "1:09:37", "remaining_time": "0:02:48"}
+{"current_steps": 5390, "total_steps": 5597, "loss": 0.6775993347167969, "lr": 7.233371857163706e-06, "epoch": 0.4141057160417947, "percentage": 96.3, "elapsed_time": "1:12:00", "remaining_time": "0:02:45"}
+{"current_steps": 5400, "total_steps": 5597, "loss": 0.6627745628356934, "lr": 6.650105810556492e-06, "epoch": 0.4148740012292563, "percentage": 96.48, "elapsed_time": "1:14:23", "remaining_time": "0:02:42"}
+{"current_steps": 5410, "total_steps": 5597, "loss": 0.6699105739593506, "lr": 6.079787436527681e-06, "epoch": 0.4156422864167179, "percentage": 96.66, "elapsed_time": "1:16:46", "remaining_time": "0:02:39"}
+{"current_steps": 5420, "total_steps": 5597, "loss": 0.6722631454467773, "lr": 5.524588654307961e-06, "epoch": 0.4164105716041795, "percentage": 96.84, "elapsed_time": "1:19:09", "remaining_time": "0:02:35"}
+{"current_steps": 5430, "total_steps": 5597, "loss": 0.6646710872650147, "lr": 4.986623803828985e-06, "epoch": 0.4171788567916411, "percentage": 97.02, "elapsed_time": "1:21:32", "remaining_time": "0:02:30"}
+{"current_steps": 5440, "total_steps": 5597, "loss": 0.6737457275390625, "lr": 4.467941593772423e-06, "epoch": 0.41794714197910265, "percentage": 97.19, "elapsed_time": "1:23:55", "remaining_time": "0:02:25"}
+{"current_steps": 5450, "total_steps": 5597, "loss": 0.6595948696136474, "lr": 3.9705172995597606e-06, "epoch": 0.41871542716656424, "percentage": 97.37, "elapsed_time": "1:26:18", "remaining_time": "0:02:19"}
+{"current_steps": 5460, "total_steps": 5597, "loss": 0.6535918712615967, "lr": 3.4962452409948346e-06, "epoch": 0.4194837123540258, "percentage": 97.55, "elapsed_time": "1:28:41", "remaining_time": "0:02:13"}
+{"current_steps": 5470, "total_steps": 5597, "loss": 0.6509208679199219, "lr": 3.046931568206211e-06, "epoch": 0.4202519975414874, "percentage": 97.73, "elapsed_time": "1:31:04", "remaining_time": "0:02:06"}
+{"current_steps": 5480, "total_steps": 5597, "loss": 0.6500594139099121, "lr": 2.624287383362404e-06, "epoch": 0.421020282728949, "percentage": 97.91, "elapsed_time": "1:33:27", "remaining_time": "0:01:59"}
+{"current_steps": 5490, "total_steps": 5597, "loss": 0.6601835250854492, "lr": 2.2299222243541845e-06, "epoch": 0.42178856791641056, "percentage": 98.09, "elapsed_time": "1:35:49", "remaining_time": "0:01:52"}
+{"current_steps": 5500, "total_steps": 5597, "loss": 0.6602890014648437, "lr": 1.8653379352598246e-06, "epoch": 0.42255685310387214, "percentage": 98.27, "elapsed_time": "1:38:12", "remaining_time": "0:01:43"}
+{"current_steps": 5510, "total_steps": 5597, "loss": 0.6565009117126465, "lr": 1.5319229469361075e-06, "epoch": 0.4233251382913337, "percentage": 98.45, "elapsed_time": "1:40:35", "remaining_time": "0:01:35"}
+{"current_steps": 5520, "total_steps": 5597, "loss": 0.6324792385101319, "lr": 1.2309469895160917e-06, "epoch": 0.4240934234787953, "percentage": 98.62, "elapsed_time": "1:42:59", "remaining_time": "0:01:26"}
+{"current_steps": 5530, "total_steps": 5597, "loss": 0.6723834991455078, "lr": 9.635562569497974e-07, "epoch": 0.4248617086662569, "percentage": 98.8, "elapsed_time": "1:45:22", "remaining_time": "0:01:16"}
+{"current_steps": 5540, "total_steps": 5597, "loss": 0.668683385848999, "lr": 7.307690420024867e-07, "epoch": 0.4256299938537185, "percentage": 98.98, "elapsed_time": "1:47:45", "remaining_time": "0:01:06"}
+{"current_steps": 5550, "total_steps": 5597, "loss": 0.676048469543457, "lr": 5.334718583335942e-07, "epoch": 0.4263982790411801, "percentage": 99.16, "elapsed_time": "1:50:07", "remaining_time": "0:00:55"}
+{"current_steps": 5560, "total_steps": 5597, "loss": 0.6339440822601319, "lr": 3.7241606442442763e-07, "epoch": 0.4271665642286417, "percentage": 99.34, "elapsed_time": "1:52:30", "remaining_time": "0:00:44"}
+{"current_steps": 5570, "total_steps": 5597, "loss": 0.6520829677581788, "lr": 2.482150022115879e-07, "epoch": 0.42793484941610327, "percentage": 99.52, "elapsed_time": "1:54:53", "remaining_time": "0:00:33"}
+{"current_steps": 5580, "total_steps": 5597, "loss": 0.6737591743469238, "lr": 1.6134166132293174e-07, "epoch": 0.42870313460356485, "percentage": 99.7, "elapsed_time": "1:57:16", "remaining_time": "0:00:21"}
+{"current_steps": 5590, "total_steps": 5597, "loss": 0.6571590423583984, "lr": 1.1212687781127357e-07, "epoch": 0.42947141979102643, "percentage": 99.87, "elapsed_time": "1:59:39", "remaining_time": "0:00:08"}
+{"current_steps": 5597, "total_steps": 5597, "epoch": 0.43000921942224957, "percentage": 100.0, "elapsed_time": "2:01:40", "remaining_time": "0:00:00"}

g2_5_plan_newcode/500M/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e481100af467a1ad0de733e04817c63bfb34f138672e47754b4abcf3c581962d
+size 8209