Upload folder using huggingface_hub

.gitattributes

@@ -59,3 +59,4 @@ g2_1_oldcode_cm_newcode/250M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g2_1_oldcode_cm_newcode/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g2_1_oldcode_cm_newcode/1000M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 g2_1_oldcode_cm_newcode__edit/250M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+g2_1_oldcode_cm_newcode__edit/500M/tokenizer.json filter=lfs diff=lfs merge=lfs -text

g2_1_oldcode_cm_newcode__edit/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_1_oldcode_cm_newcode, the instruct_replay_gemma and the edit_instruct_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_1_oldcode_cm_newcode__edit/500M/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.3726364846870839,
+    "total_flos": 2650292248117248.0,
+    "train_loss": 0.0447272484017543,
+    "train_runtime": 7385.9476,
+    "train_samples_per_second": 9.093,
+    "train_steps_per_second": 0.758
+}

g2_1_oldcode_cm_newcode__edit/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_1_oldcode_cm_newcode__edit/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_1_oldcode_cm_newcode__edit/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_1_oldcode_cm_newcode__edit/500M/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c5169335344cd62284f3a084ade586429ba41840c3f8d13d085c55afa5fe07
+size 23919549408

g2_1_oldcode_cm_newcode__edit/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_1_oldcode_cm_newcode__edit/500M/tokenizer.json

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

g2_1_oldcode_cm_newcode__edit/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_1_oldcode_cm_newcode__edit/500M/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.3726364846870839,
+    "total_flos": 2650292248117248.0,
+    "train_loss": 0.0447272484017543,
+    "train_runtime": 7385.9476,
+    "train_samples_per_second": 9.093,
+    "train_steps_per_second": 0.758
+}

g2_1_oldcode_cm_newcode__edit/500M/trainer_log.jsonl

@@ -0,0 +1,52 @@
+{"current_steps": 5090, "total_steps": 5597, "loss": 0.4408143162727356, "lr": 1.9999810479633703e-05, "epoch": 0.3388814913448735, "percentage": 90.94, "elapsed_time": "0:00:32", "remaining_time": "0:00:03"}
+{"current_steps": 5100, "total_steps": 5597, "loss": 0.5461221694946289, "lr": 1.997707677020786e-05, "epoch": 0.3395472703062583, "percentage": 91.12, "elapsed_time": "0:02:56", "remaining_time": "0:00:17"}
+{"current_steps": 5110, "total_steps": 5597, "loss": 0.5149670600891113, "lr": 1.9916538196124637e-05, "epoch": 0.3402130492676431, "percentage": 91.3, "elapsed_time": "0:05:21", "remaining_time": "0:00:30"}
+{"current_steps": 5120, "total_steps": 5597, "loss": 0.4913291931152344, "lr": 1.9818425303863402e-05, "epoch": 0.340878828229028, "percentage": 91.48, "elapsed_time": "0:07:46", "remaining_time": "0:00:43"}
+{"current_steps": 5130, "total_steps": 5597, "loss": 0.4919825553894043, "lr": 1.9683111732582887e-05, "epoch": 0.3415446071904128, "percentage": 91.66, "elapsed_time": "0:10:10", "remaining_time": "0:00:55"}
+{"current_steps": 5140, "total_steps": 5597, "loss": 0.5190771102905274, "lr": 1.951111279120706e-05, "epoch": 0.3422103861517976, "percentage": 91.83, "elapsed_time": "0:12:34", "remaining_time": "0:01:07"}
+{"current_steps": 5150, "total_steps": 5597, "loss": 0.48006448745727537, "lr": 1.9303083495996028e-05, "epoch": 0.3428761651131824, "percentage": 92.01, "elapsed_time": "0:14:59", "remaining_time": "0:01:18"}
+{"current_steps": 5160, "total_steps": 5597, "loss": 0.4808450698852539, "lr": 1.9059816076075482e-05, "epoch": 0.34354194407456723, "percentage": 92.19, "elapsed_time": "0:17:24", "remaining_time": "0:01:28"}
+{"current_steps": 5170, "total_steps": 5597, "loss": 0.47633891105651854, "lr": 1.8782236956424142e-05, "epoch": 0.34420772303595204, "percentage": 92.37, "elapsed_time": "0:19:49", "remaining_time": "0:01:38"}
+{"current_steps": 5180, "total_steps": 5597, "loss": 0.5200161457061767, "lr": 1.8471403229808897e-05, "epoch": 0.3448735019973369, "percentage": 92.55, "elapsed_time": "0:22:14", "remaining_time": "0:01:47"}
+{"current_steps": 5190, "total_steps": 5597, "loss": 0.4952213764190674, "lr": 1.8128498631103333e-05, "epoch": 0.3455392809587217, "percentage": 92.73, "elapsed_time": "0:24:38", "remaining_time": "0:01:55"}
+{"current_steps": 5200, "total_steps": 5597, "loss": 0.4824930191040039, "lr": 1.7754829029320507e-05, "epoch": 0.34620505992010653, "percentage": 92.91, "elapsed_time": "0:27:02", "remaining_time": "0:02:03"}
+{"current_steps": 5210, "total_steps": 5597, "loss": 0.5099661827087403, "lr": 1.7351817454527473e-05, "epoch": 0.34687083888149134, "percentage": 93.09, "elapsed_time": "0:29:27", "remaining_time": "0:02:11"}
+{"current_steps": 5220, "total_steps": 5597, "loss": 0.5001060485839843, "lr": 1.6920998678580345e-05, "epoch": 0.34753661784287615, "percentage": 93.26, "elapsed_time": "0:31:51", "remaining_time": "0:02:18"}
+{"current_steps": 5230, "total_steps": 5597, "loss": 0.5110831260681152, "lr": 1.6464013370317854e-05, "epoch": 0.34820239680426096, "percentage": 93.44, "elapsed_time": "0:34:17", "remaining_time": "0:02:24"}
+{"current_steps": 5240, "total_steps": 5597, "loss": 0.5009112358093262, "lr": 1.5982601847471915e-05, "epoch": 0.3488681757656458, "percentage": 93.62, "elapsed_time": "0:36:41", "remaining_time": "0:02:29"}
+{"current_steps": 5250, "total_steps": 5597, "loss": 0.49884347915649413, "lr": 1.5478597449089553e-05, "epoch": 0.34953395472703064, "percentage": 93.8, "elapsed_time": "0:39:05", "remaining_time": "0:02:35"}
+{"current_steps": 5260, "total_steps": 5597, "loss": 0.4992386817932129, "lr": 1.4953919553705725e-05, "epoch": 0.35019973368841545, "percentage": 93.98, "elapsed_time": "0:41:30", "remaining_time": "0:02:39"}
+{"current_steps": 5270, "total_steps": 5597, "loss": 0.5062578201293946, "lr": 1.441056626985559e-05, "epoch": 0.35086551264980026, "percentage": 94.16, "elapsed_time": "0:43:55", "remaining_time": "0:02:43"}
+{"current_steps": 5280, "total_steps": 5597, "loss": 0.48395280838012694, "lr": 1.3850606826762668e-05, "epoch": 0.35153129161118507, "percentage": 94.34, "elapsed_time": "0:46:19", "remaining_time": "0:02:46"}
+{"current_steps": 5290, "total_steps": 5597, "loss": 0.5183405399322509, "lr": 1.3276173694181128e-05, "epoch": 0.3521970705725699, "percentage": 94.51, "elapsed_time": "0:48:44", "remaining_time": "0:02:49"}
+{"current_steps": 5300, "total_steps": 5597, "loss": 0.4931805610656738, "lr": 1.2689454461401822e-05, "epoch": 0.35286284953395475, "percentage": 94.69, "elapsed_time": "0:51:09", "remaining_time": "0:02:52"}
+{"current_steps": 5310, "total_steps": 5597, "loss": 0.505335521697998, "lr": 1.2092683506348939e-05, "epoch": 0.35352862849533956, "percentage": 94.87, "elapsed_time": "0:53:33", "remaining_time": "0:02:53"}
+{"current_steps": 5320, "total_steps": 5597, "loss": 0.4760289192199707, "lr": 1.14881334864935e-05, "epoch": 0.35419440745672437, "percentage": 95.05, "elapsed_time": "0:55:58", "remaining_time": "0:02:54"}
+{"current_steps": 5330, "total_steps": 5597, "loss": 0.5108865261077881, "lr": 1.0878106683988481e-05, "epoch": 0.3548601864181092, "percentage": 95.23, "elapsed_time": "0:58:22", "remaining_time": "0:02:55"}
+{"current_steps": 5340, "total_steps": 5597, "loss": 0.5170565605163574, "lr": 1.026492623798551e-05, "epoch": 0.355525965379494, "percentage": 95.41, "elapsed_time": "1:00:47", "remaining_time": "0:02:55"}
+{"current_steps": 5350, "total_steps": 5597, "loss": 0.5181658267974854, "lr": 9.650927297522743e-06, "epoch": 0.3561917443408788, "percentage": 95.59, "elapsed_time": "1:03:11", "remaining_time": "0:02:55"}
+{"current_steps": 5360, "total_steps": 5597, "loss": 0.49065260887145995, "lr": 9.038448128676012e-06, "epoch": 0.35685752330226367, "percentage": 95.77, "elapsed_time": "1:05:36", "remaining_time": "0:02:54"}
+{"current_steps": 5370, "total_steps": 5597, "loss": 0.5251599788665772, "lr": 8.42982120983949e-06, "epoch": 0.3575233022636485, "percentage": 95.94, "elapsed_time": "1:08:02", "remaining_time": "0:02:52"}
+{"current_steps": 5380, "total_steps": 5597, "loss": 0.5034067153930664, "lr": 7.827364349047303e-06, "epoch": 0.3581890812250333, "percentage": 96.12, "elapsed_time": "1:10:26", "remaining_time": "0:02:50"}
+{"current_steps": 5390, "total_steps": 5597, "loss": 0.4789381980895996, "lr": 7.233371857163706e-06, "epoch": 0.3588548601864181, "percentage": 96.3, "elapsed_time": "1:12:51", "remaining_time": "0:02:47"}
+{"current_steps": 5400, "total_steps": 5597, "loss": 0.49565725326538085, "lr": 6.650105810556492e-06, "epoch": 0.3595206391478029, "percentage": 96.48, "elapsed_time": "1:15:15", "remaining_time": "0:02:44"}
+{"current_steps": 5410, "total_steps": 5597, "loss": 0.5029505729675293, "lr": 6.079787436527681e-06, "epoch": 0.3601864181091877, "percentage": 96.66, "elapsed_time": "1:17:40", "remaining_time": "0:02:41"}
+{"current_steps": 5420, "total_steps": 5597, "loss": 0.46464385986328127, "lr": 5.524588654307961e-06, "epoch": 0.3608521970705726, "percentage": 96.84, "elapsed_time": "1:20:05", "remaining_time": "0:02:36"}
+{"current_steps": 5430, "total_steps": 5597, "loss": 0.5014979839324951, "lr": 4.986623803828985e-06, "epoch": 0.3615179760319574, "percentage": 97.02, "elapsed_time": "1:22:29", "remaining_time": "0:02:32"}
+{"current_steps": 5440, "total_steps": 5597, "loss": 0.5016984939575195, "lr": 4.467941593772423e-06, "epoch": 0.3621837549933422, "percentage": 97.19, "elapsed_time": "1:24:54", "remaining_time": "0:02:27"}
+{"current_steps": 5450, "total_steps": 5597, "loss": 0.49635066986083987, "lr": 3.9705172995597606e-06, "epoch": 0.362849533954727, "percentage": 97.37, "elapsed_time": "1:27:19", "remaining_time": "0:02:21"}
+{"current_steps": 5460, "total_steps": 5597, "loss": 0.4519174575805664, "lr": 3.4962452409948346e-06, "epoch": 0.36351531291611183, "percentage": 97.55, "elapsed_time": "1:29:43", "remaining_time": "0:02:15"}
+{"current_steps": 5470, "total_steps": 5597, "loss": 0.4889498710632324, "lr": 3.046931568206211e-06, "epoch": 0.3641810918774967, "percentage": 97.73, "elapsed_time": "1:32:08", "remaining_time": "0:02:08"}
+{"current_steps": 5480, "total_steps": 5597, "loss": 0.4599448680877686, "lr": 2.624287383362404e-06, "epoch": 0.3648468708388815, "percentage": 97.91, "elapsed_time": "1:34:32", "remaining_time": "0:02:01"}
+{"current_steps": 5490, "total_steps": 5597, "loss": 0.4669328212738037, "lr": 2.2299222243541845e-06, "epoch": 0.3655126498002663, "percentage": 98.09, "elapsed_time": "1:36:56", "remaining_time": "0:01:53"}
+{"current_steps": 5500, "total_steps": 5597, "loss": 0.4652420997619629, "lr": 1.8653379352598246e-06, "epoch": 0.36617842876165113, "percentage": 98.27, "elapsed_time": "1:39:21", "remaining_time": "0:01:45"}
+{"current_steps": 5510, "total_steps": 5597, "loss": 0.4658137321472168, "lr": 1.5319229469361075e-06, "epoch": 0.36684420772303594, "percentage": 98.45, "elapsed_time": "1:41:46", "remaining_time": "0:01:36"}
+{"current_steps": 5520, "total_steps": 5597, "loss": 0.49527854919433595, "lr": 1.2309469895160917e-06, "epoch": 0.36750998668442075, "percentage": 98.62, "elapsed_time": "1:44:11", "remaining_time": "0:01:27"}
+{"current_steps": 5530, "total_steps": 5597, "loss": 0.4762737274169922, "lr": 9.635562569497974e-07, "epoch": 0.3681757656458056, "percentage": 98.8, "elapsed_time": "1:46:35", "remaining_time": "0:01:17"}
+{"current_steps": 5540, "total_steps": 5597, "loss": 0.4807307720184326, "lr": 7.307690420024867e-07, "epoch": 0.36884154460719043, "percentage": 98.98, "elapsed_time": "1:49:00", "remaining_time": "0:01:07"}
+{"current_steps": 5550, "total_steps": 5597, "loss": 0.4831793785095215, "lr": 5.334718583335942e-07, "epoch": 0.36950732356857524, "percentage": 99.16, "elapsed_time": "1:51:24", "remaining_time": "0:00:56"}
+{"current_steps": 5560, "total_steps": 5597, "loss": 0.4890940189361572, "lr": 3.7241606442442763e-07, "epoch": 0.37017310252996005, "percentage": 99.34, "elapsed_time": "1:53:49", "remaining_time": "0:00:45"}
+{"current_steps": 5570, "total_steps": 5597, "loss": 0.4997108459472656, "lr": 2.482150022115879e-07, "epoch": 0.37083888149134486, "percentage": 99.52, "elapsed_time": "1:56:13", "remaining_time": "0:00:33"}
+{"current_steps": 5580, "total_steps": 5597, "loss": 0.4323744773864746, "lr": 1.6134166132293174e-07, "epoch": 0.3715046604527297, "percentage": 99.7, "elapsed_time": "1:58:38", "remaining_time": "0:00:21"}
+{"current_steps": 5590, "total_steps": 5597, "loss": 0.4737849235534668, "lr": 1.1212687781127357e-07, "epoch": 0.37217043941411454, "percentage": 99.87, "elapsed_time": "2:01:03", "remaining_time": "0:00:09"}
+{"current_steps": 5597, "total_steps": 5597, "epoch": 0.3726364846870839, "percentage": 100.0, "elapsed_time": "2:03:06", "remaining_time": "0:00:00"}

g2_1_oldcode_cm_newcode__edit/500M/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825eaaea0349941dd5042663cd8c068004bf25e3e37fa6e4790a51afe2a23075
+size 8273