Auto upload zain 2026-08-12T22:45:12.055248 (part 2)

zain/Activation/out/glu-situglu-100L_run/checkpoint-400/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.026963262554769128,
+  "eval_steps": 2498,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013481631277384564,
+      "grad_norm": 2.078125,
+      "learning_rate": 2.66e-05,
+      "loss": 8.299653625488281,
+      "step": 20
+    },
+    {
+      "epoch": 0.002696326255476913,
+      "grad_norm": 1.3515625,
+      "learning_rate": 5.46e-05,
+      "loss": 8.04769058227539,
+      "step": 40
+    },
+    {
+      "epoch": 0.004044489383215369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.259999999999999e-05,
+      "loss": 7.8379150390625,
+      "step": 60
+    },
+    {
+      "epoch": 0.005392652510953826,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0001106,
+      "loss": 7.572837066650391,
+      "step": 80
+    },
+    {
+      "epoch": 0.006740815638692282,
+      "grad_norm": 1.1953125,
+      "learning_rate": 0.0001386,
+      "loss": 7.233182525634765,
+      "step": 100
+    },
+    {
+      "epoch": 0.008088978766430738,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.00016659999999999998,
+      "loss": 6.860689544677735,
+      "step": 120
+    },
+    {
+      "epoch": 0.009437141894169195,
+      "grad_norm": 0.94921875,
+      "learning_rate": 0.00019460000000000001,
+      "loss": 6.517751312255859,
+      "step": 140
+    },
+    {
+      "epoch": 0.010785305021907651,
+      "grad_norm": 0.8046875,
+      "learning_rate": 0.0002226,
+      "loss": 6.239968109130859,
+      "step": 160
+    },
+    {
+      "epoch": 0.012133468149646108,
+      "grad_norm": 0.6640625,
+      "learning_rate": 0.00025059999999999997,
+      "loss": 6.041232299804688,
+      "step": 180
+    },
+    {
+      "epoch": 0.013481631277384564,
+      "grad_norm": 0.5234375,
+      "learning_rate": 0.0002786,
+      "loss": 5.863973999023438,
+      "step": 200
+    },
+    {
+      "epoch": 0.01482979440512302,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00030659999999999997,
+      "loss": 5.692941665649414,
+      "step": 220
+    },
+    {
+      "epoch": 0.016177957532861477,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0003346,
+      "loss": 5.484311294555664,
+      "step": 240
+    },
+    {
+      "epoch": 0.01752612066059993,
+      "grad_norm": 1.25,
+      "learning_rate": 0.00036260000000000003,
+      "loss": 5.25721549987793,
+      "step": 260
+    },
+    {
+      "epoch": 0.01887428378833839,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.0003906,
+      "loss": 5.028667831420899,
+      "step": 280
+    },
+    {
+      "epoch": 0.020222446916076844,
+      "grad_norm": 0.75390625,
+      "learning_rate": 0.0004186,
+      "loss": 4.791546249389649,
+      "step": 300
+    },
+    {
+      "epoch": 0.021570610043815303,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0004466,
+      "loss": 4.598950958251953,
+      "step": 320
+    },
+    {
+      "epoch": 0.022918773171553757,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00047460000000000004,
+      "loss": 4.41942024230957,
+      "step": 340
+    },
+    {
+      "epoch": 0.024266936299292215,
+      "grad_norm": 0.890625,
+      "learning_rate": 0.0005026,
+      "loss": 4.27253303527832,
+      "step": 360
+    },
+    {
+      "epoch": 0.02561509942703067,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.0005306,
+      "loss": 4.1283222198486325,
+      "step": 380
+    },
+    {
+      "epoch": 0.026963262554769128,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.0005586,
+      "loss": 3.9935020446777343,
+      "step": 400
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1290513521049600.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

zain/Activation/out/glu-situglu-100L_run/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b99898fe48ff0e75b1f0139845f22400023db32e87c8fca3404fda1b772936
+size 4920

zain/Activation/out/glu-situglu-100L_run/checkpoint-500/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "situglu",
+  "architectures": [
+    "TinyLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "mlp_type": "glu",
+  "model_type": "tiny_llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 100,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": false,
+  "vocab_size": 4096,
+  "waleed_beta": 10.0
+}

zain/Activation/out/glu-situglu-100L_run/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c72023f1c9d5c3865d8b75100580803262637a2d476a60bde58ffad870c06dbc
+size 33967272

zain/Activation/out/glu-situglu-100L_run/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81e6cacb36707fadaa86cd24ef9ed323b600912f2fdc8276612e4cc4caf3861
+size 68504996

zain/Activation/out/glu-situglu-100L_run/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

zain/Activation/out/glu-situglu-100L_run/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad40e275c0c46c262ecd103385af8fb68cf3f382102b4f63937b0dbd1c69cfc
+size 1064

zain/Activation/out/glu-situglu-100L_run/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

zain/Activation/out/glu-situglu-100L_run/checkpoint-500/trainer_state.json

@@ -0,0 +1,209 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.03370407819346141,
+  "eval_steps": 2498,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013481631277384564,
+      "grad_norm": 2.078125,
+      "learning_rate": 2.66e-05,
+      "loss": 8.299653625488281,
+      "step": 20
+    },
+    {
+      "epoch": 0.002696326255476913,
+      "grad_norm": 1.3515625,
+      "learning_rate": 5.46e-05,
+      "loss": 8.04769058227539,
+      "step": 40
+    },
+    {
+      "epoch": 0.004044489383215369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.259999999999999e-05,
+      "loss": 7.8379150390625,
+      "step": 60
+    },
+    {
+      "epoch": 0.005392652510953826,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0001106,
+      "loss": 7.572837066650391,
+      "step": 80
+    },
+    {
+      "epoch": 0.006740815638692282,
+      "grad_norm": 1.1953125,
+      "learning_rate": 0.0001386,
+      "loss": 7.233182525634765,
+      "step": 100
+    },
+    {
+      "epoch": 0.008088978766430738,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.00016659999999999998,
+      "loss": 6.860689544677735,
+      "step": 120
+    },
+    {
+      "epoch": 0.009437141894169195,
+      "grad_norm": 0.94921875,
+      "learning_rate": 0.00019460000000000001,
+      "loss": 6.517751312255859,
+      "step": 140
+    },
+    {
+      "epoch": 0.010785305021907651,
+      "grad_norm": 0.8046875,
+      "learning_rate": 0.0002226,
+      "loss": 6.239968109130859,
+      "step": 160
+    },
+    {
+      "epoch": 0.012133468149646108,
+      "grad_norm": 0.6640625,
+      "learning_rate": 0.00025059999999999997,
+      "loss": 6.041232299804688,
+      "step": 180
+    },
+    {
+      "epoch": 0.013481631277384564,
+      "grad_norm": 0.5234375,
+      "learning_rate": 0.0002786,
+      "loss": 5.863973999023438,
+      "step": 200
+    },
+    {
+      "epoch": 0.01482979440512302,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00030659999999999997,
+      "loss": 5.692941665649414,
+      "step": 220
+    },
+    {
+      "epoch": 0.016177957532861477,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0003346,
+      "loss": 5.484311294555664,
+      "step": 240
+    },
+    {
+      "epoch": 0.01752612066059993,
+      "grad_norm": 1.25,
+      "learning_rate": 0.00036260000000000003,
+      "loss": 5.25721549987793,
+      "step": 260
+    },
+    {
+      "epoch": 0.01887428378833839,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.0003906,
+      "loss": 5.028667831420899,
+      "step": 280
+    },
+    {
+      "epoch": 0.020222446916076844,
+      "grad_norm": 0.75390625,
+      "learning_rate": 0.0004186,
+      "loss": 4.791546249389649,
+      "step": 300
+    },
+    {
+      "epoch": 0.021570610043815303,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0004466,
+      "loss": 4.598950958251953,
+      "step": 320
+    },
+    {
+      "epoch": 0.022918773171553757,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00047460000000000004,
+      "loss": 4.41942024230957,
+      "step": 340
+    },
+    {
+      "epoch": 0.024266936299292215,
+      "grad_norm": 0.890625,
+      "learning_rate": 0.0005026,
+      "loss": 4.27253303527832,
+      "step": 360
+    },
+    {
+      "epoch": 0.02561509942703067,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.0005306,
+      "loss": 4.1283222198486325,
+      "step": 380
+    },
+    {
+      "epoch": 0.026963262554769128,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.0005586,
+      "loss": 3.9935020446777343,
+      "step": 400
+    },
+    {
+      "epoch": 0.028311425682507583,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.0005866,
+      "loss": 3.885255813598633,
+      "step": 420
+    },
+    {
+      "epoch": 0.02965958881024604,
+      "grad_norm": 0.7890625,
+      "learning_rate": 0.0006146,
+      "loss": 3.821950912475586,
+      "step": 440
+    },
+    {
+      "epoch": 0.031007751937984496,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.0006426,
+      "loss": 3.7068336486816404,
+      "step": 460
+    },
+    {
+      "epoch": 0.032355915065722954,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.0006705999999999999,
+      "loss": 3.6370723724365233,
+      "step": 480
+    },
+    {
+      "epoch": 0.03370407819346141,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0006986,
+      "loss": 3.5550304412841798,
+      "step": 500
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1613141901312000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

zain/Activation/out/glu-situglu-100L_run/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b99898fe48ff0e75b1f0139845f22400023db32e87c8fca3404fda1b772936
+size 4920

zain/Activation/out/glu-situglu-100L_run/checkpoint-600/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "situglu",
+  "architectures": [
+    "TinyLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "mlp_type": "glu",
+  "model_type": "tiny_llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 100,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": false,
+  "vocab_size": 4096,
+  "waleed_beta": 10.0
+}

zain/Activation/out/glu-situglu-100L_run/checkpoint-600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6a728e4484a52b424b29bb69cbad64e967148c990ee48574300521062c93d8
+size 33967272

zain/Activation/out/glu-situglu-100L_run/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40695dc8028a8fe6e509c5567380be726596372e62ea7b6f6e4e258da754db5a
+size 68504996

zain/Activation/out/glu-situglu-100L_run/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

zain/Activation/out/glu-situglu-100L_run/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a21235ddd7c8c0020d887652dce105923f094e2bc54766bffa71522037a007
+size 1064

zain/Activation/out/glu-situglu-100L_run/checkpoint-600/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

zain/Activation/out/glu-situglu-100L_run/checkpoint-600/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04044489383215369,
+  "eval_steps": 2498,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013481631277384564,
+      "grad_norm": 2.078125,
+      "learning_rate": 2.66e-05,
+      "loss": 8.299653625488281,
+      "step": 20
+    },
+    {
+      "epoch": 0.002696326255476913,
+      "grad_norm": 1.3515625,
+      "learning_rate": 5.46e-05,
+      "loss": 8.04769058227539,
+      "step": 40
+    },
+    {
+      "epoch": 0.004044489383215369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.259999999999999e-05,
+      "loss": 7.8379150390625,
+      "step": 60
+    },
+    {
+      "epoch": 0.005392652510953826,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0001106,
+      "loss": 7.572837066650391,
+      "step": 80
+    },
+    {
+      "epoch": 0.006740815638692282,
+      "grad_norm": 1.1953125,
+      "learning_rate": 0.0001386,
+      "loss": 7.233182525634765,
+      "step": 100
+    },
+    {
+      "epoch": 0.008088978766430738,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.00016659999999999998,
+      "loss": 6.860689544677735,
+      "step": 120
+    },
+    {
+      "epoch": 0.009437141894169195,
+      "grad_norm": 0.94921875,
+      "learning_rate": 0.00019460000000000001,
+      "loss": 6.517751312255859,
+      "step": 140
+    },
+    {
+      "epoch": 0.010785305021907651,
+      "grad_norm": 0.8046875,
+      "learning_rate": 0.0002226,
+      "loss": 6.239968109130859,
+      "step": 160
+    },
+    {
+      "epoch": 0.012133468149646108,
+      "grad_norm": 0.6640625,
+      "learning_rate": 0.00025059999999999997,
+      "loss": 6.041232299804688,
+      "step": 180
+    },
+    {
+      "epoch": 0.013481631277384564,
+      "grad_norm": 0.5234375,
+      "learning_rate": 0.0002786,
+      "loss": 5.863973999023438,
+      "step": 200
+    },
+    {
+      "epoch": 0.01482979440512302,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00030659999999999997,
+      "loss": 5.692941665649414,
+      "step": 220
+    },
+    {
+      "epoch": 0.016177957532861477,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0003346,
+      "loss": 5.484311294555664,
+      "step": 240
+    },
+    {
+      "epoch": 0.01752612066059993,
+      "grad_norm": 1.25,
+      "learning_rate": 0.00036260000000000003,
+      "loss": 5.25721549987793,
+      "step": 260
+    },
+    {
+      "epoch": 0.01887428378833839,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.0003906,
+      "loss": 5.028667831420899,
+      "step": 280
+    },
+    {
+      "epoch": 0.020222446916076844,
+      "grad_norm": 0.75390625,
+      "learning_rate": 0.0004186,
+      "loss": 4.791546249389649,
+      "step": 300
+    },
+    {
+      "epoch": 0.021570610043815303,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0004466,
+      "loss": 4.598950958251953,
+      "step": 320
+    },
+    {
+      "epoch": 0.022918773171553757,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00047460000000000004,
+      "loss": 4.41942024230957,
+      "step": 340
+    },
+    {
+      "epoch": 0.024266936299292215,
+      "grad_norm": 0.890625,
+      "learning_rate": 0.0005026,
+      "loss": 4.27253303527832,
+      "step": 360
+    },
+    {
+      "epoch": 0.02561509942703067,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.0005306,
+      "loss": 4.1283222198486325,
+      "step": 380
+    },
+    {
+      "epoch": 0.026963262554769128,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.0005586,
+      "loss": 3.9935020446777343,
+      "step": 400
+    },
+    {
+      "epoch": 0.028311425682507583,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.0005866,
+      "loss": 3.885255813598633,
+      "step": 420
+    },
+    {
+      "epoch": 0.02965958881024604,
+      "grad_norm": 0.7890625,
+      "learning_rate": 0.0006146,
+      "loss": 3.821950912475586,
+      "step": 440
+    },
+    {
+      "epoch": 0.031007751937984496,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.0006426,
+      "loss": 3.7068336486816404,
+      "step": 460
+    },
+    {
+      "epoch": 0.032355915065722954,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.0006705999999999999,
+      "loss": 3.6370723724365233,
+      "step": 480
+    },
+    {
+      "epoch": 0.03370407819346141,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0006986,
+      "loss": 3.5550304412841798,
+      "step": 500
+    },
+    {
+      "epoch": 0.03505224132119986,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.0007,
+      "loss": 3.4874305725097656,
+      "step": 520
+    },
+    {
+      "epoch": 0.03640040444893832,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.0007,
+      "loss": 3.414617919921875,
+      "step": 540
+    },
+    {
+      "epoch": 0.03774856757667678,
+      "grad_norm": 0.478515625,
+      "learning_rate": 0.0007,
+      "loss": 3.3621952056884767,
+      "step": 560
+    },
+    {
+      "epoch": 0.03909673070441524,
+      "grad_norm": 0.478515625,
+      "learning_rate": 0.0007,
+      "loss": 3.301148223876953,
+      "step": 580
+    },
+    {
+      "epoch": 0.04044489383215369,
+      "grad_norm": 0.44140625,
+      "learning_rate": 0.0007,
+      "loss": 3.266124725341797,
+      "step": 600
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1935770281574400.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

zain/Activation/out/glu-situglu-100L_run/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b99898fe48ff0e75b1f0139845f22400023db32e87c8fca3404fda1b772936
+size 4920

zain/Activation/out/glu-situglu-100L_run/checkpoint-700/config.json

@@ -0,0 +1,36 @@
+{
+  "activation": "situglu",
+  "architectures": [
+    "TinyLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "mlp_type": "glu",
+  "model_type": "tiny_llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 100,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": false,
+  "vocab_size": 4096,
+  "waleed_beta": 10.0
+}

zain/Activation/out/glu-situglu-100L_run/checkpoint-700/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2e6f6ff772ac66fe0662150942d14cef48a594c5c6bdd588e8ba36d3f242bf
+size 33967272

zain/Activation/out/glu-situglu-100L_run/checkpoint-700/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d730f3d1537749179427a36a7c0e4cad5d77a0b2f5f5e679f5ac845b3a211bb6
+size 68504996

zain/Activation/out/glu-situglu-100L_run/checkpoint-700/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

zain/Activation/out/glu-situglu-100L_run/checkpoint-700/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aac662062525611dd137fd05108444d17dfbd69f137e40e8a3651bb69d2ba7e
+size 1064

zain/Activation/out/glu-situglu-100L_run/checkpoint-700/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

zain/Activation/out/glu-situglu-100L_run/checkpoint-700/trainer_state.json

@@ -0,0 +1,279 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04718570947084597,
+  "eval_steps": 2498,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013481631277384564,
+      "grad_norm": 2.078125,
+      "learning_rate": 2.66e-05,
+      "loss": 8.299653625488281,
+      "step": 20
+    },
+    {
+      "epoch": 0.002696326255476913,
+      "grad_norm": 1.3515625,
+      "learning_rate": 5.46e-05,
+      "loss": 8.04769058227539,
+      "step": 40
+    },
+    {
+      "epoch": 0.004044489383215369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 8.259999999999999e-05,
+      "loss": 7.8379150390625,
+      "step": 60
+    },
+    {
+      "epoch": 0.005392652510953826,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0001106,
+      "loss": 7.572837066650391,
+      "step": 80
+    },
+    {
+      "epoch": 0.006740815638692282,
+      "grad_norm": 1.1953125,
+      "learning_rate": 0.0001386,
+      "loss": 7.233182525634765,
+      "step": 100
+    },
+    {
+      "epoch": 0.008088978766430738,
+      "grad_norm": 1.1328125,
+      "learning_rate": 0.00016659999999999998,
+      "loss": 6.860689544677735,
+      "step": 120
+    },
+    {
+      "epoch": 0.009437141894169195,
+      "grad_norm": 0.94921875,
+      "learning_rate": 0.00019460000000000001,
+      "loss": 6.517751312255859,
+      "step": 140
+    },
+    {
+      "epoch": 0.010785305021907651,
+      "grad_norm": 0.8046875,
+      "learning_rate": 0.0002226,
+      "loss": 6.239968109130859,
+      "step": 160
+    },
+    {
+      "epoch": 0.012133468149646108,
+      "grad_norm": 0.6640625,
+      "learning_rate": 0.00025059999999999997,
+      "loss": 6.041232299804688,
+      "step": 180
+    },
+    {
+      "epoch": 0.013481631277384564,
+      "grad_norm": 0.5234375,
+      "learning_rate": 0.0002786,
+      "loss": 5.863973999023438,
+      "step": 200
+    },
+    {
+      "epoch": 0.01482979440512302,
+      "grad_norm": 1.375,
+      "learning_rate": 0.00030659999999999997,
+      "loss": 5.692941665649414,
+      "step": 220
+    },
+    {
+      "epoch": 0.016177957532861477,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0003346,
+      "loss": 5.484311294555664,
+      "step": 240
+    },
+    {
+      "epoch": 0.01752612066059993,
+      "grad_norm": 1.25,
+      "learning_rate": 0.00036260000000000003,
+      "loss": 5.25721549987793,
+      "step": 260
+    },
+    {
+      "epoch": 0.01887428378833839,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.0003906,
+      "loss": 5.028667831420899,
+      "step": 280
+    },
+    {
+      "epoch": 0.020222446916076844,
+      "grad_norm": 0.75390625,
+      "learning_rate": 0.0004186,
+      "loss": 4.791546249389649,
+      "step": 300
+    },
+    {
+      "epoch": 0.021570610043815303,
+      "grad_norm": 0.875,
+      "learning_rate": 0.0004466,
+      "loss": 4.598950958251953,
+      "step": 320
+    },
+    {
+      "epoch": 0.022918773171553757,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00047460000000000004,
+      "loss": 4.41942024230957,
+      "step": 340
+    },
+    {
+      "epoch": 0.024266936299292215,
+      "grad_norm": 0.890625,
+      "learning_rate": 0.0005026,
+      "loss": 4.27253303527832,
+      "step": 360
+    },
+    {
+      "epoch": 0.02561509942703067,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.0005306,
+      "loss": 4.1283222198486325,
+      "step": 380
+    },
+    {
+      "epoch": 0.026963262554769128,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.0005586,
+      "loss": 3.9935020446777343,
+      "step": 400
+    },
+    {
+      "epoch": 0.028311425682507583,
+      "grad_norm": 0.546875,
+      "learning_rate": 0.0005866,
+      "loss": 3.885255813598633,
+      "step": 420
+    },
+    {
+      "epoch": 0.02965958881024604,
+      "grad_norm": 0.7890625,
+      "learning_rate": 0.0006146,
+      "loss": 3.821950912475586,
+      "step": 440
+    },
+    {
+      "epoch": 0.031007751937984496,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.0006426,
+      "loss": 3.7068336486816404,
+      "step": 460
+    },
+    {
+      "epoch": 0.032355915065722954,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.0006705999999999999,
+      "loss": 3.6370723724365233,
+      "step": 480
+    },
+    {
+      "epoch": 0.03370407819346141,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0006986,
+      "loss": 3.5550304412841798,
+      "step": 500
+    },
+    {
+      "epoch": 0.03505224132119986,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.0007,
+      "loss": 3.4874305725097656,
+      "step": 520
+    },
+    {
+      "epoch": 0.03640040444893832,
+      "grad_norm": 0.6328125,
+      "learning_rate": 0.0007,
+      "loss": 3.414617919921875,
+      "step": 540
+    },
+    {
+      "epoch": 0.03774856757667678,
+      "grad_norm": 0.478515625,
+      "learning_rate": 0.0007,
+      "loss": 3.3621952056884767,
+      "step": 560
+    },
+    {
+      "epoch": 0.03909673070441524,
+      "grad_norm": 0.478515625,
+      "learning_rate": 0.0007,
+      "loss": 3.301148223876953,
+      "step": 580
+    },
+    {
+      "epoch": 0.04044489383215369,
+      "grad_norm": 0.44140625,
+      "learning_rate": 0.0007,
+      "loss": 3.266124725341797,
+      "step": 600
+    },
+    {
+      "epoch": 0.04179305695989215,
+      "grad_norm": 0.58203125,
+      "learning_rate": 0.0007,
+      "loss": 3.1991281509399414,
+      "step": 620
+    },
+    {
+      "epoch": 0.043141220087630605,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.0007,
+      "loss": 3.175183868408203,
+      "step": 640
+    },
+    {
+      "epoch": 0.044489383215369056,
+      "grad_norm": 0.443359375,
+      "learning_rate": 0.0007,
+      "loss": 3.1185443878173826,
+      "step": 660
+    },
+    {
+      "epoch": 0.045837546343107514,
+      "grad_norm": 0.447265625,
+      "learning_rate": 0.0007,
+      "loss": 3.091288757324219,
+      "step": 680
+    },
+    {
+      "epoch": 0.04718570947084597,
+      "grad_norm": 0.400390625,
+      "learning_rate": 0.0007,
+      "loss": 3.0479175567626955,
+      "step": 700
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2258398661836800.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

zain/Activation/out/glu-situglu-100L_run/checkpoint-700/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b99898fe48ff0e75b1f0139845f22400023db32e87c8fca3404fda1b772936
+size 4920

zain/Activation/out/glu-situglu-100L_run/training_log.jsonl

@@ -0,0 +1,38 @@
+{"step": 20, "epoch": 0.0013481631277384564, "timestamp": 1786574478.6078393, "loss": 8.299653625488281, "grad_norm": 2.078125, "learning_rate": 2.66e-05, "train/total_time_seconds": 5.533695328980684, "train/time_per_step_avg": 0.2766847664490342, "train/epoch_time_elapsed": 6.577135156840086, "train/estimated_remaining_minutes": 11.436303679893415}
+{"step": 40, "epoch": 0.002696326255476913, "timestamp": 1786574484.8776257, "loss": 8.04769058227539, "grad_norm": 1.3515625, "learning_rate": 5.46e-05, "train/total_time_seconds": 10.852699480950832, "train/time_per_step_avg": 0.2713174870237708, "train/epoch_time_elapsed": 12.846922278404236, "train/estimated_remaining_minutes": 11.124016967974603}
+{"step": 60, "epoch": 0.004044489383215369, "timestamp": 1786574491.1171036, "loss": 7.8379150390625, "grad_norm": 1.2734375, "learning_rate": 8.259999999999999e-05, "train/total_time_seconds": 16.144448928534985, "train/time_per_step_avg": 0.2690741488089164, "train/epoch_time_elapsed": 19.086400248110294, "train/estimated_remaining_minutes": 10.942348718229265}
+{"step": 80, "epoch": 0.005392652510953826, "timestamp": 1786574497.38103, "loss": 7.572837066650391, "grad_norm": 1.265625, "learning_rate": 0.0001106, "train/total_time_seconds": 21.441417019814253, "train/time_per_step_avg": 0.26801771274767816, "train/epoch_time_elapsed": 25.35032656043768, "train/estimated_remaining_minutes": 10.810047747489685}
+{"step": 100, "epoch": 0.006740815638692282, "timestamp": 1786574503.688846, "loss": 7.233182525634765, "grad_norm": 1.1953125, "learning_rate": 0.0001386, "train/total_time_seconds": 26.74744677171111, "train/time_per_step_avg": 0.2674744677171111, "train/epoch_time_elapsed": 31.65814283117652, "train/estimated_remaining_minutes": 10.698978708684443}
+{"step": 120, "epoch": 0.008088978766430738, "timestamp": 1786574510.3158803, "loss": 6.860689544677735, "grad_norm": 1.1328125, "learning_rate": 0.00016659999999999998, "train/total_time_seconds": 32.103225629776716, "train/time_per_step_avg": 0.2656953030079603, "train/epoch_time_elapsed": 38.28517517820001, "train/estimated_remaining_minutes": 10.611899583176191}
+{"step": 140, "epoch": 0.009437141894169195, "timestamp": 1786574516.5818565, "loss": 6.517751312255859, "grad_norm": 0.94921875, "learning_rate": 0.00019460000000000001, "train/total_time_seconds": 37.4054417796433, "train/time_per_step_avg": 0.26552742298692467, "train/epoch_time_elapsed": 44.55115310847759, "train/estimated_remaining_minutes": 10.50914792856645}
+{"step": 160, "epoch": 0.010785305021907651, "timestamp": 1786574522.8408346, "loss": 6.239968109130859, "grad_norm": 0.8046875, "learning_rate": 0.0002226, "train/total_time_seconds": 42.69929559901357, "train/time_per_step_avg": 0.2655484667047858, "train/epoch_time_elapsed": 50.81013148650527, "train/estimated_remaining_minutes": 10.407953302259557}
+{"step": 180, "epoch": 0.012133468149646108, "timestamp": 1786574529.1809292, "loss": 6.041232299804688, "grad_norm": 0.6640625, "learning_rate": 0.00025059999999999997, "train/total_time_seconds": 48.07227246835828, "train/time_per_step_avg": 0.2663085544854403, "train/epoch_time_elapsed": 57.15022452548146, "train/estimated_remaining_minutes": 10.326636308017704}
+{"step": 200, "epoch": 0.013481631277384564, "timestamp": 1786574535.714883, "loss": 5.863973999023438, "grad_norm": 0.5234375, "learning_rate": 0.0002786, "train/total_time_seconds": 53.626166980713606, "train/time_per_step_avg": 0.26878720209002493, "train/epoch_time_elapsed": 63.68417948484421, "train/estimated_remaining_minutes": 10.27834867130344}
+{"step": 220, "epoch": 0.01482979440512302, "timestamp": 1786574542.6790636, "loss": 5.692941665649414, "grad_norm": 1.375, "learning_rate": 0.00030659999999999997, "train/total_time_seconds": 59.30672527849674, "train/time_per_step_avg": 0.27203499648720025, "train/epoch_time_elapsed": 70.64836028963327, "train/estimated_remaining_minutes": 10.243888911740346}
+{"step": 240, "epoch": 0.016177957532861477, "timestamp": 1786574548.9629416, "loss": 5.484311294555664, "grad_norm": 0.875, "learning_rate": 0.0003346, "train/total_time_seconds": 64.62455787137151, "train/time_per_step_avg": 0.2721911609172821, "train/epoch_time_elapsed": 76.93223825097084, "train/estimated_remaining_minutes": 10.142465332590252}
+{"step": 260, "epoch": 0.01752612066059993, "timestamp": 1786574555.2635224, "loss": 5.25721549987793, "grad_norm": 1.25, "learning_rate": 0.00036260000000000003, "train/total_time_seconds": 69.94365423545241, "train/time_per_step_avg": 0.2724435863643885, "train/epoch_time_elapsed": 83.2328185737133, "train/estimated_remaining_minutes": 10.043191377398296}
+{"step": 280, "epoch": 0.01887428378833839, "timestamp": 1786574561.585235, "loss": 5.028667831420899, "grad_norm": 0.8125, "learning_rate": 0.0003906, "train/total_time_seconds": 75.27913975343108, "train/time_per_step_avg": 0.27206867285072805, "train/epoch_time_elapsed": 89.55453195795417, "train/estimated_remaining_minutes": 9.947600610274822}
+{"step": 300, "epoch": 0.020222446916076844, "timestamp": 1786574567.9139166, "loss": 4.791546249389649, "grad_norm": 0.75390625, "learning_rate": 0.0004186, "train/total_time_seconds": 80.60792702436447, "train/time_per_step_avg": 0.26981760043650865, "train/epoch_time_elapsed": 95.88321312144399, "train/estimated_remaining_minutes": 9.852079969644546}
+{"step": 320, "epoch": 0.021570610043815303, "timestamp": 1786574574.5672615, "loss": 4.598950958251953, "grad_norm": 0.875, "learning_rate": 0.0004466, "train/total_time_seconds": 85.9880293123424, "train/time_per_step_avg": 0.26681304033845665, "train/epoch_time_elapsed": 102.53655807301402, "train/estimated_remaining_minutes": 9.763224161505544}
+{"step": 340, "epoch": 0.022918773171553757, "timestamp": 1786574580.8542867, "loss": 4.41942024230957, "grad_norm": 0.8125, "learning_rate": 0.00047460000000000004, "train/total_time_seconds": 91.31005642563105, "train/time_per_step_avg": 0.2668549855425954, "train/epoch_time_elapsed": 108.82358324155211, "train/estimated_remaining_minutes": 9.668123621537404}
+{"step": 360, "epoch": 0.024266936299292215, "timestamp": 1786574587.163612, "loss": 4.27253303527832, "grad_norm": 0.890625, "learning_rate": 0.0005026, "train/total_time_seconds": 96.64731953665614, "train/time_per_step_avg": 0.2670366530120373, "train/epoch_time_elapsed": 115.13290867209435, "train/estimated_remaining_minutes": 9.575243694835375}
+{"step": 380, "epoch": 0.02561509942703067, "timestamp": 1786574593.4437447, "loss": 4.1283222198486325, "grad_norm": 1.2734375, "learning_rate": 0.0005306, "train/total_time_seconds": 101.96216157451272, "train/time_per_step_avg": 0.2668302182108164, "train/epoch_time_elapsed": 121.41304164752364, "train/estimated_remaining_minutes": 9.480692216577498}
+{"step": 400, "epoch": 0.026963262554769128, "timestamp": 1786574600.017392, "loss": 3.9935020446777343, "grad_norm": 0.54296875, "learning_rate": 0.0005586, "train/total_time_seconds": 107.53365701809525, "train/time_per_step_avg": 0.26925729993730785, "train/epoch_time_elapsed": 127.98668835312128, "train/estimated_remaining_minutes": 9.409194989083336}
+{"step": 420, "epoch": 0.028311425682507583, "timestamp": 1786574606.664945, "loss": 3.885255813598633, "grad_norm": 0.546875, "learning_rate": 0.0005866, "train/total_time_seconds": 112.89078459888697, "train/time_per_step_avg": 0.2690275528654456, "train/epoch_time_elapsed": 134.6342415958643, "train/estimated_remaining_minutes": 9.317969522447813}
+{"step": 440, "epoch": 0.02965958881024604, "timestamp": 1786574613.038697, "loss": 3.821950912475586, "grad_norm": 0.7890625, "learning_rate": 0.0006146, "train/total_time_seconds": 118.25393801182508, "train/time_per_step_avg": 0.2694388158619404, "train/epoch_time_elapsed": 141.00799356028438, "train/estimated_remaining_minutes": 9.22739061758938}
+{"step": 460, "epoch": 0.031007751937984496, "timestamp": 1786574619.3816445, "loss": 3.7068336486816404, "grad_norm": 0.52734375, "learning_rate": 0.0006426, "train/total_time_seconds": 123.59944036230445, "train/time_per_step_avg": 0.26952120825648307, "train/epoch_time_elapsed": 147.35094125196338, "train/estimated_remaining_minutes": 9.13561080938772}
+{"step": 480, "epoch": 0.032355915065722954, "timestamp": 1786574625.742511, "loss": 3.6370723724365233, "grad_norm": 0.6328125, "learning_rate": 0.0006705999999999999, "train/total_time_seconds": 128.9706449471414, "train/time_per_step_avg": 0.2700848337262869, "train/epoch_time_elapsed": 153.71180725097656, "train/estimated_remaining_minutes": 9.045857735875892}
+{"step": 500, "epoch": 0.03370407819346141, "timestamp": 1786574632.0688386, "loss": 3.5550304412841798, "grad_norm": 0.5625, "learning_rate": 0.0006986, "train/total_time_seconds": 134.30982853844762, "train/time_per_step_avg": 0.26776171520352365, "train/epoch_time_elapsed": 160.03813540562987, "train/estimated_remaining_minutes": 8.95398856922984}
+{"step": 520, "epoch": 0.03505224132119986, "timestamp": 1786574638.7088253, "loss": 3.4874305725097656, "grad_norm": 0.47265625, "learning_rate": 0.0007, "train/total_time_seconds": 139.67404821142554, "train/time_per_step_avg": 0.26783263612538577, "train/epoch_time_elapsed": 166.67812218144536, "train/estimated_remaining_minutes": 8.863929982648159}
+{"step": 540, "epoch": 0.03640040444893832, "timestamp": 1786574645.0168326, "loss": 3.414617919921875, "grad_norm": 0.6328125, "learning_rate": 0.0007, "train/total_time_seconds": 145.00912476703525, "train/time_per_step_avg": 0.2675518675521016, "train/epoch_time_elapsed": 172.98612849786878, "train/estimated_remaining_minutes": 8.772156930351516}
+{"step": 560, "epoch": 0.03774856757667678, "timestamp": 1786574651.315112, "loss": 3.3621952056884767, "grad_norm": 0.478515625, "learning_rate": 0.0007, "train/total_time_seconds": 150.32971427217126, "train/time_per_step_avg": 0.2673027390986681, "train/epoch_time_elapsed": 179.28440859541297, "train/estimated_remaining_minutes": 8.679751359762268}
+{"step": 580, "epoch": 0.03909673070441524, "timestamp": 1786574657.6687937, "loss": 3.301148223876953, "grad_norm": 0.478515625, "learning_rate": 0.0007, "train/total_time_seconds": 155.6691726744175, "train/time_per_step_avg": 0.2669852772727609, "train/epoch_time_elapsed": 185.63809048756957, "train/estimated_remaining_minutes": 8.588644009623033}
+{"step": 600, "epoch": 0.04044489383215369, "timestamp": 1786574664.274563, "loss": 3.266124725341797, "grad_norm": 0.44140625, "learning_rate": 0.0007, "train/total_time_seconds": 161.24586637690663, "train/time_per_step_avg": 0.26936037838459015, "train/epoch_time_elapsed": 192.2438549697399, "train/estimated_remaining_minutes": 8.510198503225629}
+{"step": 620, "epoch": 0.04179305695989215, "timestamp": 1786574670.9500022, "loss": 3.1991281509399414, "grad_norm": 0.58203125, "learning_rate": 0.0007, "train/total_time_seconds": 166.63569385558367, "train/time_per_step_avg": 0.2696164564415813, "train/epoch_time_elapsed": 198.919298350811, "train/estimated_remaining_minutes": 8.421373775497239}
+{"step": 640, "epoch": 0.043141220087630605, "timestamp": 1786574677.2724392, "loss": 3.175183868408203, "grad_norm": 0.51953125, "learning_rate": 0.0007, "train/total_time_seconds": 171.97098869085312, "train/time_per_step_avg": 0.26961863923817875, "train/epoch_time_elapsed": 205.24173552542925, "train/estimated_remaining_minutes": 8.329844764713197}
+{"step": 660, "epoch": 0.044489383215369056, "timestamp": 1786574683.574097, "loss": 3.1185443878173826, "grad_norm": 0.443359375, "learning_rate": 0.0007, "train/total_time_seconds": 177.30246318131685, "train/time_per_step_avg": 0.26972748909145594, "train/epoch_time_elapsed": 211.54339312389493, "train/estimated_remaining_minutes": 8.238296269030885}
+{"step": 680, "epoch": 0.045837546343107514, "timestamp": 1786574689.957703, "loss": 3.091288757324219, "grad_norm": 0.447265625, "learning_rate": 0.0007, "train/total_time_seconds": 182.6907045468688, "train/time_per_step_avg": 0.27021531872451304, "train/epoch_time_elapsed": 217.92699952423573, "train/estimated_remaining_minutes": 8.149438291061305}
+{"step": 700, "epoch": 0.04718570947084597, "timestamp": 1786574696.3050113, "loss": 3.0479175567626955, "grad_norm": 0.400390625, "learning_rate": 0.0007, "train/total_time_seconds": 188.0292291790247, "train/time_per_step_avg": 0.2678336280211806, "train/epoch_time_elapsed": 224.27430825307965, "train/estimated_remaining_minutes": 8.058395536243916}
+{"step": 720, "epoch": 0.04853387259858443, "timestamp": 1786574702.9306242, "loss": 3.012004280090332, "grad_norm": 0.39453125, "learning_rate": 0.0007, "train/total_time_seconds": 193.37752113491297, "train/time_per_step_avg": 0.267418272793293, "train/epoch_time_elapsed": 230.89992128685117, "train/estimated_remaining_minutes": 7.967870083799655}
+{"step": 740, "epoch": 0.04988203572632288, "timestamp": 1786574709.2385693, "loss": 2.973306655883789, "grad_norm": 0.40625, "learning_rate": 0.0007, "train/total_time_seconds": 198.70704197138548, "train/time_per_step_avg": 0.2673605328053236, "train/epoch_time_elapsed": 237.20786146447062, "train/estimated_remaining_minutes": 7.876675537604469}
+{"step": 760, "epoch": 0.05123019885406134, "timestamp": 1786574715.6162934, "loss": 2.9569366455078123, "grad_norm": 0.41015625, "learning_rate": 0.0007, "train/total_time_seconds": 204.0810208916664, "train/time_per_step_avg": 0.2677855771034956, "train/epoch_time_elapsed": 243.58559001237154, "train/estimated_remaining_minutes": 7.787302112971481}