Training in progress, step 2500, checkpoint

checkpoint-2500/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "Grogros/dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-d4-a0.25",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

checkpoint-2500/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad91ed3365c3ba58234bf7c3015559e2f586d73aab6520378bc712f043fdc96
+size 4943274328

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6c81b492b9a5c71c93520de5b5edd2450100ff03b1d1b8c7b736e5343e7157
+size 3724602

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e974499082141155c9aecccfd7f7b244a293a307a51c33f9c947773acee209
+size 14244

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18fdf17d77d34a6dc43fb505d89df155af8f574eb1ddc8da3e2d900c61723cd5
+size 1064

checkpoint-2500/trainer_state.json

@@ -0,0 +1,208 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07659196397114015,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003063678558845606,
+      "grad_norm": 2.935556411743164,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.006127357117691212,
+      "grad_norm": 2.975250005722046,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.9241,
+      "step": 200
+    },
+    {
+      "epoch": 0.009191035676536818,
+      "grad_norm": 2.8458304405212402,
+      "learning_rate": 9.987820251299121e-06,
+      "loss": 2.9023,
+      "step": 300
+    },
+    {
+      "epoch": 0.012254714235382424,
+      "grad_norm": 2.9931607246398926,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 2.8897,
+      "step": 400
+    },
+    {
+      "epoch": 0.015318392794228029,
+      "grad_norm": 2.8005623817443848,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 2.8751,
+      "step": 500
+    },
+    {
+      "epoch": 0.018382071353073636,
+      "grad_norm": 2.8539531230926514,
+      "learning_rate": 9.414737964294636e-06,
+      "loss": 2.8567,
+      "step": 600
+    },
+    {
+      "epoch": 0.02144574991191924,
+      "grad_norm": 2.6978955268859863,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 2.8676,
+      "step": 700
+    },
+    {
+      "epoch": 0.024509428470764847,
+      "grad_norm": 2.8115577697753906,
+      "learning_rate": 8.596699001693257e-06,
+      "loss": 2.8524,
+      "step": 800
+    },
+    {
+      "epoch": 0.027573107029610452,
+      "grad_norm": 2.6445884704589844,
+      "learning_rate": 8.078307376628292e-06,
+      "loss": 2.8612,
+      "step": 900
+    },
+    {
+      "epoch": 0.030636785588456058,
+      "grad_norm": 2.5841586589813232,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 2.8564,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03370046414730166,
+      "grad_norm": 2.6466314792633057,
+      "learning_rate": 6.873032967079562e-06,
+      "loss": 2.8298,
+      "step": 1100
+    },
+    {
+      "epoch": 0.03676414270614727,
+      "grad_norm": 2.583447217941284,
+      "learning_rate": 6.209609477998339e-06,
+      "loss": 2.8302,
+      "step": 1200
+    },
+    {
+      "epoch": 0.039827821264992874,
+      "grad_norm": 2.628443956375122,
+      "learning_rate": 5.522642316338268e-06,
+      "loss": 2.8323,
+      "step": 1300
+    },
+    {
+      "epoch": 0.04289149982383848,
+      "grad_norm": 2.5776467323303223,
+      "learning_rate": 4.825502516487497e-06,
+      "loss": 2.8347,
+      "step": 1400
+    },
+    {
+      "epoch": 0.04595517838268409,
+      "grad_norm": 2.7446603775024414,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 2.8188,
+      "step": 1500
+    },
+    {
+      "epoch": 0.049018856941529694,
+      "grad_norm": 2.671675205230713,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 2.8029,
+      "step": 1600
+    },
+    {
+      "epoch": 0.0520825355003753,
+      "grad_norm": 2.616115093231201,
+      "learning_rate": 2.8081442660546126e-06,
+      "loss": 2.8085,
+      "step": 1700
+    },
+    {
+      "epoch": 0.055146214059220905,
+      "grad_norm": 2.603142738342285,
+      "learning_rate": 2.204035482646267e-06,
+      "loss": 2.8186,
+      "step": 1800
+    },
+    {
+      "epoch": 0.058209892618066514,
+      "grad_norm": 2.7121975421905518,
+      "learning_rate": 1.6543469682057105e-06,
+      "loss": 2.8059,
+      "step": 1900
+    },
+    {
+      "epoch": 0.061273571176912116,
+      "grad_norm": 2.7854678630828857,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 2.8125,
+      "step": 2000
+    },
+    {
+      "epoch": 0.06433724973575772,
+      "grad_norm": 2.736281394958496,
+      "learning_rate": 7.597595192178702e-07,
+      "loss": 2.7972,
+      "step": 2100
+    },
+    {
+      "epoch": 0.06740092829460333,
+      "grad_norm": 2.678331136703491,
+      "learning_rate": 4.322727117869951e-07,
+      "loss": 2.8067,
+      "step": 2200
+    },
+    {
+      "epoch": 0.07046460685344894,
+      "grad_norm": 2.682953357696533,
+      "learning_rate": 1.9369152030840553e-07,
+      "loss": 2.8054,
+      "step": 2300
+    },
+    {
+      "epoch": 0.07352828541229454,
+      "grad_norm": 2.732428789138794,
+      "learning_rate": 4.865965629214819e-08,
+      "loss": 2.7976,
+      "step": 2400
+    },
+    {
+      "epoch": 0.07659196397114015,
+      "grad_norm": 2.747227191925049,
+      "learning_rate": 0.0,
+      "loss": 2.7989,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3916038848512e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ebc2147cd7d387a793a437f5833050acc1b742d42594bd97dae83098ab49ba1
+size 5368