Training in progress, step 2500, checkpoint

checkpoint-2500/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "Grogros/dmWM-llama-3.2-1B-Instruct-OWTWM-DistillationWM-Al4-wmToken-d4-a0.1-v2-meta-OWT",
+  "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": 128257
+}

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:c8f45a20a10a6b076382e1028dece86001e0281ce4bb3a0fadba228b5d20d531
+size 4943282520

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611ed1f44b60e77d2040f92d8f389880ed10c53041b3a33739a482a00f668551
+size 3724602

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f64536942d475b96a7eaaefe437b68ec0e312da7567860fd76d266d073caabab
+size 14244

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfda160a9c70923068c261961532d9255f61746ab719f17a35aebc6ad8ff53e8
+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": 2.5270798206329346,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 3.1564,
+      "step": 100
+    },
+    {
+      "epoch": 0.006127357117691212,
+      "grad_norm": 2.604092597961426,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.1166,
+      "step": 200
+    },
+    {
+      "epoch": 0.009191035676536818,
+      "grad_norm": 2.5005924701690674,
+      "learning_rate": 3e-06,
+      "loss": 3.0905,
+      "step": 300
+    },
+    {
+      "epoch": 0.012254714235382424,
+      "grad_norm": 2.7525177001953125,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.0652,
+      "step": 400
+    },
+    {
+      "epoch": 0.015318392794228029,
+      "grad_norm": 2.5251283645629883,
+      "learning_rate": 5e-06,
+      "loss": 3.0351,
+      "step": 500
+    },
+    {
+      "epoch": 0.018382071353073636,
+      "grad_norm": 2.6771860122680664,
+      "learning_rate": 6e-06,
+      "loss": 3.0028,
+      "step": 600
+    },
+    {
+      "epoch": 0.02144574991191924,
+      "grad_norm": 2.4799458980560303,
+      "learning_rate": 7e-06,
+      "loss": 3.0007,
+      "step": 700
+    },
+    {
+      "epoch": 0.024509428470764847,
+      "grad_norm": 2.8402369022369385,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.9753,
+      "step": 800
+    },
+    {
+      "epoch": 0.027573107029610452,
+      "grad_norm": 2.446842908859253,
+      "learning_rate": 9e-06,
+      "loss": 2.9737,
+      "step": 900
+    },
+    {
+      "epoch": 0.030636785588456058,
+      "grad_norm": 2.3989391326904297,
+      "learning_rate": 1e-05,
+      "loss": 2.9618,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03370046414730166,
+      "grad_norm": 2.469160795211792,
+      "learning_rate": 9.99695413509548e-06,
+      "loss": 2.928,
+      "step": 1100
+    },
+    {
+      "epoch": 0.03676414270614727,
+      "grad_norm": 2.4107494354248047,
+      "learning_rate": 9.987820251299121e-06,
+      "loss": 2.9214,
+      "step": 1200
+    },
+    {
+      "epoch": 0.039827821264992874,
+      "grad_norm": 2.540278911590576,
+      "learning_rate": 9.972609476841368e-06,
+      "loss": 2.9198,
+      "step": 1300
+    },
+    {
+      "epoch": 0.04289149982383848,
+      "grad_norm": 2.4398670196533203,
+      "learning_rate": 9.951340343707852e-06,
+      "loss": 2.9182,
+      "step": 1400
+    },
+    {
+      "epoch": 0.04595517838268409,
+      "grad_norm": 2.49687123298645,
+      "learning_rate": 9.924038765061042e-06,
+      "loss": 2.8994,
+      "step": 1500
+    },
+    {
+      "epoch": 0.049018856941529694,
+      "grad_norm": 2.4655182361602783,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 2.8805,
+      "step": 1600
+    },
+    {
+      "epoch": 0.0520825355003753,
+      "grad_norm": 2.4170656204223633,
+      "learning_rate": 9.851478631379982e-06,
+      "loss": 2.8829,
+      "step": 1700
+    },
+    {
+      "epoch": 0.055146214059220905,
+      "grad_norm": 2.362334966659546,
+      "learning_rate": 9.806308479691595e-06,
+      "loss": 2.8891,
+      "step": 1800
+    },
+    {
+      "epoch": 0.058209892618066514,
+      "grad_norm": 2.426173210144043,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 2.875,
+      "step": 1900
+    },
+    {
+      "epoch": 0.061273571176912116,
+      "grad_norm": 2.6380629539489746,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 2.879,
+      "step": 2000
+    },
+    {
+      "epoch": 0.06433724973575772,
+      "grad_norm": 2.5123095512390137,
+      "learning_rate": 9.635919272833938e-06,
+      "loss": 2.8622,
+      "step": 2100
+    },
+    {
+      "epoch": 0.06740092829460333,
+      "grad_norm": 2.3789472579956055,
+      "learning_rate": 9.567727288213005e-06,
+      "loss": 2.8669,
+      "step": 2200
+    },
+    {
+      "epoch": 0.07046460685344894,
+      "grad_norm": 2.387221336364746,
+      "learning_rate": 9.493970231495836e-06,
+      "loss": 2.8641,
+      "step": 2300
+    },
+    {
+      "epoch": 0.07352828541229454,
+      "grad_norm": 2.4947221279144287,
+      "learning_rate": 9.414737964294636e-06,
+      "loss": 2.8525,
+      "step": 2400
+    },
+    {
+      "epoch": 0.07659196397114015,
+      "grad_norm": 2.390381097793579,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 2.8497,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10000,
+  "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": false
+      },
+      "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 sha256:343fd12cd57f4f5c4c4d092162b0058e69041ee73092ab79cda1f02d0d79adab
+size 5368