Training in progress, step 500, checkpoint

checkpoint-500/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "Grogros/gpt2-kgw-k1-delta2.0-LearnabilityScratch",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50263
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd3ac7e42b640ff87ce3deb4fe9e39e1585f0be019ba961b065cd0311126638
+size 497792640

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f6a8dcc63ea00571cf9af2182fdff3c91f8e8139cad240a699a991b2fec26d
+size 1385018

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7836a15b0a818d03d3c518f7051540787964b1691a1099d33911e7f6ae541af
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f20d3fd8f2ca072c88294e1b245d2fc0feec4c84032b4ae4d3711181320962
+size 1064

checkpoint-500/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.033417992247025796,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00334179922470258,
+      "grad_norm": 133.46705627441406,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 4.7441,
+      "step": 50
+    },
+    {
+      "epoch": 0.00668359844940516,
+      "grad_norm": 2.1861348152160645,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.9603,
+      "step": 100
+    },
+    {
+      "epoch": 0.01002539767410774,
+      "grad_norm": 1.7571604251861572,
+      "learning_rate": 1.2e-05,
+      "loss": 0.8109,
+      "step": 150
+    },
+    {
+      "epoch": 0.01336719689881032,
+      "grad_norm": 1.7635782957077026,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.7511,
+      "step": 200
+    },
+    {
+      "epoch": 0.016708996123512898,
+      "grad_norm": 1.6808218955993652,
+      "learning_rate": 2e-05,
+      "loss": 0.7345,
+      "step": 250
+    },
+    {
+      "epoch": 0.02005079534821548,
+      "grad_norm": 1.8249382972717285,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.6971,
+      "step": 300
+    },
+    {
+      "epoch": 0.02339259457291806,
+      "grad_norm": 1.4581658840179443,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 0.6754,
+      "step": 350
+    },
+    {
+      "epoch": 0.02673439379762064,
+      "grad_norm": 2.1062357425689697,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.6455,
+      "step": 400
+    },
+    {
+      "epoch": 0.030076193022323217,
+      "grad_norm": 1.9214518070220947,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 0.6606,
+      "step": 450
+    },
+    {
+      "epoch": 0.033417992247025796,
+      "grad_norm": 2.335805654525757,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.631,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8361345024000000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4877b2bb6aa02f44091dbac6e0bcae91c9429765a2cc6ddc09d654f5c77718f9
+size 5368