Initial upload of CosmoGPT2-Mini model files

config.json

@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "bfloat16",
+  "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,
+  "pad_token_id": null,
+  "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
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c493c9afdf24d504ae73a01e1f66a6c70fad231a2ccc3a23f00448f69c66d7d4
+size 248894656

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498858c6dc3fd7035f6eeb004f86cec42f09bdb3c1d85ae43e4bcfebf76deb58
+size 497885643

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d9a3585be330baac0fa76dc042507447958421f2bd245ba0cc3f3d33f6d724
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8083cb28f9178670969e8954135f0609f0eac2102b31887abccd667da0fb9cf
+size 1465

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,120 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5614035087719298,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.056140350877192984,
+      "grad_norm": 3.546875,
+      "learning_rate": 2.4750000000000002e-05,
+      "loss": 3.1684613037109375,
+      "step": 100
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 2.625,
+      "learning_rate": 4.975e-05,
+      "loss": 2.9828875732421873,
+      "step": 200
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 2.75,
+      "learning_rate": 4.38125e-05,
+      "loss": 2.9039926147460937,
+      "step": 300
+    },
+    {
+      "epoch": 0.22456140350877193,
+      "grad_norm": 2.703125,
+      "learning_rate": 3.75625e-05,
+      "loss": 2.862659912109375,
+      "step": 400
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 2.46875,
+      "learning_rate": 3.13125e-05,
+      "loss": 2.8550177001953125,
+      "step": 500
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "eval_loss": 2.695997476577759,
+      "eval_runtime": 112.3251,
+      "eval_samples_per_second": 13.354,
+      "eval_steps_per_second": 1.674,
+      "step": 500
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 2.5625,
+      "learning_rate": 2.50625e-05,
+      "loss": 2.8371957397460936,
+      "step": 600
+    },
+    {
+      "epoch": 0.3929824561403509,
+      "grad_norm": 2.453125,
+      "learning_rate": 1.88125e-05,
+      "loss": 2.83647705078125,
+      "step": 700
+    },
+    {
+      "epoch": 0.44912280701754387,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.2562499999999999e-05,
+      "loss": 2.8517510986328123,
+      "step": 800
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 2.28125,
+      "learning_rate": 6.3125e-06,
+      "loss": 2.8428424072265623,
+      "step": 900
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 2.421875,
+      "learning_rate": 6.250000000000001e-08,
+      "loss": 2.8378897094726563,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "eval_loss": 2.6861302852630615,
+      "eval_runtime": 111.8875,
+      "eval_samples_per_second": 13.406,
+      "eval_steps_per_second": 1.68,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1000,
+  "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": 4180672512000000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:730d0150783c2222a6815ae0702bb5fa06d9cdde68d131f8f95848bb25435f9b
+size 5201