Upload folder using huggingface_hub

slots/0/checkpoint-27/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "TwinyForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 128,
+  "model_type": "twiny",
+  "neftune_alpha": 0.0,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "num_key_value_heads": 3,
+  "qk_norm": true,
+  "rezero_init": 1.0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

slots/0/checkpoint-27/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0005264168656164975,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.9496920948759166e-05,
+      "grad_norm": 243.27565002441406,
+      "learning_rate": 5e-05,
+      "loss": 64.64595031738281,
+      "step": 1
+    },
+    {
+      "epoch": 0.00038993841897518337,
+      "grad_norm": 21.290706634521484,
+      "learning_rate": 4.9999997291360456e-05,
+      "loss": 19.46853316457648,
+      "step": 20
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 128228,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 43147237386240.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}