Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "ccore/getcode-350m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 49152
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.47.0"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2e096f0f51e0c0eb883ddad1c7b1ff62a258cdabda750fcb19250f8a3ab5d11
+size 1447317080

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a6b0997847f2b0ada221298830b2deb0ed4b07bb97ee70cf344ddceb01e46a
+size 2894813242

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7882a938f81b5d65dc6792ab79e376aa68f8b34a702d85d3e51323da0429a7e5
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": 0.5563850402832031,
+  "best_model_checkpoint": "./opt_trained2/checkpoint-43",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 43,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5563850402832031,
+      "eval_runtime": 16.8934,
+      "eval_samples_per_second": 17.758,
+      "eval_steps_per_second": 4.44,
+      "step": 43
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "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": 1968190425273600.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79588ef006b4c033f0fd3d59d0987acd4668042b7cfd96edaf0a29cb13b029d
+size 5368