Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "ccore/getcode-v2",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.47.0"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a9a39b49dc8af48cc4147e9762b14c8e860aef41fd18ec146ac27c65dc6812
+size 500979600

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35af0ead48eb3e1b4330ce43fd33be1a5ff3cebe1cf0458eba7bb56fce618b03
+size 1002078330

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243bed054e6ca95566a31f84929c545f9505688d6a662df2d1ba4f4954f9e518
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57298e368684a7f74b8580ab500ef876b797e959380e8c09da0e2d665556ed4b
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 0.9235808253288269,
+  "best_model_checkpoint": "./opt_trained3/checkpoint-1361",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1361,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3675457134981163,
+      "grad_norm": 1.4956048727035522,
+      "learning_rate": 9.189154158168292e-05,
+      "loss": 0.939,
+      "step": 500
+    },
+    {
+      "epoch": 0.7350914269962326,
+      "grad_norm": 1.0351307392120361,
+      "learning_rate": 7.019605024359474e-05,
+      "loss": 0.9314,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9235808253288269,
+      "eval_runtime": 760.9492,
+      "eval_samples_per_second": 50.851,
+      "eval_steps_per_second": 12.713,
+      "step": 1361
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 6.8780176144128e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ece721c919142a4326911838f17a116511a7a472a5798db73eacd9dc97d85ed
+size 5368