Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,30 @@
+{
+  "_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": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 51291,
+  "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": "4.52.4"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce2082edf266e6f182dc36882c0e8873eb663423b5c9b9c86d50df896c5fd1c
+size 504109968

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d6383e00324023d50b8bfe8304334dc4c40fecdfb3672be47f255427845277
+size 1008339066

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a065e52fd1cd091490253122882a9451037f261eed4bb923ccae9f878dd9e127
+size 14244

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce3543cfd9408629df4e2940ee147ee544a6b8b337ca4f18a0f0c754c922bae
+size 988

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a032a18f99851eafb2bed1e48f688ab223dbfac47c2dab29d5379cfc240219fb
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_global_step": 6,
+  "best_metric": 5.9545183181762695,
+  "best_model_checkpoint": "./opt_thinker_ckpts/checkpoint-6",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.9545183181762695,
+      "eval_runtime": 1.0261,
+      "eval_samples_per_second": 8.771,
+      "eval_steps_per_second": 4.873,
+      "step": 6
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 18,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 78123255552000.0,
+  "train_batch_size": 2,
+  "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:d6fcf86d4764f326a1095e09bc7b190fa9d03e5a26d8d3fff2e041bc6c57dd55
+size 5304