Training in progress, epoch 0, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-125m",
+  "_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:d503853e3752c1d2acfb70d8010c636331c5361b828446d3a72b4ef7e6e500cd
+size 500979600

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7564b9dea97b53e6c8165c1f1f78ef564901bfd2a91265ff04d60b76344c60bb
+size 1002078330

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dba13805ccab6ab361a19ec0b6ab90650597c58b4e25b4c574871d6ae4529d1
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9dcc1d0e5adec204cacb9a61e6122f6644f24cb70ae169677431c21cadecba0
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 1.013350248336792,
+  "best_model_checkpoint": "./opt_trained3/checkpoint-609",
+  "epoch": 0.998769987699877,
+  "eval_steps": 500,
+  "global_step": 609,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8200082000820008,
+      "grad_norm": 3.336149215698242,
+      "learning_rate": 9.835913054681877e-05,
+      "loss": 1.0546,
+      "step": 500
+    },
+    {
+      "epoch": 0.998769987699877,
+      "eval_loss": 1.013350248336792,
+      "eval_runtime": 259.9403,
+      "eval_samples_per_second": 50.035,
+      "eval_steps_per_second": 12.511,
+      "step": 609
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6090,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 2.419219229184e+16,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432b24e0a454c6ba118d533189ffa32a4ef3f0654798d68a647380ab38384532
+size 5368