Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-350m",
+  "_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": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

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:b2bb88839db9a955142114b0e76d39e26a142b8977b4728631688d07d165e23a
+size 1324830880

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515f491249e7958cf9a7a470705046756ae81353f7b8f0cd47ce02c6286833ab
+size 2649896094

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fed6c366e6b4d634f87f865713fdb70cf06e8a7a7c65ee518a6e3d2b2e6bcf
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0aaaa3515571c8a17b1e2c93ba8bd4a56602e00b0c7a9ae99db5b0f312b3d10
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.9037830233573914,
+  "best_model_checkpoint": "./opt_trained3/checkpoint-2643",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2643,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18917896329928113,
+      "grad_norm": 14.101566314697266,
+      "learning_rate": 9.784324123011948e-05,
+      "loss": 0.9633,
+      "step": 500
+    },
+    {
+      "epoch": 0.37835792659856227,
+      "grad_norm": 6.891010761260986,
+      "learning_rate": 9.14928228350961e-05,
+      "loss": 0.908,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5675368898978433,
+      "grad_norm": 11.300192832946777,
+      "learning_rate": 8.150526293753795e-05,
+      "loss": 0.9047,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7567158531971245,
+      "grad_norm": 5.797523021697998,
+      "learning_rate": 6.875604231051344e-05,
+      "loss": 0.9013,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9458948164964056,
+      "grad_norm": 9.209771156311035,
+      "learning_rate": 5.4362720963179184e-05,
+      "loss": 0.9028,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9037830233573914,
+      "eval_runtime": 1653.9704,
+      "eval_samples_per_second": 19.886,
+      "eval_steps_per_second": 4.972,
+      "step": 2643
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5286,
+  "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": 2.0851212666249216e+17,
+  "train_batch_size": 14,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe7bd86a461c37c8ba7d0715f243e5104dddcebcba1d9de1048a8cc77c508b7
+size 5368