Training in progress, step 2000

last-checkpoint/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "DeepESP/gpt2-spanish",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0a9b8e781a9adc7b5206dce36c417fd75247f48535f73b8a0ff22cd1819064
+size 995604017

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47f80fd3abb09376d66de448ae040a39e35f293dd81734c87eb836d4bd0ff71
+size 510396521

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d28830c94d92b6d19326a0184936f2862087877e8af1a427622e66aefb96fa
+size 14503

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da848d6aca6f5529d88e638c4fb471ab39c2f011f2295ed728f24a9ae6b4786
+size 623

last-checkpoint/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 3.926462411880493,
+  "best_model_checkpoint": "./ES_corlec/checkpoint-2000",
+  "epoch": 0.3965107057890563,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9880573248407645e-05,
+      "loss": 4.1429,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9681528662420383e-05,
+      "loss": 3.7366,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9482484076433124e-05,
+      "loss": 3.5836,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9283439490445862e-05,
+      "loss": 3.4588,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 3.926462411880493,
+      "eval_runtime": 958.5106,
+      "eval_samples_per_second": 42.233,
+      "eval_steps_per_second": 2.641,
+      "step": 2000
+    }
+  ],
+  "max_steps": 50440,
+  "num_train_epochs": 10,
+  "total_flos": 2449612800000000.0,
+  "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:f92189c0b6c23d5f9d7c3d130adcc7471dc4c86b70cac88476f76de70c090a5a
+size 3055

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea0473e9c607af55cb0af2f38e543d3b953dd7cbed60a5f660fff9faa18d40b
+oid sha256:f47f80fd3abb09376d66de448ae040a39e35f293dd81734c87eb836d4bd0ff71
 size 510396521

stdout.slurm

@@ -0,0 +1,4 @@
+{'loss': 4.1429, 'learning_rate': 1.9880573248407645e-05, 'epoch': 0.1}
+{'loss': 3.7366, 'learning_rate': 1.9681528662420383e-05, 'epoch': 0.2}
+{'loss': 3.5836, 'learning_rate': 1.9482484076433124e-05, 'epoch': 0.3}
+{'loss': 3.4588, 'learning_rate': 1.9283439490445862e-05, 'epoch': 0.4}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e59540712d7c8d6b9be5c69d0df41f78a36058553ff27ee00da306a9a8da6a37
+oid sha256:f92189c0b6c23d5f9d7c3d130adcc7471dc4c86b70cac88476f76de70c090a5a
 size 3055