Fin de l'entraînement

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 6.851921081542969,
+    "eval_mae": Infinity,
+    "eval_mse": Infinity,
+    "eval_runtime": 1.4635,
+    "eval_samples_per_second": 6.833,
+    "eval_steps_per_second": 1.367,
+    "total_flos": 0.0,
+    "train_loss": 16.987167358398438,
+    "train_runtime": 31.9592,
+    "train_samples_per_second": 9.762,
+    "train_steps_per_second": 0.25
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 6.851921081542969,
+    "eval_mae": Infinity,
+    "eval_mse": Infinity,
+    "eval_runtime": 1.4635,
+    "eval_samples_per_second": 6.833,
+    "eval_steps_per_second": 1.367
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 0.0,
+    "train_loss": 16.987167358398438,
+    "train_runtime": 31.9592,
+    "train_samples_per_second": 9.762,
+    "train_steps_per_second": 0.25
+}

trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_global_step": null,
+  "best_metric": Infinity,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.967957496643066,
+      "eval_mae": Infinity,
+      "eval_mse": Infinity,
+      "eval_runtime": 1.2935,
+      "eval_samples_per_second": 7.731,
+      "eval_steps_per_second": 1.546,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.95061731338501,
+      "eval_mae": Infinity,
+      "eval_mse": Infinity,
+      "eval_runtime": 1.3806,
+      "eval_samples_per_second": 7.243,
+      "eval_steps_per_second": 1.449,
+      "step": 4
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.900310516357422,
+      "eval_mae": Infinity,
+      "eval_mse": Infinity,
+      "eval_runtime": 1.5227,
+      "eval_samples_per_second": 6.567,
+      "eval_steps_per_second": 1.313,
+      "step": 6
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 6.851921081542969,
+      "eval_mae": Infinity,
+      "eval_mse": Infinity,
+      "eval_runtime": 1.201,
+      "eval_samples_per_second": 8.327,
+      "eval_steps_per_second": 1.665,
+      "step": 8
+    },
+    {
+      "epoch": 4.0,
+      "step": 8,
+      "total_flos": 0.0,
+      "train_loss": 16.987167358398438,
+      "train_runtime": 31.9592,
+      "train_samples_per_second": 9.762,
+      "train_steps_per_second": 0.25
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 8,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}