Training in progress, step 10

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69ebf165abb785e8e69f7a31ea603ab84d4d086cadb565695d4afe72370385fd
+oid sha256:8f5065fd2750a7eba93fd64dbecadc648c773e3c8fe9018fc06397d64f6678b5
 size 4372840

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.8363636363636364,
+    "eval_loss": 0.561950147151947,
+    "eval_runtime": 67.7082,
+    "eval_samples": 7,
+    "eval_samples_per_second": 0.325,
+    "eval_steps_per_second": 0.325,
+    "test_samples": 22,
+    "total_flos": 3.417506073386496e+16,
+    "train_loss": 0.7223965204679049,
+    "train_runtime": 1358.774,
+    "train_samples": 110,
+    "train_samples_per_second": 0.243,
+    "train_steps_per_second": 0.029
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.8363636363636364,
+    "eval_loss": 0.575309157371521,
+    "eval_runtime": 21.2797,
+    "eval_samples": 7,
+    "eval_samples_per_second": 0.329,
+    "eval_steps_per_second": 0.329
+}

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.8363636363636364,
+    "eval_loss": 0.561950147151947,
+    "eval_runtime": 67.7082,
+    "eval_samples_per_second": 0.325,
+    "eval_steps_per_second": 0.325,
+    "test_samples": 22
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.8363636363636364,
+    "total_flos": 3.417506073386496e+16,
+    "train_loss": 0.7223965204679049,
+    "train_runtime": 1358.774,
+    "train_samples": 110,
+    "train_samples_per_second": 0.243,
+    "train_steps_per_second": 0.029
+}

trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.575309157371521,
+  "best_model_checkpoint": "/home/paperspace/mmdoc/outputs/Damarcode_AB_v1_20241129_qwen_v2/checkpoint-30",
+  "epoch": 2.8363636363636364,
+  "eval_steps": 10,
+  "global_step": 39,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.16364361345767975,
+      "learning_rate": 0.0002,
+      "loss": 0.9083,
+      "step": 10
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "eval_loss": 0.8434579968452454,
+      "eval_runtime": 21.3435,
+      "eval_samples_per_second": 0.328,
+      "eval_steps_per_second": 0.328,
+      "step": 10
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.26582711935043335,
+      "learning_rate": 0.0002,
+      "loss": 0.7852,
+      "step": 20
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "eval_loss": 0.7271223068237305,
+      "eval_runtime": 21.286,
+      "eval_samples_per_second": 0.329,
+      "eval_steps_per_second": 0.329,
+      "step": 20
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 1.215633749961853,
+      "learning_rate": 0.0002,
+      "loss": 0.6799,
+      "step": 30
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "eval_loss": 0.575309157371521,
+      "eval_runtime": 21.239,
+      "eval_samples_per_second": 0.33,
+      "eval_steps_per_second": 0.33,
+      "step": 30
+    },
+    {
+      "epoch": 2.8363636363636364,
+      "step": 39,
+      "total_flos": 3.417506073386496e+16,
+      "train_loss": 0.7223965204679049,
+      "train_runtime": 1358.774,
+      "train_samples_per_second": 0.243,
+      "train_steps_per_second": 0.029
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 39,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.417506073386496e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}