Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
+    "down_proj",
+    "q_proj",
     "k_proj",
     "o_proj",
-    "q_proj",
-    "down_proj",
-    "gate_proj"
+    "gate_proj",
+    "up_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c45f69fafde611e0235ecfe131c73d8dfda5c84980dc7f6e1665cfd0f7148e91
+oid sha256:2592befc98f86aa9c39f766a20af328d4d18f5c7c775f8e1eca91c4b76b20dfc
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:907d8f8caff76dec0f748f11f64a36bcebb9a25a53daef9ec11f1a07a4ee993c
+oid sha256:65abf4da535795bea55a70667eb47631177f9697f84bf2bc5806e450a88651a3
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35bc92371de2dc48fc3204fa3557c31d40e6fd4491378f9e7a4c4fa05636082a
+oid sha256:80d2fa6d0958c9fdd25d8902864c6b85a1f48f760bf117b29d82e62027fc276b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010362694300518135,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.13471502590673576,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.010362694300518135,
       "eval_loss": 3.649900197982788,
-      "eval_runtime": 0.7537,
-      "eval_samples_per_second": 54.402,
-      "eval_steps_per_second": 27.864,
+      "eval_runtime": 0.7545,
+      "eval_samples_per_second": 54.343,
+      "eval_steps_per_second": 27.834,
       "step": 1
+    },
+    {
+      "epoch": 0.05181347150259067,
+      "grad_norm": 2.8373703956604004,
+      "learning_rate": 5e-05,
+      "loss": 3.5652,
+      "step": 5
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "grad_norm": 2.706880569458008,
+      "learning_rate": 0.0001,
+      "loss": 3.4354,
+      "step": 10
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "eval_loss": 3.3804771900177,
+      "eval_runtime": 0.7498,
+      "eval_samples_per_second": 54.684,
+      "eval_steps_per_second": 28.009,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3429265047552.0,
+  "total_flos": 44580445618176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c551c9f7f5f4a66ff8bbb865eef447fb7aa7db30d2a90a1ea2bc5e1572b8008
+oid sha256:3deb8db21df51bdd3dd533930565ad8646049734528e7771fd35a1c9fc253333
 size 6776