Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "down_proj",
+    "q_proj",
     "k_proj",
     "o_proj",
-    "up_proj",
     "gate_proj",
-    "down_proj",
-    "q_proj",
-    "v_proj"
+    "up_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 sha256:067386c634089e509837267ab1ec2304d71a4f102df64b1935c6b958ba71a318
+oid sha256:1647e4672b5305331add1c8c3c040df697445b4efa2f7486ddff6e6e064c0dcc
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcafcaeb8f0427dd716fbca104510c151cb078693d1b4eaab699482d74336e3f
+oid sha256:9bd13b841899d4b29a01b78edf5776f8bfbbaa48b189a39b2483a9d9a2fc5329
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33799e390fc551a91dceaf2550988dbd7c80389c682f07c9be0447bc39719a8a
+oid sha256:f9d23ddc432877538e1482ac7028d4be4d6733be4d7e298176c8e6b45a4685c3
 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": 0.0009315323707498836,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.012109920819748486,
+  "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": 0.0009315323707498836,
       "eval_loss": 2.67449688911438,
-      "eval_runtime": 54.9348,
-      "eval_samples_per_second": 8.246,
-      "eval_steps_per_second": 4.132,
+      "eval_runtime": 54.9548,
+      "eval_samples_per_second": 8.243,
+      "eval_steps_per_second": 4.131,
       "step": 1
+    },
+    {
+      "epoch": 0.004657661853749418,
+      "grad_norm": 1.050082802772522,
+      "learning_rate": 5e-05,
+      "loss": 2.3571,
+      "step": 5
+    },
+    {
+      "epoch": 0.009315323707498836,
+      "grad_norm": 1.03178071975708,
+      "learning_rate": 0.0001,
+      "loss": 2.2236,
+      "step": 10
+    },
+    {
+      "epoch": 0.009315323707498836,
+      "eval_loss": 2.541896104812622,
+      "eval_runtime": 55.3938,
+      "eval_samples_per_second": 8.178,
+      "eval_steps_per_second": 4.098,
+      "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": 184956424814592.0,
+  "total_flos": 2404433522589696.0,
   "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:a7a783e2cb61f1f43d6afcdbdcdfbd95b4109b5c47233201292d879218f18c04
+oid sha256:437e6c44cf818a520a480862c3b92c9bdcd57c2f883416df0c4a13a3d8e335dd
 size 6776