Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
-    "o_proj",
-    "q_proj",
     "down_proj",
+    "q_proj",
+    "k_proj",
     "up_proj",
+    "v_proj",
+    "o_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11cd6e0cdeff975da288609b55ef898aaec77649c3bed28cd8634c90df7b5e74
+oid sha256:5769af024b5e7958d9d18ba9f9f6337919f184033024e32ce83e7a98e3de0e26
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88962162f094ddca0e80cfab7d56f5e2562e5bf34db45629cca71492a321a69a
+oid sha256:267e89237fd4eac1d8b919b5bc99b3762842294c6c1552d4969f354c8e3b1a12
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f77e5c5e2b3568f719182c676f1fde3c01053246b78917a938493b63e042794
+oid sha256:c8bdc1434b82e729d437ce7476e89e3fe3eb047c15923d5160caede3c0b81f0f
 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": 5.8532588018379236e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00076092364423893,
+  "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": 5.8532588018379236e-05,
       "eval_loss": 3.375028133392334,
-      "eval_runtime": 782.1369,
-      "eval_samples_per_second": 9.198,
-      "eval_steps_per_second": 4.599,
+      "eval_runtime": 782.6628,
+      "eval_samples_per_second": 9.192,
+      "eval_steps_per_second": 4.596,
       "step": 1
+    },
+    {
+      "epoch": 0.00029266294009189616,
+      "grad_norm": 2.181471109390259,
+      "learning_rate": 5e-05,
+      "loss": 2.3814,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005853258801837923,
+      "grad_norm": 2.263486385345459,
+      "learning_rate": 0.0001,
+      "loss": 3.1999,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005853258801837923,
+      "eval_loss": 2.706347703933716,
+      "eval_runtime": 787.5742,
+      "eval_samples_per_second": 9.134,
+      "eval_steps_per_second": 4.567,
+      "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": 238886427033600.0,
+  "total_flos": 3248855407656960.0,
   "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 sha256:175e76b353d0f8b2df820a6ab3b3e5b2bcffb6cfe81996344e0578ef59bd01a5
+oid sha256:fdf3a9fab4cbcec360f77e2b33645177e3a3556847c6a6b2e9cafe03f1be4a58
 size 6776