Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "q_proj",
     "down_proj",
     "v_proj",
     "gate_proj",
     "k_proj",
-    "q_proj",
-    "o_proj"
+    "o_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 sha256:20773e25fbd558971ea630c4075d0b99e3d360bc12bb995d11f5a3cd3565431e
+oid sha256:68bce30b614f83a643f0741359170685dff02f80338af5e654726ff360bf455e
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16fe69cedb540c918ed050988e44f793bf79f8f62af9ed51d38f018a1acbb128
+oid sha256:8a18697cb7228c9e6b36d188b7d97c5e2d87673644dc4fb2eda14a02ca20be05
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2bc2b2c105845278ea7ad88e94af703d7c35b694632461ef449346f75a9e5cd
+oid sha256:f92ff5a5b676a9b8b9f1a4521e56d6a9c9ca74b909b133a54f52c8e597e8f5a1
 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": 4.9809478743804945e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0006475232236694644,
+  "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": 4.9809478743804945e-05,
       "eval_loss": 1.2049556970596313,
-      "eval_runtime": 266.0222,
-      "eval_samples_per_second": 31.779,
-      "eval_steps_per_second": 15.89,
+      "eval_runtime": 268.8732,
+      "eval_samples_per_second": 31.442,
+      "eval_steps_per_second": 15.721,
       "step": 1
+    },
+    {
+      "epoch": 0.00024904739371902474,
+      "grad_norm": 1.1703884601593018,
+      "learning_rate": 5e-05,
+      "loss": 0.9729,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004980947874380495,
+      "grad_norm": 1.128602385520935,
+      "learning_rate": 0.0001,
+      "loss": 1.2574,
+      "step": 10
+    },
+    {
+      "epoch": 0.0004980947874380495,
+      "eval_loss": 1.1664738655090332,
+      "eval_runtime": 268.8172,
+      "eval_samples_per_second": 31.449,
+      "eval_steps_per_second": 15.724,
+      "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": 38368796737536.0,
+  "total_flos": 351713970094080.0,
   "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:b36788609a0cfed3775a0c7df3b751386ad9da1d55eef3c5479c1ee8b878ecc3
+oid sha256:3069bfb898db8d0e65e09553b96f0521cbdf4844f506b548035a0cee3ef614c9
 size 6776