Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "o_proj",
-    "up_proj",
-    "q_proj",
     "gate_proj",
+    "q_proj",
+    "up_proj",
+    "down_proj",
     "k_proj",
-    "down_proj"
+    "o_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 sha256:87115f8ac046726188cd9def26a6d37928abffe5bbaa2cbc010779c43d1fec57
+oid sha256:7b3e11a66a38207ce99a54b043aef4de1c80c60958eb4667d09a90773551c794
 size 2185308216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a9a9e37467a4018bb704695f64bc750554e4401301c7b903615592b7163a29e
+oid sha256:51957ad7b37db647e51475cf7904e7241eb51c2bf90022448091c132ba60ff2c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:6286a07b356beb4b76bbb49982b1e35c009b260102e0a6e40f5c518c1a9550e1
 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": 0.00045259108395564606,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005883684091423399,
+  "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": 0.00045259108395564606,
       "eval_loss": 0.4409753978252411,
-      "eval_runtime": 119.6487,
-      "eval_samples_per_second": 7.781,
-      "eval_steps_per_second": 3.895,
+      "eval_runtime": 119.5679,
+      "eval_samples_per_second": 7.786,
+      "eval_steps_per_second": 3.897,
       "step": 1
+    },
+    {
+      "epoch": 0.0022629554197782305,
+      "grad_norm": 0.2826593220233917,
+      "learning_rate": 5e-05,
+      "loss": 0.4614,
+      "step": 5
+    },
+    {
+      "epoch": 0.004525910839556461,
+      "grad_norm": 0.3693868815898895,
+      "learning_rate": 0.0001,
+      "loss": 0.4523,
+      "step": 10
+    },
+    {
+      "epoch": 0.004525910839556461,
+      "eval_loss": 0.4037085175514221,
+      "eval_runtime": 120.5989,
+      "eval_samples_per_second": 7.72,
+      "eval_steps_per_second": 3.864,
+      "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": 369913050955776.0,
+  "total_flos": 4623913136947200.0,
   "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 sha256:98e7a45d433edbc75bf0162591e23963ce0b9af786e50c2397b85a5de9c07c9a
+oid sha256:d254b9b40a7a95c9a4ce87f0308e42595a21a12aa3c10a8b344ca5ecdac28b3b
 size 6776