Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "up_proj",
+    "v_proj",
     "o_proj",
     "k_proj",
-    "v_proj",
-    "q_proj",
     "down_proj",
-    "up_proj"
+    "gate_proj",
+    "q_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 sha256:1759d192056abfd9cb222aba9403ecd9dc11bc551f90333426552f5cad92db6f
+oid sha256:6d6b6fe4f6bcff5b8d1e275bb5de5012fb4185d141b32077ce3544bc62debbeb
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca5604966bec584cc89c2403179749c1d62712e8fd65d38846c4931a304fc13
+oid sha256:c74bb52439a0e67a095a2f9519fde24aeab41ff6291413fa4d929c03c9453b6b
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17cd0b5f1e33bd6dba2461570a653efdaf1fb902096b4df09992935b3fc24a4
+oid sha256:2c5ccb91bc863285e4b6a29afacd6382c0b78a1a6c2bd0f12c46edbbd9bbfaf5
 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": 0.0011560693641618498,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.015028901734104046,
+  "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": 0.0011560693641618498,
       "eval_loss": 5.359778881072998,
-      "eval_runtime": 14.4038,
-      "eval_samples_per_second": 25.341,
-      "eval_steps_per_second": 12.705,
+      "eval_runtime": 14.3601,
+      "eval_samples_per_second": 25.418,
+      "eval_steps_per_second": 12.744,
       "step": 1
+    },
+    {
+      "epoch": 0.005780346820809248,
+      "grad_norm": 7.12149715423584,
+      "learning_rate": 5e-05,
+      "loss": 5.0646,
+      "step": 5
+    },
+    {
+      "epoch": 0.011560693641618497,
+      "grad_norm": 7.830906391143799,
+      "learning_rate": 0.0001,
+      "loss": 4.5362,
+      "step": 10
+    },
+    {
+      "epoch": 0.011560693641618497,
+      "eval_loss": 4.520800590515137,
+      "eval_runtime": 12.3117,
+      "eval_samples_per_second": 29.647,
+      "eval_steps_per_second": 14.864,
+      "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": 8903816380416.0,
+  "total_flos": 117975567040512.0,
   "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 sha256:8f46f10a209c05d306d6d5c642ea9b94efef44e34bd51d4e6c274419144c2656
+oid sha256:0428d789300c6ef8546127da4f581bc75936965d556eafa7666a9fb38a04dccb
 size 6776