Training in progress, step 1500, checkpoint

last-checkpoint/adapter_config.json

@@ -24,12 +24,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "up_proj",
-    "down_proj",
-    "k_proj",
     "gate_proj",
     "v_proj",
-    "o_proj"
+    "down_proj",
+    "k_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 sha256:63c2d0792b1d88ce11dcb0206c9f4b195249bfd60b565b2b275d5506c6884aef
+oid sha256:387a609d77a6f04994f41806c4342af3479a3584ba26eb5046c846fb53e3733d
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c9c2ad8af99359ec7701ff21f6fdf2d25cecd98c987a9c59a0056d7961e783
+oid sha256:edd45e5310384e1cd99d112de2d42d78613c36dec95eed74460a89120c2efd24
 size 591208618

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34bcae41c589c7e4cab7b2ef263b878c90c2741404a6af11994dc31537b2319b
+oid sha256:a9affc1541e7e94c18354d5173bc55400c5f07faf3d080c6d453d48e7a8d6ac3
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d05dc84075e8f7dd1191c36f3be9dda12073208e12f7d2cef433c38d6336774a
+oid sha256:4748c3ebf0e4c051c58b92e4a8c5b87cdb39d55cfdc2aec81a1baef0f02fc113
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cd3a54077bf63f8ad925067efe37ddc4042a938e38b49241196f2ca99e6b9c
+oid sha256:19f4fe1ab3e08a0747220960bdfd6d03295c271f39bd8ca520946db1ae21cdde
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1778301192403946,
+  "epoch": 1.766671573678787,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -156,6 +156,84 @@
       "eval_samples_per_second": 1.39,
       "eval_steps_per_second": 0.695,
       "step": 1000
+    },
+    {
+      "epoch": 1.2367142646842337,
+      "grad_norm": 0.5041179060935974,
+      "learning_rate": 7.319880650722838e-05,
+      "loss": 0.4541,
+      "step": 1050
+    },
+    {
+      "epoch": 1.295598410128073,
+      "grad_norm": 0.5369197726249695,
+      "learning_rate": 7.01111937773246e-05,
+      "loss": 0.4576,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3544825555719122,
+      "grad_norm": 0.5211925506591797,
+      "learning_rate": 6.692915791902665e-05,
+      "loss": 0.4472,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4133667010157516,
+      "grad_norm": 0.5664705038070679,
+      "learning_rate": 6.366763876055806e-05,
+      "loss": 0.4427,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4722508464595907,
+      "grad_norm": 0.5420666337013245,
+      "learning_rate": 6.034194930847975e-05,
+      "loss": 0.4395,
+      "step": 1250
+    },
+    {
+      "epoch": 1.53113499190343,
+      "grad_norm": 0.558952271938324,
+      "learning_rate": 5.6967703852306786e-05,
+      "loss": 0.4305,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5900191373472694,
+      "grad_norm": 0.510136067867279,
+      "learning_rate": 5.356074465458553e-05,
+      "loss": 0.428,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6489032827911085,
+      "grad_norm": 0.506799578666687,
+      "learning_rate": 5.013706757062534e-05,
+      "loss": 0.4251,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7077874282349477,
+      "grad_norm": 0.5179591178894043,
+      "learning_rate": 4.671274694710388e-05,
+      "loss": 0.4188,
+      "step": 1450
+    },
+    {
+      "epoch": 1.766671573678787,
+      "grad_norm": 0.531908392906189,
+      "learning_rate": 4.3303860152151445e-05,
+      "loss": 0.4177,
+      "step": 1500
+    },
+    {
+      "epoch": 1.766671573678787,
+      "eval_loss": 0.4321376383304596,
+      "eval_runtime": 2174.1694,
+      "eval_samples_per_second": 1.389,
+      "eval_steps_per_second": 0.695,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -175,7 +253,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1226707705777357e+17,
+  "total_flos": 2.011350882666414e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cbb7a8dca460a6c61190997fda8d2ab2173e3728cdc1e9fc28122c635e84db4
+oid sha256:ebcd21407e4d67b6689be225553b0c97b643782323ffcb915a758db6678d480a
 size 5752