Training in progress, step 2550, checkpoint

last-checkpoint/adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "q_proj",
     "up_proj",
-    "gate_proj",
-    "k_proj",
     "v_proj",
     "down_proj",
-    "q_proj"
+    "o_proj",
+    "k_proj",
+    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:378c742a2ed47583532794cae1fd2de4a6760ea2e1b8121476178b01d980da3e
+oid sha256:dcb38d1a14c924041fe5a80f020327deb0212523052b88a9869515999fb8b0d4
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a898a183983728143a712f6bc3eb4cff78c82a63ea213dd37b8d81025cbe4b5c
+oid sha256:f9295ab1b0a55031b1697cf0d73be84f706f3df721cf031ba0ba34ebee613008
 size 57081771

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3a9e09f9c50cf219bb4c5d3609a4ab4f8f9e31801cf50cb4cced79e186978e
+oid sha256:6fb274dfbe503274d6dd4f2521e2755230b18e2c0f55f4480cf566471adb1def
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7651515151515151,
+  "epoch": 0.5796771993634917,
   "eval_steps": 300,
-  "global_step": 2525,
+  "global_step": 2550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1018,10 +1018,20 @@
       "mean_token_accuracy": 0.9421089863777161,
       "num_tokens": 123713.0,
       "step": 2525
+    },
+    {
+      "entropy": 0.16171722620725631,
+      "epoch": 0.5796771993634917,
+      "grad_norm": 0.33440494537353516,
+      "learning_rate": 0.0002,
+      "loss": 0.15710799217224122,
+      "mean_token_accuracy": 0.9462839317321777,
+      "num_tokens": 31337.0,
+      "step": 2550
     }
   ],
   "logging_steps": 25,
-  "max_steps": 3300,
+  "max_steps": 4399,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 25,
@@ -1037,7 +1047,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4410656586072064e+17,
+  "total_flos": 2.4591659063217254e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960f819df65000b60022084047fdd37ac0488cbb84d6a7a54a670acd7a6a59f6
+oid sha256:9f44b81cef0de28756796a239128e158d8d837ede815af7c9b8b55df63dc7629
 size 5649