Training in progress, step 300, checkpoint

last-checkpoint/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "o_proj",
+    "q_proj",
+    "v_proj",
     "k_proj",
+    "up_proj",
     "down_proj",
-    "q_proj",
     "gate_proj",
-    "v_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 sha256:374da347622d668269859b72eea6f2d0b4a91b341a780d5b61734db381dfaa05
+oid sha256:fbb4f2a54acdd2dc060e3f9b839392093f0072bde87714829f2c22879be8a83b
 size 161533160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87be9e7a373870535fef2fa6152f10c18656b3e076faafdcd2eb3a7235ee483
+oid sha256:9692d49a09a3c2f840030cbb28ca611ed0b3e2db87ed53e29bafb9a9ff2c6c81
 size 323292202

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f8f252de09a4793e5f13e772318938c884d18658b3687d3f2f6915920086464
+oid sha256:061821e3d04852eeae52afa7567aad700ed25cb9e80039e019f6142953cc33e4
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.033112582781456956,
+  "epoch": 0.04966887417218543,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,20 @@
       "eval_samples_per_second": 3.185,
       "eval_steps_per_second": 3.185,
       "step": 200
+    },
+    {
+      "epoch": 0.041390728476821195,
+      "grad_norm": 3.0053958892822266,
+      "learning_rate": 1.3741721854304637e-05,
+      "loss": 0.9816,
+      "step": 250
+    },
+    {
+      "epoch": 0.04966887417218543,
+      "grad_norm": 3.028010368347168,
+      "learning_rate": 1.6501103752759385e-05,
+      "loss": 0.9372,
+      "step": 300
     }
   ],
   "logging_steps": 50,
@@ -71,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1563083893899264.0,
+  "total_flos": 2342017777532928.0,
   "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 sha256:6a2edd0949861cb7badd527f7095b9c2224394d2fdbe771dec750a5cdb83b3f5
-size 5688
+oid sha256:5dd2ef96eff028fc6db83c8627ce2e789cafe652a25ea367c040819bc392f916
+size 5752