Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "q_proj",
+    "o_proj",
     "k_proj",
-    "v_proj",
-    "up_proj",
+    "down_proj",
     "gate_proj",
-    "o_proj"
+    "v_proj",
+    "q_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 sha256:0c641e93e0d5d000dd423b79cfc84462e622e84a170eaa462368f123fd7fe4b4
+oid sha256:4a220705759e32cf58a4c81c4193434555aaad4da2645381e8109e24537d9a68
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f068e78a9723cda68d52e53f514b736226ef28d8ba4d8ff05faf4912a4f02f0d
+oid sha256:ce2a6195d93f3bf4d5e786f91b14774685db0d88bfdf1d40f20b80172f8864d4
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165ffe955f1fff238d7fa55fc3e704ed1175348f65c16d2a2296ab05188c0b98
+oid sha256:7b0a5df432412fe204bb01886dc33204ff821698d28871df0a93efadc187549a
 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": 0.0001591849729385546,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0020694046482012097,
+  "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": 0.0001591849729385546,
       "eval_loss": NaN,
-      "eval_runtime": 131.7571,
-      "eval_samples_per_second": 20.075,
-      "eval_steps_per_second": 10.041,
+      "eval_runtime": 133.9717,
+      "eval_samples_per_second": 19.743,
+      "eval_steps_per_second": 9.875,
       "step": 1
+    },
+    {
+      "epoch": 0.000795924864692773,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.001591849729385546,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.001591849729385546,
+      "eval_loss": NaN,
+      "eval_runtime": 132.6323,
+      "eval_samples_per_second": 19.942,
+      "eval_steps_per_second": 9.975,
+      "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": 68560663609344.0,
+  "total_flos": 942709124628480.0,
   "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 sha256:2edd64c910b5786964e84a92414e71f289ada7e56a7a832d8c6ff276bf3b673f
+oid sha256:c15c65220df6ec6c97ef727f9cdbdad5c061bd130d30cbae080f4142ac6ae9f0
 size 6776