Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "down_proj",
+    "o_proj",
+    "up_proj",
     "q_proj",
-    "gate_proj",
-    "v_proj",
     "k_proj",
-    "up_proj",
-    "o_proj"
+    "v_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 sha256:5906af3143810f35473cc0f36a4aee21e1d73ca6299c3d82e7fc1c15aa763cc7
+oid sha256:47de1b13452ca219cc898e872b62873a9447c0d8150f17c1181615413a067e65
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:983fd17b78b8f84c5a2731d70e7080981bdbb4831a972cd04abbd883bd0990cb
+oid sha256:051e7bdda2697f7564d4494a92c4a9d8a8e6ed3a06f6e4bd7656bf93da091865
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:43f0afd2a6da0fca19f600fb0b6d301534483f4096658807dd63f0bc368c2a3d
 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": 0.0017675651789659744,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.022978347326557666,
+  "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": 0.0017675651789659744,
       "eval_loss": 1.5736385583877563,
-      "eval_runtime": 18.499,
-      "eval_samples_per_second": 12.92,
-      "eval_steps_per_second": 6.487,
+      "eval_runtime": 18.5113,
+      "eval_samples_per_second": 12.911,
+      "eval_steps_per_second": 6.483,
       "step": 1
+    },
+    {
+      "epoch": 0.008837825894829872,
+      "grad_norm": 1.6883810758590698,
+      "learning_rate": 5e-05,
+      "loss": 1.4734,
+      "step": 5
+    },
+    {
+      "epoch": 0.017675651789659744,
+      "grad_norm": 1.110305666923523,
+      "learning_rate": 0.0001,
+      "loss": 1.4599,
+      "step": 10
+    },
+    {
+      "epoch": 0.017675651789659744,
+      "eval_loss": 1.436456561088562,
+      "eval_runtime": 18.9204,
+      "eval_samples_per_second": 12.632,
+      "eval_steps_per_second": 6.342,
+      "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": 184956424814592.0,
+  "total_flos": 2913063690829824.0,
   "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:b9bc0d3c3576da483ae8c8aff331e93041ffc9e488fed3cb7b7fd88540acf532
+oid sha256:9f96514a44fa9698b164a375e7b4a8409f0414b87cfe90474cf7b9532499e1bc
 size 6776