Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
     "k_proj",
-    "o_proj",
     "q_proj",
-    "gate_proj",
-    "up_proj",
-    "v_proj"
+    "o_proj",
+    "down_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 sha256:0faadb3b17a2f7e3ec9b5451f1110384b5d6eb7e4cf4f81353cc7216deb09095
+oid sha256:c436c76ed95cd105a8dc8c237dae594b1698eba8e00aa2357361e57cb54aa258
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6034389d9ab96676757cfa1f86e395bfcf23e0e1811592c2eade57b9077e3d41
+oid sha256:0eeb8fb70986a06c1a5803e8f3753c134619599421db15cd2e3ce2b2bd45297e
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3847e8ae6b97fc91eeb16daa3bfa2299004f32a5173f06812164a57eab15de7
+oid sha256:71fb647c14a3881b77dc1f14cdf3eaca00c93c2c9d84a3a0e2d23ce12fc302b3
 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": 0.000260061114361875,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0033807944867043755,
+  "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": 0.000260061114361875,
       "eval_loss": 5.437866687774658,
-      "eval_runtime": 84.6046,
-      "eval_samples_per_second": 19.148,
-      "eval_steps_per_second": 9.574,
+      "eval_runtime": 84.0843,
+      "eval_samples_per_second": 19.266,
+      "eval_steps_per_second": 9.633,
       "step": 1
+    },
+    {
+      "epoch": 0.001300305571809375,
+      "grad_norm": 2.6719722747802734,
+      "learning_rate": 5e-05,
+      "loss": 4.9857,
+      "step": 5
+    },
+    {
+      "epoch": 0.00260061114361875,
+      "grad_norm": 2.542518138885498,
+      "learning_rate": 0.0001,
+      "loss": 5.1103,
+      "step": 10
+    },
+    {
+      "epoch": 0.00260061114361875,
+      "eval_loss": 5.061859607696533,
+      "eval_runtime": 85.9399,
+      "eval_samples_per_second": 18.85,
+      "eval_steps_per_second": 9.425,
+      "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": 64859651702784.0,
+  "total_flos": 843175472136192.0,
   "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:b42c822e2ebd8e1631e7df92eace1810561cb26c5cb10943b8177b6d59306320
+oid sha256:d93d2ce4a089cce0f971e3c948bebe5dfe15e2d17ba5404881574342e11ac013
 size 6776