Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
-    "up_proj",
     "v_proj",
     "gate_proj",
+    "k_proj",
     "o_proj",
-    "q_proj"
+    "up_proj",
+    "q_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:dfa777f90baf57a224ddd2e99a76ccb1d02de9a525134b287ca14c4933063cc7
+oid sha256:10e837b4eba8803ff1e54dbccad3115be86d26e5573c4231fbcd6802a5ea2b8b
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a64995a00fa28b24a411f6700524db01f2ea5082cc699e3880b9b5735310ea
+oid sha256:cd5b333bf51ef7ebb19f4c8bd301d33f128a76fad3adddf3ec6c85c3e31ffb18
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5312ddb8f626229a291c72b544634e2d97dd8ec4ceca4550f1b24f37a77647
+oid sha256:41e8229120dce69fa1081c29f9ca7f12647fb8db9c60a1f8dce12e8d0bda6beb
 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": 0.005847953216374269,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.07602339181286549,
+  "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": 0.005847953216374269,
       "eval_loss": 4.58418083190918,
-      "eval_runtime": 3.9727,
-      "eval_samples_per_second": 18.124,
-      "eval_steps_per_second": 9.062,
+      "eval_runtime": 4.0022,
+      "eval_samples_per_second": 17.99,
+      "eval_steps_per_second": 8.995,
       "step": 1
+    },
+    {
+      "epoch": 0.029239766081871343,
+      "grad_norm": 3.0935211181640625,
+      "learning_rate": 5e-05,
+      "loss": 4.5876,
+      "step": 5
+    },
+    {
+      "epoch": 0.05847953216374269,
+      "grad_norm": 3.019068717956543,
+      "learning_rate": 0.0001,
+      "loss": 4.2658,
+      "step": 10
+    },
+    {
+      "epoch": 0.05847953216374269,
+      "eval_loss": 4.069548606872559,
+      "eval_runtime": 4.0436,
+      "eval_samples_per_second": 17.806,
+      "eval_steps_per_second": 8.903,
+      "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": 50009733070848.0,
+  "total_flos": 650126529921024.0,
   "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:e27923fdd6fb62e83d086f3e3b7f5db7c2be735e0dc6f773bb61218d24de131a
+oid sha256:9b28baa96a82cd0afd2f26e5c5bc268efbafe8e22125a9cea296a7300bf71fd2
 size 6776