Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "down_proj",
+    "o_proj",
     "up_proj",
+    "q_proj",
     "gate_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
     "v_proj"
   ],

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917418dd014b58d36fd24c56fdafaf7d35fdb1ffb746ebbf388e00f07facf17f
+oid sha256:b33d74cf9053a835e4dc5b527b6f1fd7afc65f500b885fa168374e00360eaaeb
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b7bd8267e04cd7e2d1d2563e1fe6c53f129fa1d2a7b5f1d6da3f36eff59a2e
+oid sha256:9a04ea89e27d81bdfadd01a2e32a838b97dd199b922186e5ed62d456c997190b
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e1a1220d67625c7f0818e9c3442286fea4c5721e7fd1bd057ffdcbf1f017270
+oid sha256:eec0b831766904c9b8fb59ee1139aa6cf829f8c2f96522ec78ad42870d94eb38
 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": 0.00012853470437017994,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0016709511568123393,
+  "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": 0.00012853470437017994,
       "eval_loss": NaN,
-      "eval_runtime": 517.9676,
-      "eval_samples_per_second": 6.325,
-      "eval_steps_per_second": 3.162,
+      "eval_runtime": 435.0938,
+      "eval_samples_per_second": 7.529,
+      "eval_steps_per_second": 3.765,
       "step": 1
+    },
+    {
+      "epoch": 0.0006426735218508997,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 14.901,
+      "step": 5
+    },
+    {
+      "epoch": 0.0012853470437017994,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0012853470437017994,
+      "eval_loss": NaN,
+      "eval_runtime": 463.821,
+      "eval_samples_per_second": 7.063,
+      "eval_steps_per_second": 3.532,
+      "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": 15581678665728.0,
+  "total_flos": 213691593129984.0,
   "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:a7493af658ff0aefe2286ebc6809f78a29d41bed42a8edd1545a167ea935ab48
+oid sha256:dccdf3c257a9e352f51b49a642b438162de1e3ea259f58e7e0d905d716670ec3
 size 6776