Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "o_proj",
-    "k_proj",
+    "q_proj",
     "up_proj",
-    "gate_proj",
+    "k_proj",
+    "down_proj",
     "v_proj",
-    "q_proj"
+    "o_proj",
+    "gate_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:c1eefec1f73f2fa5098c633f09a4648ffa147eb0d99c6e79df9a06f1ef815bec
+oid sha256:4a7a3b8ad382c019a800623866e13d1f5e176c6e85338c20f40e82c67b168c88
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c61b11791b2d779f263989a949f9b302849fc6b873ba7ad43039fb6b8e47f02b
+oid sha256:25925d380c421bc636f42bfa34b37a2043f12ff9e034cfc8d4f16fef4f94e237
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb5dd3632f621f63027a71316dd458a1d0eb2cb6f6bdb9c2be6da1bb386cb19
+oid sha256:28934651e3cc601cebcc7f319634626605fa8378a663dfd651812ecf10624b8a
 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": 0.000637551801083838,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.008288173414089895,
+  "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": 0.000637551801083838,
       "eval_loss": 6.481906890869141,
-      "eval_runtime": 27.9357,
-      "eval_samples_per_second": 23.661,
-      "eval_steps_per_second": 11.849,
+      "eval_runtime": 27.6478,
+      "eval_samples_per_second": 23.908,
+      "eval_steps_per_second": 11.972,
       "step": 1
+    },
+    {
+      "epoch": 0.0031877590054191903,
+      "grad_norm": 3.5302960872650146,
+      "learning_rate": 5e-05,
+      "loss": 5.9171,
+      "step": 5
+    },
+    {
+      "epoch": 0.006375518010838381,
+      "grad_norm": 4.611023902893066,
+      "learning_rate": 0.0001,
+      "loss": 5.6593,
+      "step": 10
+    },
+    {
+      "epoch": 0.006375518010838381,
+      "eval_loss": 5.287916660308838,
+      "eval_runtime": 27.76,
+      "eval_samples_per_second": 23.811,
+      "eval_steps_per_second": 11.924,
+      "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": 82004866498560.0,
+  "total_flos": 1230072997478400.0,
   "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:c2bc752240307d344feddf441aac0aaa7342bd667aa5823127a97a68f04076ca
+oid sha256:c6dd7119f9311333b2cf66fa9e3ace94f03b25a38a9f23ad68a701cd845fecdc
 size 6776