Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "gate_proj",
     "down_proj",
-    "o_proj",
     "v_proj",
-    "up_proj",
-    "q_proj"
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "up_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:bd6c98f719a2a3807289ce5cce2b4bdbf8fb0805fb5376da3b6e7fa635de0ac0
+oid sha256:3a9e99d43c71e573d67c410ef836ede6e0367c7540d8009ec904d47bc7e1cc9d
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed8a20584e470fb022729995c282913a93527e5c45616e5c3b154d839157b47
+oid sha256:2c242245516d16c47287ea296d338e46ebb26c84486a3ffeda15397429416af1
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d9a862f2f5d6e68aebf00bb86cfa48b9230ee8ec6f82d72a38d56361eaada5
+oid sha256:66858b40af83947edf569c3acabc2f826bba88e0c12f7d5c52a38d9c298d66a3
 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": 0.00012734797835084368,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0016555237185609678,
+  "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": 0.00012734797835084368,
       "eval_loss": 2.5662894248962402,
-      "eval_runtime": 162.0579,
-      "eval_samples_per_second": 20.406,
-      "eval_steps_per_second": 10.206,
+      "eval_runtime": 162.3491,
+      "eval_samples_per_second": 20.37,
+      "eval_steps_per_second": 10.188,
       "step": 1
+    },
+    {
+      "epoch": 0.0006367398917542184,
+      "grad_norm": 0.610783576965332,
+      "learning_rate": 5e-05,
+      "loss": 1.9454,
+      "step": 5
+    },
+    {
+      "epoch": 0.0012734797835084368,
+      "grad_norm": 0.5147393941879272,
+      "learning_rate": 0.0001,
+      "loss": 1.518,
+      "step": 10
+    },
+    {
+      "epoch": 0.0012734797835084368,
+      "eval_loss": 2.484592914581299,
+      "eval_runtime": 161.1375,
+      "eval_samples_per_second": 20.523,
+      "eval_steps_per_second": 10.265,
+      "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": 104358456852480.0,
+  "total_flos": 1147943025377280.0,
   "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 sha256:7e5d13a12d2163c8a94805cb30688592332d58b089be9670019ba2bdcc4e0c68
+oid sha256:6fb1c79e98d1000773f04006554665350f187ab774524416ccad67e606aea363
 size 6776