Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "fc2",
     "dense",
-    "k_proj",
-    "fc1"
+    "fc2",
+    "v_proj",
+    "fc1",
+    "q_proj",
+    "k_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:ab0e759fd16f74bd234a44afebb49459e1e371c34b31b2f27a4e830fcbe60f2e
+oid sha256:46b0a02ce114ba44f9af855cd27de865daca8d4e4db304200c4144e09da24c52
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b597b29164e75cde94486752eeb32516b4981d6a1ad57a88c4ef37f467121e
+oid sha256:405c0e5c6f9c6bff74d097cb5fd9de736ea0dca6e70fb4e53d2ee4f78cdb237d
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f7fc8844aec33ac39a8d418b0bd207d733e4fe0c75f9ba828fd5cf8e97fb4e8
+oid sha256:872c1161ac0d8b2e9f04a948a3b27a13cec6f9ed82cefc1f06cd5658419b5833
 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

@@ -1,27 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007708614376565812,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.010021198689535556,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0007708614376565812,
-      "eval_loss": 6.9276123046875,
-      "eval_runtime": 10.9929,
-      "eval_samples_per_second": 49.759,
-      "eval_steps_per_second": 24.925,
+      "eval_loss": 6.92765474319458,
+      "eval_runtime": 10.9768,
+      "eval_samples_per_second": 49.832,
+      "eval_steps_per_second": 24.962,
       "step": 1
+    },
+    {
+      "epoch": 0.003854307188282906,
+      "grad_norm": 0.2718292474746704,
+      "learning_rate": 5e-05,
+      "loss": 6.9326,
+      "step": 5
+    },
+    {
+      "epoch": 0.007708614376565812,
+      "grad_norm": 0.28688400983810425,
+      "learning_rate": 0.0001,
+      "loss": 6.9263,
+      "step": 10
+    },
+    {
+      "epoch": 0.007708614376565812,
+      "eval_loss": 6.924817085266113,
+      "eval_runtime": 10.2915,
+      "eval_samples_per_second": 53.151,
+      "eval_steps_per_second": 26.624,
+      "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": 2636660736.0,
+  "total_flos": 34276589568.0,
   "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 sha256:5cd59e8ca0c80a5c8ccbd8b02eeeca09013b590f659ab6c32046a726c630a927
+oid sha256:0468d9e7105a605683154e65cc6e66cf0eea7f3239a0e2d5688d582522ca414d
 size 6776