Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "o_proj",
     "gate_proj",
     "down_proj",
-    "up_proj",
-    "o_proj",
     "k_proj",
+    "up_proj",
+    "v_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7cd833a57185bf59260c9c8a68e37ebb5c4cc0ff8c6873d6f6fdc04d9c2a93
+oid sha256:e51e8de3a073805df165b190669d256dff44f88d59b3179afae968f17fcfc6bb
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672ecb683af5cad4a222ad5ba85ba3302f5c2b91ca7ee3b2e812e60d950be6ed
+oid sha256:4b0109d301cfbb3652f6eca760a1f95817bb8818cad442aa64cb5fd92ee4bbbf
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03effc09274b064eaa47ae39260846394d0147ce1a4b40de401a8a269cfd7a8e
+oid sha256:95769943b503fd37e5ac516a17484f5788998a9cd717e8fc51b80176db1e71d3
 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": 2.326758302164467e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0003024785792813807,
+  "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": 2.326758302164467e-05,
       "eval_loss": 5.18183708190918,
-      "eval_runtime": 1097.3011,
-      "eval_samples_per_second": 16.492,
-      "eval_steps_per_second": 8.247,
+      "eval_runtime": 1103.9859,
+      "eval_samples_per_second": 16.392,
+      "eval_steps_per_second": 8.197,
       "step": 1
+    },
+    {
+      "epoch": 0.00011633791510822335,
+      "grad_norm": 3.286332368850708,
+      "learning_rate": 5e-05,
+      "loss": 5.2746,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002326758302164467,
+      "grad_norm": 4.80321741104126,
+      "learning_rate": 0.0001,
+      "loss": 4.9456,
+      "step": 10
+    },
+    {
+      "epoch": 0.0002326758302164467,
+      "eval_loss": 4.540585517883301,
+      "eval_runtime": 1107.4278,
+      "eval_samples_per_second": 16.341,
+      "eval_steps_per_second": 8.171,
+      "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": 164782292336640.0,
+  "total_flos": 2183365373460480.0,
   "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:af1bf5174a4eb39d43d7346cd0a343f4ea0a46f66ffa37777138e6e515e96744
+oid sha256:0e7cecc101ccfe83a1fbe35893de511459d7305b1060d8fe88c3b93b4f104b3d
 size 6776