Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "down_proj",
-    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
     "q_proj",
     "o_proj",
-    "v_proj",
-    "k_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 sha256:4b0788b45aba5b79086a9b002a0c49b2412d0c69a21172e15c09598a422fd988
+oid sha256:13e4a0ce1a491934418e6f4710ac3d42222e97de23ab5116e984442b53f75e20
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d6759ac235d13c42277ebe3c0b314bb70f8d9791fa0f38383e4a928eda7225b
+oid sha256:0ab87d6d19502706755356ad753f1517a727090c10a1424130b8c39c9a365d5d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:ada9b88cecb69c9d2d8d4079789122084e4f2f601b6cf82350a60242621e3280
 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": 3.0264282849987515e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0003934356770498377,
+  "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": 3.0264282849987515e-05,
       "eval_loss": 5.79030179977417,
-      "eval_runtime": 942.464,
-      "eval_samples_per_second": 14.762,
-      "eval_steps_per_second": 7.382,
+      "eval_runtime": 940.4939,
+      "eval_samples_per_second": 14.793,
+      "eval_steps_per_second": 7.397,
       "step": 1
+    },
+    {
+      "epoch": 0.00015132141424993757,
+      "grad_norm": 12.141045570373535,
+      "learning_rate": 5e-05,
+      "loss": 5.9707,
+      "step": 5
+    },
+    {
+      "epoch": 0.00030264282849987514,
+      "grad_norm": 9.119531631469727,
+      "learning_rate": 0.0001,
+      "loss": 4.826,
+      "step": 10
+    },
+    {
+      "epoch": 0.00030264282849987514,
+      "eval_loss": 2.8944547176361084,
+      "eval_runtime": 940.3469,
+      "eval_samples_per_second": 14.796,
+      "eval_steps_per_second": 7.398,
+      "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": 184956424814592.0,
+  "total_flos": 2404433522589696.0,
   "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 sha256:8ef7749088c48eb2537195c05e5af0bcc9869e5ffff1355e1f1f378e03e18cda
+oid sha256:1b2820eb7874bfe01c1067ef86e59bfabaad6154c096ad808997843b52dda045
 size 6776