Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "v_proj",
     "q_proj",
-    "o_proj",
-    "up_proj",
     "k_proj",
-    "down_proj"
+    "down_proj",
+    "gate_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 sha256:6b4bfcbf62c21ceb839aae56d32fbc3ed7ba466bb4c49dbde280873ba2cf92b1
+oid sha256:87633ac9e2400a2975d43a2f0032361aa5c5f78525c56c3b85f22189fa2e8c3e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d07cdcf777f55e505b7a46f6244e14401834a52e9de73273df42721a0865bf12
+oid sha256:144bf8e00a98487cb749d076fca44ece55bcd222459162653fe0f72099b3559a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
 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": 8.443271767810026e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0010976253298153034,
+  "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": 8.443271767810026e-05,
       "eval_loss": 6.900400638580322,
-      "eval_runtime": 415.6051,
-      "eval_samples_per_second": 11.999,
-      "eval_steps_per_second": 6.001,
+      "eval_runtime": 415.9031,
+      "eval_samples_per_second": 11.991,
+      "eval_steps_per_second": 5.997,
       "step": 1
+    },
+    {
+      "epoch": 0.00042216358839050134,
+      "grad_norm": 225.8194580078125,
+      "learning_rate": 5e-05,
+      "loss": 26.3712,
+      "step": 5
+    },
+    {
+      "epoch": 0.0008443271767810027,
+      "grad_norm": 205.8764190673828,
+      "learning_rate": 0.0001,
+      "loss": 10.7889,
+      "step": 10
+    },
+    {
+      "epoch": 0.0008443271767810027,
+      "eval_loss": 1.4552971124649048,
+      "eval_runtime": 425.3753,
+      "eval_samples_per_second": 11.724,
+      "eval_steps_per_second": 5.863,
+      "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": 175267179921408.0,
+  "total_flos": 2278473338978304.0,
   "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:ca8e3bc73b47ddc5bcedbf930fa82a2d0caba2004f84e0688c6ea9400ee1f3e8
+oid sha256:e8f2c33553704ddd78142baf60fdf0481e0bc1e068821f14659c67de9a6ab0b2
 size 6776