Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
     "gate_proj",
-    "up_proj",
+    "q_proj",
     "k_proj",
+    "up_proj",
+    "v_proj",
     "down_proj",
     "o_proj"
   ],

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5ecc78504eaa310b338b66e3e28da1f444c69b626f557084189b835f3072017
+oid sha256:cc68e9249496f953e631a20d5351f25de4982a87396fe94b3651fa0a33278439
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a25356f1d4da875880fb13346a4087d097ad469aced44a354bf5582f0c250ed7
+oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b515e348d3e765152c4c940a8ea06c2d64704d97a831f020760a94092e8ecfbf
+oid sha256:bb42603c6ea93282cd7b812e4230cfeb74ceecfc7f6b103a7e0220f43cb7ac48
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,102 +1,27 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009005155451495982,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 1.1256539345826217e-05,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.00018010310902991962,
+      "epoch": 1.1256539345826217e-05,
       "eval_loss": NaN,
-      "eval_runtime": 718.7196,
-      "eval_samples_per_second": 52.045,
-      "eval_steps_per_second": 6.506,
+      "eval_runtime": 1405.2675,
+      "eval_samples_per_second": 26.618,
+      "eval_steps_per_second": 13.309,
       "step": 1
-    },
-    {
-      "epoch": 0.0018010310902991963,
-      "grad_norm": NaN,
-      "learning_rate": 9.330127018922194e-05,
-      "loss": 0.0,
-      "step": 10
-    },
-    {
-      "epoch": 0.0018010310902991963,
-      "eval_loss": NaN,
-      "eval_runtime": 717.1542,
-      "eval_samples_per_second": 52.159,
-      "eval_steps_per_second": 6.52,
-      "step": 10
-    },
-    {
-      "epoch": 0.0036020621805983926,
-      "grad_norm": NaN,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.0,
-      "step": 20
-    },
-    {
-      "epoch": 0.0036020621805983926,
-      "eval_loss": NaN,
-      "eval_runtime": 715.5675,
-      "eval_samples_per_second": 52.275,
-      "eval_steps_per_second": 6.535,
-      "step": 20
-    },
-    {
-      "epoch": 0.0054030932708975885,
-      "grad_norm": NaN,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.0054030932708975885,
-      "eval_loss": NaN,
-      "eval_runtime": 715.4625,
-      "eval_samples_per_second": 52.282,
-      "eval_steps_per_second": 6.536,
-      "step": 30
-    },
-    {
-      "epoch": 0.007204124361196785,
-      "grad_norm": NaN,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.007204124361196785,
-      "eval_loss": NaN,
-      "eval_runtime": 716.0996,
-      "eval_samples_per_second": 52.236,
-      "eval_steps_per_second": 6.53,
-      "step": 40
-    },
-    {
-      "epoch": 0.009005155451495982,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.009005155451495982,
-      "eval_loss": NaN,
-      "eval_runtime": 716.5761,
-      "eval_samples_per_second": 52.201,
-      "eval_steps_per_second": 6.525,
-      "step": 50
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 50,
+  "logging_steps": 5,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -109,8 +34,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.597629050696499e+16,
-  "train_batch_size": 8,
+  "total_flos": 32429825851392.0,
+  "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 sha256:32ea9d163e7dbd75379368f24d33f3d4bff43268d9da67856239504391db438c
+oid sha256:4a6d62f7df6ccdfbf754194dfa47373cb38687275fb0f6fae10a37282c882344
 size 6776