Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b33d74cf9053a835e4dc5b527b6f1fd7afc65f500b885fa168374e00360eaaeb
+oid sha256:8c544d1850c50d7487a2473e802b796965356db1b34fe845fe64fd47eb6373e9
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24231d9f62d9453a30d95ed5d05b38409d367a52b64901ef92783ec18aa9614a
+oid sha256:58b7bd8267e04cd7e2d1d2563e1fe6c53f129fa1d2a7b5f1d6da3f36eff59a2e
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591f6d71d3e7c596287a3263c9372a9567c1ac708bf71d4a056da58812b2d207
+oid sha256:5e1a1220d67625c7f0818e9c3442286fea4c5721e7fd1bd057ffdcbf1f017270
 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

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006426735218508998,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.00012853470437017994,
+  "eval_steps": 1,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,127 +11,17 @@
     {
       "epoch": 0.00012853470437017994,
       "eval_loss": NaN,
-      "eval_runtime": 435.0938,
-      "eval_samples_per_second": 7.529,
-      "eval_steps_per_second": 3.765,
+      "eval_runtime": 446.6747,
+      "eval_samples_per_second": 7.334,
+      "eval_steps_per_second": 3.667,
       "step": 1
-    },
-    {
-      "epoch": 0.0006426735218508997,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 14.901,
-      "step": 5
-    },
-    {
-      "epoch": 0.0012853470437017994,
-      "grad_norm": NaN,
-      "learning_rate": 0.0001,
-      "loss": 0.0,
-      "step": 10
-    },
-    {
-      "epoch": 0.0012853470437017994,
-      "eval_loss": NaN,
-      "eval_runtime": 463.821,
-      "eval_samples_per_second": 7.063,
-      "eval_steps_per_second": 3.532,
-      "step": 10
-    },
-    {
-      "epoch": 0.0019280205655526992,
-      "grad_norm": NaN,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 0.0,
-      "step": 15
-    },
-    {
-      "epoch": 0.002570694087403599,
-      "grad_norm": NaN,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 0.0,
-      "step": 20
-    },
-    {
-      "epoch": 0.002570694087403599,
-      "eval_loss": NaN,
-      "eval_runtime": 512.5001,
-      "eval_samples_per_second": 6.392,
-      "eval_steps_per_second": 3.196,
-      "step": 20
-    },
-    {
-      "epoch": 0.003213367609254499,
-      "grad_norm": NaN,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 0.0,
-      "step": 25
-    },
-    {
-      "epoch": 0.0038560411311053984,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.0038560411311053984,
-      "eval_loss": NaN,
-      "eval_runtime": 516.5033,
-      "eval_samples_per_second": 6.343,
-      "eval_steps_per_second": 3.171,
-      "step": 30
-    },
-    {
-      "epoch": 0.004498714652956298,
-      "grad_norm": NaN,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.005141388174807198,
-      "grad_norm": NaN,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.005141388174807198,
-      "eval_loss": NaN,
-      "eval_runtime": 436.0731,
-      "eval_samples_per_second": 7.513,
-      "eval_steps_per_second": 3.756,
-      "step": 40
-    },
-    {
-      "epoch": 0.005784061696658098,
-      "grad_norm": NaN,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.006426735218508998,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.006426735218508998,
-      "eval_loss": NaN,
-      "eval_runtime": 359.6146,
-      "eval_samples_per_second": 9.11,
-      "eval_steps_per_second": 4.555,
-      "step": 50
     }
   ],
   "logging_steps": 5,
-  "max_steps": 50,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 13,
+  "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -144,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 834732785664000.0,
+  "total_flos": 15581678665728.0,
   "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:dccdf3c257a9e352f51b49a642b438162de1e3ea259f58e7e0d905d716670ec3
+oid sha256:4b42cf6d719ec25581c8260a10da18c0a441bf614bc077d007b52905995aaebb
 size 6776