Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "down_proj",
+    "q_proj",
+    "gate_proj",
     "o_proj",
-    "v_proj",
     "k_proj",
-    "q_proj",
-    "gate_proj"
+    "v_proj",
+    "down_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:c6518d29557adddebea8ab07a45fead7314cb285e1b4ccc1aaed1be99403013a
+oid sha256:1f68575dee3f94cedd53e9f87f4f1b2e25d222c7bb169611098a6eae80044dd4
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23ea087ef11e9a7f8693d2827d2995d6dbb48d00248219d377b647e04287834
+oid sha256:e7a06a1492b09f6e7b7f85faeadf45c9c7b97bc589fa7dc2c2c9dd60d641495f
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4300d8b6f4c70f72e8e8cff18d74764ca7940a4984b5afd5af382974ab4bdd4
+oid sha256:5ed413ffc1f3bedbef14e57f493d3e8611649fb25a4d11d4dded6eabfeeb78de
 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": 0.02126528442317916,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.0004253056884635832,
+  "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": 0.0004253056884635832,
       "eval_loss": 7.85447359085083,
-      "eval_runtime": 42.8425,
-      "eval_samples_per_second": 23.108,
-      "eval_steps_per_second": 11.554,
+      "eval_runtime": 42.5688,
+      "eval_samples_per_second": 23.256,
+      "eval_steps_per_second": 11.628,
       "step": 1
-    },
-    {
-      "epoch": 0.002126528442317916,
-      "grad_norm": 7.163774490356445,
-      "learning_rate": 5e-05,
-      "loss": 8.2534,
-      "step": 5
-    },
-    {
-      "epoch": 0.004253056884635832,
-      "grad_norm": 8.35838508605957,
-      "learning_rate": 0.0001,
-      "loss": 7.2732,
-      "step": 10
-    },
-    {
-      "epoch": 0.004253056884635832,
-      "eval_loss": 6.484969615936279,
-      "eval_runtime": 41.7478,
-      "eval_samples_per_second": 23.714,
-      "eval_steps_per_second": 11.857,
-      "step": 10
-    },
-    {
-      "epoch": 0.006379585326953748,
-      "grad_norm": 8.19398307800293,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 5.6656,
-      "step": 15
-    },
-    {
-      "epoch": 0.008506113769271665,
-      "grad_norm": 3.4491403102874756,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 3.2487,
-      "step": 20
-    },
-    {
-      "epoch": 0.008506113769271665,
-      "eval_loss": 3.1702444553375244,
-      "eval_runtime": 42.0779,
-      "eval_samples_per_second": 23.528,
-      "eval_steps_per_second": 11.764,
-      "step": 20
-    },
-    {
-      "epoch": 0.01063264221158958,
-      "grad_norm": 4.044790744781494,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 3.7479,
-      "step": 25
-    },
-    {
-      "epoch": 0.012759170653907496,
-      "grad_norm": 8.27008056640625,
-      "learning_rate": 5e-05,
-      "loss": 3.3817,
-      "step": 30
-    },
-    {
-      "epoch": 0.012759170653907496,
-      "eval_loss": 2.4049201011657715,
-      "eval_runtime": 41.9827,
-      "eval_samples_per_second": 23.581,
-      "eval_steps_per_second": 11.791,
-      "step": 30
-    },
-    {
-      "epoch": 0.014885699096225412,
-      "grad_norm": 3.2958786487579346,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 2.6821,
-      "step": 35
-    },
-    {
-      "epoch": 0.01701222753854333,
-      "grad_norm": 4.264033317565918,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 2.5639,
-      "step": 40
-    },
-    {
-      "epoch": 0.01701222753854333,
-      "eval_loss": 2.0401220321655273,
-      "eval_runtime": 42.0737,
-      "eval_samples_per_second": 23.53,
-      "eval_steps_per_second": 11.765,
-      "step": 40
-    },
-    {
-      "epoch": 0.019138755980861243,
-      "grad_norm": 1.2952890396118164,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 1.4608,
-      "step": 45
-    },
-    {
-      "epoch": 0.02126528442317916,
-      "grad_norm": 1.7913731336593628,
-      "learning_rate": 0.0,
-      "loss": 1.0928,
-      "step": 50
-    },
-    {
-      "epoch": 0.02126528442317916,
-      "eval_loss": 1.9964807033538818,
-      "eval_runtime": 41.817,
-      "eval_samples_per_second": 23.675,
-      "eval_steps_per_second": 11.837,
-      "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": 2399807113003008.0,
+  "total_flos": 40537282314240.0,
   "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:ce4dace37f45c654c666912c1c51ca9379dcab7944d80414f17f3c41aaeed6dd
+oid sha256:1913613e4881acbc49919ced88163786823e6eaea442c2ed99306eaedfeb7041
 size 6776