Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33816cb4d1d40e54a9a22d18fa79d42c408f022c664058840d81462d6d9dc13a
+oid sha256:90789eaf27c1a6ea27c2230017dea34e504798adb9fa6f123af43f10418f43bc
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e30b050bbd1e3964f2835a2c1129e6d66ccdbb80d217634300d9dd1be4107022
+oid sha256:ca9486662bf96ee12aa25458575616b3ed0df5e3f1ffd975a5de6dadf38ec98f
 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": 43.2771,
-      "eval_samples_per_second": 22.876,
-      "eval_steps_per_second": 11.438,
+      "eval_runtime": 42.7134,
+      "eval_samples_per_second": 23.178,
+      "eval_steps_per_second": 11.589,
       "step": 1
-    },
-    {
-      "epoch": 0.002126528442317916,
-      "grad_norm": 6.834736347198486,
-      "learning_rate": 5e-05,
-      "loss": 8.2547,
-      "step": 5
-    },
-    {
-      "epoch": 0.004253056884635832,
-      "grad_norm": 7.907984256744385,
-      "learning_rate": 0.0001,
-      "loss": 7.2747,
-      "step": 10
-    },
-    {
-      "epoch": 0.004253056884635832,
-      "eval_loss": 6.519143104553223,
-      "eval_runtime": 42.5001,
-      "eval_samples_per_second": 23.294,
-      "eval_steps_per_second": 11.647,
-      "step": 10
-    },
-    {
-      "epoch": 0.006379585326953748,
-      "grad_norm": 8.192647933959961,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 5.7035,
-      "step": 15
-    },
-    {
-      "epoch": 0.008506113769271665,
-      "grad_norm": 3.512517213821411,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 3.2579,
-      "step": 20
-    },
-    {
-      "epoch": 0.008506113769271665,
-      "eval_loss": 3.160048723220825,
-      "eval_runtime": 42.4292,
-      "eval_samples_per_second": 23.333,
-      "eval_steps_per_second": 11.667,
-      "step": 20
-    },
-    {
-      "epoch": 0.01063264221158958,
-      "grad_norm": 4.011580467224121,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 3.7366,
-      "step": 25
-    },
-    {
-      "epoch": 0.012759170653907496,
-      "grad_norm": 8.26055908203125,
-      "learning_rate": 5e-05,
-      "loss": 3.3705,
-      "step": 30
-    },
-    {
-      "epoch": 0.012759170653907496,
-      "eval_loss": 2.402796745300293,
-      "eval_runtime": 41.946,
-      "eval_samples_per_second": 23.602,
-      "eval_steps_per_second": 11.801,
-      "step": 30
-    },
-    {
-      "epoch": 0.014885699096225412,
-      "grad_norm": 3.6072275638580322,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 2.691,
-      "step": 35
-    },
-    {
-      "epoch": 0.01701222753854333,
-      "grad_norm": 4.195740699768066,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 2.5675,
-      "step": 40
-    },
-    {
-      "epoch": 0.01701222753854333,
-      "eval_loss": 2.025411605834961,
-      "eval_runtime": 42.3392,
-      "eval_samples_per_second": 23.383,
-      "eval_steps_per_second": 11.691,
-      "step": 40
-    },
-    {
-      "epoch": 0.019138755980861243,
-      "grad_norm": 2.1295504570007324,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 1.4533,
-      "step": 45
-    },
-    {
-      "epoch": 0.02126528442317916,
-      "grad_norm": 1.8195337057113647,
-      "learning_rate": 0.0,
-      "loss": 1.0902,
-      "step": 50
-    },
-    {
-      "epoch": 0.02126528442317916,
-      "eval_loss": 1.979973554611206,
-      "eval_runtime": 42.3444,
-      "eval_samples_per_second": 23.38,
-      "eval_steps_per_second": 11.69,
-      "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 sha256:14215c2ba727af56389e5a74c891a1128628f4542eb9a17d58c07b79a75b1c06
+oid sha256:2a19124f781a1e92c356f87d71eecc9954dcd1210d65b24810b99377a1b1704f
 size 6776