Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db68505416b43b5ab3144c095946dca5c0470948630bb2b59f05350177c6a35e
+oid sha256:1040764725569afb7a85cd33866c01423464706e95a3c1240071e87efdfb1539
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac23af39d6e81cb77fbfee9ae60700a8a02757620c830e41030a2ab21bb1a28
+oid sha256:2385c1ab6fa561783a6d479ae78162a5a74b3ea6a4f5c453160c03cda40e7086
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7092244c60798e1ab03d4fe68ee97ba243124819620dca59a1f7c2ad2682481a
+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

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14461315979754158,
-  "eval_steps": 10,
-  "global_step": 50,
+  "epoch": 0.0028922631959508315,
+  "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": 0.0028922631959508315,
       "eval_loss": NaN,
-      "eval_runtime": 6.2947,
-      "eval_samples_per_second": 23.194,
-      "eval_steps_per_second": 11.597,
+      "eval_runtime": 6.3062,
+      "eval_samples_per_second": 23.152,
+      "eval_steps_per_second": 11.576,
       "step": 1
-    },
-    {
-      "epoch": 0.014461315979754157,
-      "grad_norm": 10.416779518127441,
-      "learning_rate": 5e-05,
-      "loss": 14.9854,
-      "step": 5
-    },
-    {
-      "epoch": 0.028922631959508314,
-      "grad_norm": 13.535470008850098,
-      "learning_rate": 0.0001,
-      "loss": 14.8002,
-      "step": 10
-    },
-    {
-      "epoch": 0.028922631959508314,
-      "eval_loss": NaN,
-      "eval_runtime": 5.7587,
-      "eval_samples_per_second": 25.353,
-      "eval_steps_per_second": 12.676,
-      "step": 10
-    },
-    {
-      "epoch": 0.04338394793926247,
-      "grad_norm": 20.537771224975586,
-      "learning_rate": 9.619397662556435e-05,
-      "loss": 11.9873,
-      "step": 15
-    },
-    {
-      "epoch": 0.05784526391901663,
-      "grad_norm": 14.810287475585938,
-      "learning_rate": 8.535533905932738e-05,
-      "loss": 7.629,
-      "step": 20
-    },
-    {
-      "epoch": 0.05784526391901663,
-      "eval_loss": NaN,
-      "eval_runtime": 5.8211,
-      "eval_samples_per_second": 25.081,
-      "eval_steps_per_second": 12.541,
-      "step": 20
-    },
-    {
-      "epoch": 0.07230657989877079,
-      "grad_norm": 16.019132614135742,
-      "learning_rate": 6.91341716182545e-05,
-      "loss": 4.178,
-      "step": 25
-    },
-    {
-      "epoch": 0.08676789587852494,
-      "grad_norm": 12.57477855682373,
-      "learning_rate": 5e-05,
-      "loss": 2.7147,
-      "step": 30
-    },
-    {
-      "epoch": 0.08676789587852494,
-      "eval_loss": NaN,
-      "eval_runtime": 5.8652,
-      "eval_samples_per_second": 24.892,
-      "eval_steps_per_second": 12.446,
-      "step": 30
-    },
-    {
-      "epoch": 0.1012292118582791,
-      "grad_norm": 7.327167510986328,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 1.4571,
-      "step": 35
-    },
-    {
-      "epoch": 0.11569052783803326,
-      "grad_norm": 8.205806732177734,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.7687,
-      "step": 40
-    },
-    {
-      "epoch": 0.11569052783803326,
-      "eval_loss": NaN,
-      "eval_runtime": 5.9274,
-      "eval_samples_per_second": 24.631,
-      "eval_steps_per_second": 12.316,
-      "step": 40
-    },
-    {
-      "epoch": 0.1301518438177874,
-      "grad_norm": 7.59572696685791,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.922,
-      "step": 45
-    },
-    {
-      "epoch": 0.14461315979754158,
-      "grad_norm": 5.605504512786865,
-      "learning_rate": 0.0,
-      "loss": 0.5988,
-      "step": 50
-    },
-    {
-      "epoch": 0.14461315979754158,
-      "eval_loss": NaN,
-      "eval_runtime": 5.7064,
-      "eval_samples_per_second": 25.585,
-      "eval_steps_per_second": 12.793,
-      "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": 1621491292569600.0,
+  "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 sha256:1902621960c56a0cce64c50cce46dc3e46c3215f6ff1ccb44365bafa5c5bfa8c
+oid sha256:bd4275ff3d26fd9049abbaa16020213e17f044c3f332528589704b35494b01f4
 size 6776