Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd11b513214d933db443ffb11fab092e4d6a61996f946075a0ace8f578a6b93
+oid sha256:1a108caa133c396d44ab9dff2a27d67d96866b2d2cbe83d7bd21100c5417c590
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3220425797c34586c09a9c059365760d75bf52f11239d1f2ef0be6ef893e064
+oid sha256:e2f8108b4db96948fbabd90394bb04c2e00573de0ba6a38725971deb35bd27af
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6be89b2cd2a89bc9a357c462211278505e1756ffdfc78ecf89b3010a0b8981e
+oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
+oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
 size 1064

last-checkpoint/trainer_state.json

@@ -1,49 +1,56 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3333333333333333,
-  "eval_steps": 2,
-  "global_step": 2,
+  "epoch": 0.25,
+  "eval_steps": 3,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.16666666666666666,
+      "epoch": 0.08333333333333333,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 1.3997,
+      "loss": 1.4927,
       "step": 1
     },
     {
-      "epoch": 0.16666666666666666,
-      "eval_loss": 1.4973297119140625,
-      "eval_runtime": 0.2886,
-      "eval_samples_per_second": 10.395,
-      "eval_steps_per_second": 6.93,
+      "epoch": 0.08333333333333333,
+      "eval_loss": 1.4977792501449585,
+      "eval_runtime": 0.3019,
+      "eval_samples_per_second": 9.937,
+      "eval_steps_per_second": 9.937,
       "step": 1
     },
     {
-      "epoch": 0.3333333333333333,
-      "grad_norm": 5.478867530822754,
+      "epoch": 0.16666666666666666,
+      "grad_norm": 4.949731349945068,
       "learning_rate": 2e-05,
-      "loss": 1.4535,
+      "loss": 1.307,
       "step": 2
     },
     {
-      "epoch": 0.3333333333333333,
-      "eval_loss": 1.4973297119140625,
-      "eval_runtime": 0.284,
-      "eval_samples_per_second": 10.565,
-      "eval_steps_per_second": 7.043,
-      "step": 2
+      "epoch": 0.25,
+      "grad_norm": 5.8763322830200195,
+      "learning_rate": 4e-05,
+      "loss": 1.5735,
+      "step": 3
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.4451128244400024,
+      "eval_runtime": 0.4158,
+      "eval_samples_per_second": 7.215,
+      "eval_steps_per_second": 7.215,
+      "step": 3
     }
   ],
   "logging_steps": 1,
-  "max_steps": 6,
+  "max_steps": 10,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 2,
+  "save_steps": 3,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -56,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 739825699258368.0,
+  "total_flos": 554869274443776.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74dcf4a29346d06a18985986c93532599870827345febcfc1739afefe0e2e2b9
+oid sha256:1dfa5dd032e4a03f440be49b93d0489893f415e88c3769ffa1903e5787dfef9f
 size 6776