Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "v_proj",
     "q_proj",
+    "down_proj",
     "k_proj",
     "gate_proj",
-    "up_proj",
-    "down_proj",
-    "v_proj"
+    "up_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 sha256:5d0165165d309efe2bc67ec47e2fb6939609fabc938111d98e7b1570542826dd
+oid sha256:b86f1d75825127d6bdce267195ecc8e3b03228a53b17b923021815e62f1f022b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cebde071ebc7692d3308fd8930794e495278090d35bb7ce7c201261abdb2c13b
+oid sha256:39e84f08cb28b8a7c6faf406e8b310afe9a91c97e6c247d547cc2b4ce7102915
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6bf19e75a59ee8c6a96e9c63d30b78c698cbfef05ceb7eb28dd7602d0b1a826
+oid sha256:631dfb2aa9ae256eca5748a1b2ab04547dfc14e5e8346db748407ed5d049499d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
 size 1064

last-checkpoint/trainer_state.json

@@ -1,71 +1,56 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6666666666666666,
-  "eval_steps": 2,
-  "global_step": 4,
+  "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": 0.453,
+      "eval_samples_per_second": 6.622,
+      "eval_steps_per_second": 6.622,
       "step": 1
     },
     {
-      "epoch": 0.3333333333333333,
-      "grad_norm": 5.478867530822754,
+      "epoch": 0.16666666666666666,
+      "grad_norm": 4.665465831756592,
       "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": 0.5,
-      "grad_norm": 5.20695686340332,
+      "epoch": 0.25,
+      "grad_norm": 5.513491153717041,
       "learning_rate": 4e-05,
-      "loss": 1.5303,
+      "loss": 1.5735,
       "step": 3
     },
     {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 4.481665134429932,
-      "learning_rate": 6e-05,
-      "loss": 1.394,
-      "step": 4
-    },
-    {
-      "epoch": 0.6666666666666666,
-      "eval_loss": 1.2689329385757446,
-      "eval_runtime": 0.3021,
-      "eval_samples_per_second": 9.93,
-      "eval_steps_per_second": 6.62,
-      "step": 4
+      "epoch": 0.25,
+      "eval_loss": 1.4473786354064941,
+      "eval_runtime": 0.4679,
+      "eval_samples_per_second": 6.412,
+      "eval_steps_per_second": 6.412,
+      "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": {
@@ -78,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1479651398516736.0,
+  "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:ab37ef2135f6555964c7f23e135ed3a58c3b21e0a8dfdabb28e1c2f6cc491bb9
 size 6776