Training in progress, step 2, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375a7b623cd8a59ab3d10e500079c097a4547152217b681a810e226913f3d682
+oid sha256:ab80569229851ef850ebd7615a9d6b503a27bdf7d9215e786db688744b620de5
 size 42002136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5223988d47a2de5512e5c0de068bad3a8780d956d1677215b23ab175550c4bb9
+oid sha256:d49df34ac12930a27b6c1c60b5485de770d24907d44643cb11bed5d4e803f985
 size 21822612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f6b164984e5f0c6a9b66a5c3b228b696dfe0509b284cfd72ad745ce2466743
+oid sha256:6872307f4470a047155c6b916b2c9040d688e2f96562192a9d5c5fb6108984b7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003051338774887482,
+  "epoch": 0.0012205355099549928,
   "eval_steps": 2,
-  "global_step": 5,
+  "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0006102677549774964,
-      "grad_norm": 3.421682834625244,
+      "grad_norm": 3.7491719722747803,
       "learning_rate": 2e-05,
       "loss": 3.7463,
       "step": 1
@@ -18,58 +18,29 @@
     {
       "epoch": 0.0006102677549774964,
       "eval_loss": 3.6378390789031982,
-      "eval_runtime": 137.6009,
-      "eval_samples_per_second": 5.015,
-      "eval_steps_per_second": 5.015,
+      "eval_runtime": 127.7739,
+      "eval_samples_per_second": 5.4,
+      "eval_steps_per_second": 5.4,
       "step": 1
     },
     {
       "epoch": 0.0012205355099549928,
-      "grad_norm": 2.2864131927490234,
+      "grad_norm": 2.4883432388305664,
       "learning_rate": 4e-05,
       "loss": 3.1519,
       "step": 2
     },
     {
       "epoch": 0.0012205355099549928,
-      "eval_loss": 3.636766195297241,
-      "eval_runtime": 137.4407,
-      "eval_samples_per_second": 5.02,
-      "eval_steps_per_second": 5.02,
+      "eval_loss": 3.636899948120117,
+      "eval_runtime": 128.4391,
+      "eval_samples_per_second": 5.372,
+      "eval_steps_per_second": 5.372,
       "step": 2
-    },
-    {
-      "epoch": 0.0018308032649324891,
-      "grad_norm": 2.357367992401123,
-      "learning_rate": 6e-05,
-      "loss": 3.2508,
-      "step": 3
-    },
-    {
-      "epoch": 0.0024410710199099855,
-      "grad_norm": 2.7122113704681396,
-      "learning_rate": 8e-05,
-      "loss": 2.8676,
-      "step": 4
-    },
-    {
-      "epoch": 0.0024410710199099855,
-      "eval_loss": 3.6266050338745117,
-      "eval_runtime": 137.7678,
-      "eval_samples_per_second": 5.008,
-      "eval_steps_per_second": 5.008,
-      "step": 4
-    },
-    {
-      "epoch": 0.003051338774887482,
-      "grad_norm": 3.0725150108337402,
-      "learning_rate": 0.0001,
-      "loss": 3.607,
-      "step": 5
     }
   ],
   "logging_steps": 1,
-  "max_steps": 5,
+  "max_steps": 7,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 2,
@@ -80,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 704176176758784.0,
+  "total_flos": 265509050253312.0,
   "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 sha256:6a2c870520a9a7880f4c5f15ed3afdfcaf0a5beb91e3491c082bc8e761598a84
+oid sha256:a9344c361878f4869b2797bdf1f8d81734af396c9e1fdfc09e99f9bc8dec22bd
 size 6776