Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
-    "v_proj",
     "up_proj",
-    "gate_proj",
     "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_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:b8301b0a7c2edb3ef49e63e955b94c5f7aa54ca23938bacd9ad6f48921e865cf
+oid sha256:fb1c264f6196955ec5d50aceba9f69ebb491f5f59d3179389aba510cf2502268
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3ae107236b21ac299da4f9c410ecd16d7252c9ab7addeb29d2c9ae41cabed5
+oid sha256:684456c183eb573dc7011e2de17428357e159ff24159fcec08d3ac7b0999af5b
 size 40131268

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:488baf69d6cf1d409ec86db959f5eb220fc31086ce80e19f640d54604f101e7d
+oid sha256:2e524ff3216d25dca0d2eceddd64da44de7a73e6c490de4502f1a3d3a54b33a4
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00659582264565775,
+  "epoch": 0.007328691828508612,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,90 +18,97 @@
     {
       "epoch": 0.0007328691828508611,
       "eval_loss": 12.304828643798828,
-      "eval_runtime": 57.0786,
-      "eval_samples_per_second": 5.046,
-      "eval_steps_per_second": 5.046,
+      "eval_runtime": 56.9499,
+      "eval_samples_per_second": 5.057,
+      "eval_steps_per_second": 5.057,
       "step": 1
     },
     {
       "epoch": 0.0014657383657017222,
-      "grad_norm": 39.946189880371094,
+      "grad_norm": 42.04989242553711,
       "learning_rate": 2e-05,
       "loss": 10.6283,
       "step": 2
     },
     {
       "epoch": 0.0021986075485525836,
-      "grad_norm": 36.35205078125,
+      "grad_norm": 37.467315673828125,
       "learning_rate": 4e-05,
       "loss": 11.3833,
       "step": 3
     },
     {
       "epoch": 0.0021986075485525836,
-      "eval_loss": 12.076598167419434,
-      "eval_runtime": 56.5009,
-      "eval_samples_per_second": 5.097,
-      "eval_steps_per_second": 5.097,
+      "eval_loss": 12.051217079162598,
+      "eval_runtime": 56.814,
+      "eval_samples_per_second": 5.069,
+      "eval_steps_per_second": 5.069,
       "step": 3
     },
     {
       "epoch": 0.0029314767314034445,
-      "grad_norm": 43.041465759277344,
+      "grad_norm": 44.678558349609375,
       "learning_rate": 6e-05,
-      "loss": 9.7042,
+      "loss": 9.6695,
       "step": 4
     },
     {
       "epoch": 0.003664345914254306,
-      "grad_norm": 46.06086349487305,
+      "grad_norm": 48.171749114990234,
       "learning_rate": 8e-05,
-      "loss": 14.8458,
+      "loss": 14.795,
       "step": 5
     },
     {
       "epoch": 0.004397215097105167,
-      "grad_norm": 31.989681243896484,
+      "grad_norm": 32.893001556396484,
       "learning_rate": 0.0001,
-      "loss": 7.5335,
+      "loss": 7.3908,
       "step": 6
     },
     {
       "epoch": 0.004397215097105167,
-      "eval_loss": 9.594720840454102,
-      "eval_runtime": 56.5212,
-      "eval_samples_per_second": 5.095,
-      "eval_steps_per_second": 5.095,
+      "eval_loss": 9.441511154174805,
+      "eval_runtime": 56.7951,
+      "eval_samples_per_second": 5.071,
+      "eval_steps_per_second": 5.071,
       "step": 6
     },
     {
       "epoch": 0.005130084279956028,
-      "grad_norm": 36.64425277709961,
+      "grad_norm": 38.151817321777344,
       "learning_rate": 0.00012,
-      "loss": 7.3467,
+      "loss": 7.0317,
       "step": 7
     },
     {
       "epoch": 0.005862953462806889,
-      "grad_norm": 32.363521575927734,
+      "grad_norm": 32.140113830566406,
       "learning_rate": 0.00014,
-      "loss": 5.3234,
+      "loss": 5.01,
       "step": 8
     },
     {
       "epoch": 0.00659582264565775,
-      "grad_norm": 26.217491149902344,
+      "grad_norm": 26.151323318481445,
       "learning_rate": 0.00016,
-      "loss": 6.7949,
+      "loss": 6.6914,
       "step": 9
     },
     {
       "epoch": 0.00659582264565775,
-      "eval_loss": 6.482934951782227,
-      "eval_runtime": 56.9284,
-      "eval_samples_per_second": 5.059,
-      "eval_steps_per_second": 5.059,
+      "eval_loss": 6.388987064361572,
+      "eval_runtime": 56.8562,
+      "eval_samples_per_second": 5.065,
+      "eval_steps_per_second": 5.065,
       "step": 9
+    },
+    {
+      "epoch": 0.007328691828508612,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 8.1154,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1770795621679104.0,
+  "total_flos": 1967550690754560.0,
   "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 sha256:72b5ec9cd53bed712805221792024653bec1693ae9132893c54190849f7ca423
+oid sha256:722f3b82bb852127c4404471dd8bb057b70f4e0cb5a02b713538b276ca5a19c9
 size 6712