Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
     "v_proj",
-    "o_proj",
-    "down_proj",
     "gate_proj",
-    "up_proj"
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_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 sha256:8d5d825604a999751abc205aa2360be9ac17ae2adf32df32ee1a962155b6acc4
+oid sha256:8637d98b9e8f2383f1d8e7d249eb7d420976d90f9bc2f6ecaa78ffbbc3f5b73f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2339e6a163a447e287b8f491e1231c10c9a5adcb351a9fbb85b2332c6a6635
+oid sha256:42bfb32aeec4c8449802c213c5c94f8330903d85114eded22c94a2b4706e6403
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:787ef78ee12881294c4aa83ed64603709fff88fc133de1a040e06eba2a245935
+oid sha256:1f9d63457fb0762bec521007b4b65dfde2dbfedf3cf13f579982482514a7d902
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00037837224261228196,
+  "epoch": 0.00022702334556736918,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 3.7837224261228196e-05,
-      "grad_norm": 15.425179481506348,
+      "grad_norm": 14.805928230285645,
       "learning_rate": 2e-05,
       "loss": 4.2775,
       "step": 1
@@ -18,97 +18,61 @@
     {
       "epoch": 3.7837224261228196e-05,
       "eval_loss": 1.0869630575180054,
-      "eval_runtime": 1969.7164,
-      "eval_samples_per_second": 2.825,
-      "eval_steps_per_second": 2.825,
+      "eval_runtime": 2378.1464,
+      "eval_samples_per_second": 2.34,
+      "eval_steps_per_second": 2.34,
       "step": 1
     },
     {
       "epoch": 7.567444852245639e-05,
-      "grad_norm": 14.54034423828125,
+      "grad_norm": 14.053690910339355,
       "learning_rate": 4e-05,
       "loss": 4.198,
       "step": 2
     },
     {
       "epoch": 0.00011351167278368459,
-      "grad_norm": 9.865498542785645,
+      "grad_norm": 9.68853759765625,
       "learning_rate": 6e-05,
-      "loss": 4.3061,
+      "loss": 4.309,
       "step": 3
     },
     {
       "epoch": 0.00011351167278368459,
-      "eval_loss": 0.9358382225036621,
-      "eval_runtime": 2314.6741,
-      "eval_samples_per_second": 2.404,
-      "eval_steps_per_second": 2.404,
+      "eval_loss": 0.9365310072898865,
+      "eval_runtime": 2383.4538,
+      "eval_samples_per_second": 2.334,
+      "eval_steps_per_second": 2.334,
       "step": 3
     },
     {
       "epoch": 0.00015134889704491279,
-      "grad_norm": 7.155860424041748,
+      "grad_norm": 7.027285099029541,
       "learning_rate": 8e-05,
-      "loss": 3.874,
+      "loss": 3.8788,
       "step": 4
     },
     {
       "epoch": 0.00018918612130614098,
-      "grad_norm": 4.540463924407959,
+      "grad_norm": 4.5182366371154785,
       "learning_rate": 0.0001,
-      "loss": 3.2857,
+      "loss": 3.2846,
       "step": 5
     },
     {
       "epoch": 0.00022702334556736918,
-      "grad_norm": 3.66566801071167,
+      "grad_norm": 3.581972122192383,
       "learning_rate": 0.00012,
-      "loss": 3.2424,
+      "loss": 3.2404,
       "step": 6
     },
     {
       "epoch": 0.00022702334556736918,
-      "eval_loss": 0.7986580729484558,
-      "eval_runtime": 2384.8555,
-      "eval_samples_per_second": 2.333,
-      "eval_steps_per_second": 2.333,
+      "eval_loss": 0.7990255951881409,
+      "eval_runtime": 2317.8914,
+      "eval_samples_per_second": 2.4,
+      "eval_steps_per_second": 2.4,
       "step": 6
-    },
-    {
-      "epoch": 0.00026486056982859735,
-      "grad_norm": 4.557755470275879,
-      "learning_rate": 0.00014,
-      "loss": 3.3631,
-      "step": 7
-    },
-    {
-      "epoch": 0.00030269779408982557,
-      "grad_norm": 3.7365407943725586,
-      "learning_rate": 0.00016,
-      "loss": 2.95,
-      "step": 8
-    },
-    {
-      "epoch": 0.00034053501835105374,
-      "grad_norm": 3.51993989944458,
-      "learning_rate": 0.00018,
-      "loss": 2.4298,
-      "step": 9
-    },
-    {
-      "epoch": 0.00034053501835105374,
-      "eval_loss": 0.6866493821144104,
-      "eval_runtime": 2377.7125,
-      "eval_samples_per_second": 2.34,
-      "eval_steps_per_second": 2.34,
-      "step": 9
-    },
-    {
-      "epoch": 0.00037837224261228196,
-      "grad_norm": 2.6987967491149902,
-      "learning_rate": 0.0002,
-      "loss": 2.6814,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +87,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 7031294986813440.0,
+  "total_flos": 4218776992088064.0,
   "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 sha256:291b68746f328c8f5d6f048071017ecfa63bfb5a09e3a8555c42108a03bc05b5
+oid sha256:8c49defa0185f3971ee1ec8e0038c402fa3301af18c0e87abd89a3514b3a03b4
 size 6776