Training in progress, step 26, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "up_proj",
-    "k_proj",
-    "down_proj",
     "v_proj",
+    "up_proj",
     "o_proj",
-    "gate_proj"
+    "gate_proj",
+    "k_proj",
+    "down_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:e6daf585527ce7949465a751f906278d017f700ad8312595d76c9724a21c7cb8
+oid sha256:dd8999f4f20f203a48ab2768a173ae6e22f7ef059d5922acbdb6f7f93cdaa31a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f2180e78c8f9b2737fd8fe2e82edc07309340956741a9e31795d58d5d5ef7ff
+oid sha256:a56430a939b2e00864acd65d2c40a4a33d9dfe8c64027c6eab18d450528032a2
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
+oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011927836588638736,
-  "eval_steps": 2,
-  "global_step": 5,
+  "epoch": 0.06202475026092143,
+  "eval_steps": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0023855673177277472,
-      "grad_norm": 1.2481120824813843,
+      "grad_norm": 1.3246102333068848,
       "learning_rate": 1e-05,
       "loss": 0.9265,
       "step": 1
@@ -18,61 +18,208 @@
     {
       "epoch": 0.0023855673177277472,
       "eval_loss": 0.9870346188545227,
-      "eval_runtime": 65.0919,
-      "eval_samples_per_second": 10.846,
-      "eval_steps_per_second": 5.423,
+      "eval_runtime": 65.1117,
+      "eval_samples_per_second": 10.843,
+      "eval_steps_per_second": 5.421,
       "step": 1
     },
     {
       "epoch": 0.0047711346354554944,
-      "grad_norm": 1.427655577659607,
+      "grad_norm": 1.5241637229919434,
       "learning_rate": 2e-05,
       "loss": 1.0298,
       "step": 2
     },
-    {
-      "epoch": 0.0047711346354554944,
-      "eval_loss": 0.9387862086296082,
-      "eval_runtime": 16.6543,
-      "eval_samples_per_second": 42.392,
-      "eval_steps_per_second": 21.196,
-      "step": 2
-    },
     {
       "epoch": 0.007156701953183241,
-      "grad_norm": 1.2481718063354492,
+      "grad_norm": 1.3183329105377197,
       "learning_rate": 3e-05,
-      "loss": 0.9639,
+      "loss": 0.9629,
       "step": 3
     },
     {
       "epoch": 0.009542269270910989,
-      "grad_norm": 1.2510924339294434,
+      "grad_norm": 1.3316704034805298,
       "learning_rate": 4e-05,
-      "loss": 0.9506,
-      "step": 4
-    },
-    {
-      "epoch": 0.009542269270910989,
-      "eval_loss": 0.8984954953193665,
-      "eval_runtime": 16.8324,
-      "eval_samples_per_second": 41.943,
-      "eval_steps_per_second": 20.971,
+      "loss": 0.9491,
       "step": 4
     },
     {
       "epoch": 0.011927836588638736,
-      "grad_norm": 1.215053677558899,
+      "grad_norm": 1.2836781740188599,
       "learning_rate": 5e-05,
-      "loss": 0.8298,
+      "loss": 0.8294,
       "step": 5
+    },
+    {
+      "epoch": 0.014313403906366482,
+      "grad_norm": 1.3446112871170044,
+      "learning_rate": 6e-05,
+      "loss": 0.7596,
+      "step": 6
+    },
+    {
+      "epoch": 0.01669897122409423,
+      "grad_norm": 1.3533251285552979,
+      "learning_rate": 7e-05,
+      "loss": 0.8652,
+      "step": 7
+    },
+    {
+      "epoch": 0.019084538541821978,
+      "grad_norm": 1.2886685132980347,
+      "learning_rate": 8e-05,
+      "loss": 0.6794,
+      "step": 8
+    },
+    {
+      "epoch": 0.021470105859549723,
+      "grad_norm": 1.0436530113220215,
+      "learning_rate": 9e-05,
+      "loss": 0.5633,
+      "step": 9
+    },
+    {
+      "epoch": 0.02385567317727747,
+      "grad_norm": 0.8520669937133789,
+      "learning_rate": 0.0001,
+      "loss": 0.4955,
+      "step": 10
+    },
+    {
+      "epoch": 0.02624124049500522,
+      "grad_norm": 0.7037628889083862,
+      "learning_rate": 9.98458666866564e-05,
+      "loss": 0.3973,
+      "step": 11
+    },
+    {
+      "epoch": 0.028626807812732965,
+      "grad_norm": 0.8181518912315369,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 0.4359,
+      "step": 12
+    },
+    {
+      "epoch": 0.031012375130460713,
+      "grad_norm": 0.6722888946533203,
+      "learning_rate": 9.861849601988383e-05,
+      "loss": 0.3231,
+      "step": 13
+    },
+    {
+      "epoch": 0.031012375130460713,
+      "eval_loss": 0.303219199180603,
+      "eval_runtime": 16.6267,
+      "eval_samples_per_second": 42.462,
+      "eval_steps_per_second": 21.231,
+      "step": 13
+    },
+    {
+      "epoch": 0.03339794244818846,
+      "grad_norm": 0.6669241786003113,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.3008,
+      "step": 14
+    },
+    {
+      "epoch": 0.035783509765916204,
+      "grad_norm": 0.6451194882392883,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.2879,
+      "step": 15
+    },
+    {
+      "epoch": 0.038169077083643956,
+      "grad_norm": 0.6567999720573425,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.2355,
+      "step": 16
+    },
+    {
+      "epoch": 0.0405546444013717,
+      "grad_norm": 0.534218430519104,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 0.1906,
+      "step": 17
+    },
+    {
+      "epoch": 0.042940211719099446,
+      "grad_norm": 0.7300930023193359,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.2783,
+      "step": 18
+    },
+    {
+      "epoch": 0.0453257790368272,
+      "grad_norm": 0.5893413424491882,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 0.1718,
+      "step": 19
+    },
+    {
+      "epoch": 0.04771134635455494,
+      "grad_norm": 0.6724103093147278,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.1679,
+      "step": 20
+    },
+    {
+      "epoch": 0.05009691367228269,
+      "grad_norm": 0.8837454915046692,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.1861,
+      "step": 21
+    },
+    {
+      "epoch": 0.05248248099001044,
+      "grad_norm": 0.7627610564231873,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.1885,
+      "step": 22
+    },
+    {
+      "epoch": 0.054868048307738185,
+      "grad_norm": 0.47815459966659546,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 0.1022,
+      "step": 23
+    },
+    {
+      "epoch": 0.05725361562546593,
+      "grad_norm": 0.46670857071876526,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.1405,
+      "step": 24
+    },
+    {
+      "epoch": 0.059639182943193675,
+      "grad_norm": 0.5231714844703674,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1264,
+      "step": 25
+    },
+    {
+      "epoch": 0.06202475026092143,
+      "grad_norm": 0.4806453585624695,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.1219,
+      "step": 26
+    },
+    {
+      "epoch": 0.06202475026092143,
+      "eval_loss": 0.0903618112206459,
+      "eval_runtime": 16.6327,
+      "eval_samples_per_second": 42.447,
+      "eval_steps_per_second": 21.223,
+      "step": 26
     }
   ],
   "logging_steps": 1,
-  "max_steps": 5,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 2,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -80,12 +227,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3295645846732800.0,
+  "total_flos": 1.713735840301056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e263d391be8f592d64c6f477c3e14ccc7c583c050e5bbadc9320af574c2d1c3
+oid sha256:31b5cdd3cd707bf07eb2bb55c3a7762a30f419ba7acabac68f8e2c545a57fb8b
 size 6776