Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "gate_proj",
-    "o_proj",
-    "q_proj",
     "k_proj",
     "down_proj",
-    "v_proj"
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "gate_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 sha256:5b37c3c3688bef73b576a3530942694ccb9f025c5852ff9698238ba1124acec3
+oid sha256:e9e75ea8842804f67731a1381ebcf772d861ce735e4c8169fdaf6a92730000af
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9857d29be73ca23bbf30f9c1582a975f9e8c9413eaf40fd4594f3094f2f38238
+oid sha256:3e6da998bd689061d0492c683a439af5ca5c45d15ca5cecdae50754123eba437
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
+oid sha256:0c134cc708ce9d81193583fcacdd32f3e4fe0ff99e63b47726e2fd3625affde6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 0.8333333333333334,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12,67 +12,103 @@
       "epoch": 0.08333333333333333,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 1.4927,
+      "loss": 1.4924,
       "step": 1
     },
     {
       "epoch": 0.08333333333333333,
-      "eval_loss": 1.4977792501449585,
-      "eval_runtime": 0.3019,
-      "eval_samples_per_second": 9.937,
-      "eval_steps_per_second": 9.937,
+      "eval_loss": 1.4975985288619995,
+      "eval_runtime": 0.1911,
+      "eval_samples_per_second": 15.701,
+      "eval_steps_per_second": 15.701,
       "step": 1
     },
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 4.949731349945068,
+      "grad_norm": 5.183752536773682,
       "learning_rate": 2e-05,
-      "loss": 1.307,
+      "loss": 1.3074,
       "step": 2
     },
     {
       "epoch": 0.25,
-      "grad_norm": 5.8763322830200195,
+      "grad_norm": 6.239664077758789,
       "learning_rate": 4e-05,
-      "loss": 1.5735,
+      "loss": 1.5739,
       "step": 3
     },
     {
       "epoch": 0.25,
-      "eval_loss": 1.4451128244400024,
-      "eval_runtime": 0.4158,
-      "eval_samples_per_second": 7.215,
-      "eval_steps_per_second": 7.215,
+      "eval_loss": 1.4466005563735962,
+      "eval_runtime": 0.211,
+      "eval_samples_per_second": 14.216,
+      "eval_steps_per_second": 14.216,
       "step": 3
     },
     {
       "epoch": 0.3333333333333333,
-      "grad_norm": 4.730646133422852,
+      "grad_norm": 5.012392044067383,
       "learning_rate": 6e-05,
-      "loss": 1.2767,
+      "loss": 1.2793,
       "step": 4
     },
     {
       "epoch": 0.4166666666666667,
-      "grad_norm": 3.4440248012542725,
+      "grad_norm": 3.691774845123291,
       "learning_rate": 8e-05,
-      "loss": 1.3011,
+      "loss": 1.3057,
       "step": 5
     },
     {
       "epoch": 0.5,
-      "grad_norm": 2.8259096145629883,
+      "grad_norm": 3.0195882320404053,
       "learning_rate": 0.0001,
-      "loss": 1.0815,
+      "loss": 1.0885,
       "step": 6
     },
     {
       "epoch": 0.5,
-      "eval_loss": 0.816199779510498,
-      "eval_runtime": 0.4516,
-      "eval_samples_per_second": 6.643,
-      "eval_steps_per_second": 6.643,
+      "eval_loss": 0.8231927752494812,
+      "eval_runtime": 0.2024,
+      "eval_samples_per_second": 14.826,
+      "eval_steps_per_second": 14.826,
       "step": 6
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 2.5046184062957764,
+      "learning_rate": 0.00012,
+      "loss": 0.8365,
+      "step": 7
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.7154762744903564,
+      "learning_rate": 0.00014,
+      "loss": 0.5475,
+      "step": 8
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.8666529655456543,
+      "learning_rate": 0.00016,
+      "loss": 0.2414,
+      "step": 9
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.049252700060606,
+      "eval_runtime": 0.2077,
+      "eval_samples_per_second": 14.444,
+      "eval_steps_per_second": 14.444,
+      "step": 9
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.775001049041748,
+      "learning_rate": 0.00018,
+      "loss": 0.1515,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1109738548887552.0,
+  "total_flos": 1849564248145920.0,
   "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 sha256:1dfa5dd032e4a03f440be49b93d0489893f415e88c3769ffa1903e5787dfef9f
+oid sha256:d5fa11f84d8d8e5e8936ae65e6012c835679c9ed6678232c43544c849861d322
 size 6776