Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
     "up_proj",
-    "v_proj",
-    "q_proj",
+    "gate_proj",
     "o_proj",
-    "gate_proj"
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "v_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:e9e75ea8842804f67731a1381ebcf772d861ce735e4c8169fdaf6a92730000af
+oid sha256:880b442943ff2aa3e48ebcf36c6976cee9e4e2d9f8eef2811873ac4ca9658696
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6da998bd689061d0492c683a439af5ca5c45d15ca5cecdae50754123eba437
+oid sha256:ffba35bcc4792c076b7cfb45ceb3d53776881bc3f3e4294fa76cd64f44e67298
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c134cc708ce9d81193583fcacdd32f3e4fe0ff99e63b47726e2fd3625affde6
+oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8333333333333334,
+  "epoch": 0.75,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12,103 +12,96 @@
       "epoch": 0.08333333333333333,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 1.4924,
+      "loss": 1.4927,
       "step": 1
     },
     {
       "epoch": 0.08333333333333333,
-      "eval_loss": 1.4975985288619995,
-      "eval_runtime": 0.1911,
-      "eval_samples_per_second": 15.701,
-      "eval_steps_per_second": 15.701,
+      "eval_loss": 1.4977792501449585,
+      "eval_runtime": 0.3019,
+      "eval_samples_per_second": 9.937,
+      "eval_steps_per_second": 9.937,
       "step": 1
     },
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 5.183752536773682,
+      "grad_norm": 4.949731349945068,
       "learning_rate": 2e-05,
-      "loss": 1.3074,
+      "loss": 1.307,
       "step": 2
     },
     {
       "epoch": 0.25,
-      "grad_norm": 6.239664077758789,
+      "grad_norm": 5.8763322830200195,
       "learning_rate": 4e-05,
-      "loss": 1.5739,
+      "loss": 1.5735,
       "step": 3
     },
     {
       "epoch": 0.25,
-      "eval_loss": 1.4466005563735962,
-      "eval_runtime": 0.211,
-      "eval_samples_per_second": 14.216,
-      "eval_steps_per_second": 14.216,
+      "eval_loss": 1.4451128244400024,
+      "eval_runtime": 0.4158,
+      "eval_samples_per_second": 7.215,
+      "eval_steps_per_second": 7.215,
       "step": 3
     },
     {
       "epoch": 0.3333333333333333,
-      "grad_norm": 5.012392044067383,
+      "grad_norm": 4.730646133422852,
       "learning_rate": 6e-05,
-      "loss": 1.2793,
+      "loss": 1.2767,
       "step": 4
     },
     {
       "epoch": 0.4166666666666667,
-      "grad_norm": 3.691774845123291,
+      "grad_norm": 3.4440248012542725,
       "learning_rate": 8e-05,
-      "loss": 1.3057,
+      "loss": 1.3011,
       "step": 5
     },
     {
       "epoch": 0.5,
-      "grad_norm": 3.0195882320404053,
+      "grad_norm": 2.8259096145629883,
       "learning_rate": 0.0001,
-      "loss": 1.0885,
+      "loss": 1.0815,
       "step": 6
     },
     {
       "epoch": 0.5,
-      "eval_loss": 0.8231927752494812,
-      "eval_runtime": 0.2024,
-      "eval_samples_per_second": 14.826,
-      "eval_steps_per_second": 14.826,
+      "eval_loss": 0.816199779510498,
+      "eval_runtime": 0.4516,
+      "eval_samples_per_second": 6.643,
+      "eval_steps_per_second": 6.643,
       "step": 6
     },
     {
       "epoch": 0.5833333333333334,
-      "grad_norm": 2.5046184062957764,
+      "grad_norm": 2.387253522872925,
       "learning_rate": 0.00012,
-      "loss": 0.8365,
+      "loss": 0.8264,
       "step": 7
     },
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 2.7154762744903564,
+      "grad_norm": 2.6841723918914795,
       "learning_rate": 0.00014,
-      "loss": 0.5475,
+      "loss": 0.5359,
       "step": 8
     },
     {
       "epoch": 0.75,
-      "grad_norm": 2.8666529655456543,
+      "grad_norm": 2.8740291595458984,
       "learning_rate": 0.00016,
-      "loss": 0.2414,
+      "loss": 0.229,
       "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,
+      "eval_loss": 0.04347331449389458,
+      "eval_runtime": 0.4018,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 7.467,
       "step": 9
-    },
-    {
-      "epoch": 0.8333333333333334,
-      "grad_norm": 2.775001049041748,
-      "learning_rate": 0.00018,
-      "loss": 0.1515,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +116,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 1664607823331328.0,
   "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:d5fa11f84d8d8e5e8936ae65e6012c835679c9ed6678232c43544c849861d322
+oid sha256:1dfa5dd032e4a03f440be49b93d0489893f415e88c3769ffa1903e5787dfef9f
 size 6776