Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
-    "k_proj",
-    "v_proj",
     "down_proj",
+    "k_proj",
     "q_proj",
-    "gate_proj"
+    "o_proj",
+    "gate_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:cd369857a58facdb719310ed0c433f98021e0cb70cbf79051b3acc1a5a7e5766
+oid sha256:b3eafd208c8b1b308a4db4817d9f91069457d86ff52bcd8f222fabac8ae2f964
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:052abd428764f2dfe7a361966d305bf9b9a3bf0356a650b684cd5c0f17213f27
+oid sha256:830786a12465bd667b8cbe5f848bdfdca0ca44728a7f8240a05c6c53d7236291
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
+oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004858299595141701,
+  "epoch": 0.0072874493927125505,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0008097165991902834,
-      "grad_norm": 5.243322849273682,
+      "grad_norm": 5.536149024963379,
       "learning_rate": 2e-05,
       "loss": 14.12,
       "step": 1
@@ -18,14 +18,14 @@
     {
       "epoch": 0.0008097165991902834,
       "eval_loss": 16.039548873901367,
-      "eval_runtime": 48.3021,
-      "eval_samples_per_second": 5.403,
-      "eval_steps_per_second": 5.403,
+      "eval_runtime": 46.298,
+      "eval_samples_per_second": 5.637,
+      "eval_steps_per_second": 5.637,
       "step": 1
     },
     {
       "epoch": 0.0016194331983805667,
-      "grad_norm": 5.311802387237549,
+      "grad_norm": 5.57291841506958,
       "learning_rate": 4e-05,
       "loss": 14.9434,
       "step": 2
@@ -34,45 +34,74 @@
       "epoch": 0.0024291497975708503,
       "grad_norm": NaN,
       "learning_rate": 4e-05,
-      "loss": 17.5635,
+      "loss": 17.5653,
       "step": 3
     },
     {
       "epoch": 0.0024291497975708503,
-      "eval_loss": 16.010040283203125,
-      "eval_runtime": 47.6629,
-      "eval_samples_per_second": 5.476,
-      "eval_steps_per_second": 5.476,
+      "eval_loss": 16.010469436645508,
+      "eval_runtime": 48.2421,
+      "eval_samples_per_second": 5.41,
+      "eval_steps_per_second": 5.41,
       "step": 3
     },
     {
       "epoch": 0.0032388663967611335,
-      "grad_norm": 4.934993267059326,
+      "grad_norm": 5.217444896697998,
       "learning_rate": 6e-05,
-      "loss": 15.4629,
+      "loss": 15.4635,
       "step": 4
     },
     {
       "epoch": 0.004048582995951417,
-      "grad_norm": 6.582982063293457,
+      "grad_norm": 6.765219688415527,
       "learning_rate": 8e-05,
-      "loss": 14.5189,
+      "loss": 14.5212,
       "step": 5
     },
     {
       "epoch": 0.004858299595141701,
-      "grad_norm": 7.352993011474609,
+      "grad_norm": 7.5979485511779785,
       "learning_rate": 0.0001,
-      "loss": 14.5364,
+      "loss": 14.5423,
       "step": 6
     },
     {
       "epoch": 0.004858299595141701,
-      "eval_loss": 15.222670555114746,
-      "eval_runtime": 47.7487,
-      "eval_samples_per_second": 5.466,
-      "eval_steps_per_second": 5.466,
+      "eval_loss": 15.2241849899292,
+      "eval_runtime": 47.8959,
+      "eval_samples_per_second": 5.449,
+      "eval_steps_per_second": 5.449,
       "step": 6
+    },
+    {
+      "epoch": 0.005668016194331984,
+      "grad_norm": 7.779355049133301,
+      "learning_rate": 0.00012,
+      "loss": 16.3143,
+      "step": 7
+    },
+    {
+      "epoch": 0.006477732793522267,
+      "grad_norm": 8.685688972473145,
+      "learning_rate": 0.00014,
+      "loss": 13.914,
+      "step": 8
+    },
+    {
+      "epoch": 0.0072874493927125505,
+      "grad_norm": 11.748001098632812,
+      "learning_rate": 0.00016,
+      "loss": 13.1216,
+      "step": 9
+    },
+    {
+      "epoch": 0.0072874493927125505,
+      "eval_loss": 12.131016731262207,
+      "eval_runtime": 47.8201,
+      "eval_samples_per_second": 5.458,
+      "eval_steps_per_second": 5.458,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 985898535616512.0,
+  "total_flos": 1478847803424768.0,
   "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:a6e1305fc8f281ddb72b2abbc2f99245c4a414545702847872a68fca4d715eef
+oid sha256:cc7eb56965fd55276c944caeebbd855891392f90553ede8609b47d5de737c680
 size 6776