Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
+    "up_proj",
     "o_proj",
     "q_proj",
+    "k_proj",
+    "down_proj",
     "gate_proj",
-    "up_proj",
-    "k_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 sha256:535272549b1f5b90ea025e3ea410ae4a801f7f3d9886fb3bcfddba9153c93ded
+oid sha256:704283ad3282193d4b9cc263f29c3a552106472c0f16c5f186eb3328ee8192ff
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4272e8204e90c6c85d31243cfd9fca9ac77f1553b297a9f41324c4577644a1a
+oid sha256:b623d627db90cf0b0565f2210c8dd660a908e52b0f995753e9eb0b13a3297223
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03245da28a18b4bf0e9aa3981318b4c5a3d75cdaf1ce720f632a24751d3eb7e
+oid sha256:da371ed384dd48ba3f51b4afee7d61db3dfdb18617828b0330774642ccc5f0e8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006045492329781607,
+  "epoch": 0.000906823849467241,
   "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": 0.00010075820549636011,
-      "grad_norm": 8.359752932236722e+18,
+      "grad_norm": 6.578465480158216e+18,
       "learning_rate": 2e-05,
       "loss": 1.8654,
       "step": 1
@@ -18,61 +18,90 @@
     {
       "epoch": 0.00010075820549636011,
       "eval_loss": 1.7779617309570312,
-      "eval_runtime": 1454.9416,
-      "eval_samples_per_second": 2.872,
-      "eval_steps_per_second": 1.436,
+      "eval_runtime": 1454.0406,
+      "eval_samples_per_second": 2.874,
+      "eval_steps_per_second": 1.437,
       "step": 1
     },
     {
       "epoch": 0.00020151641099272022,
-      "grad_norm": 2.626370165041791e+18,
+      "grad_norm": 2.1462115130466632e+18,
       "learning_rate": 4e-05,
       "loss": 1.3359,
       "step": 2
     },
     {
       "epoch": 0.0003022746164890803,
-      "grad_norm": 3.249743505089626e+18,
+      "grad_norm": 2.517414610043142e+18,
       "learning_rate": 6e-05,
-      "loss": 1.3042,
+      "loss": 1.3138,
       "step": 3
     },
     {
       "epoch": 0.0003022746164890803,
-      "eval_loss": 1.7708849906921387,
-      "eval_runtime": 1454.6249,
-      "eval_samples_per_second": 2.873,
+      "eval_loss": 1.7785661220550537,
+      "eval_runtime": 1454.8386,
+      "eval_samples_per_second": 2.872,
       "eval_steps_per_second": 1.437,
       "step": 3
     },
     {
       "epoch": 0.00040303282198544043,
-      "grad_norm": 8.100253344674611e+18,
+      "grad_norm": 7.439758018171896e+18,
       "learning_rate": 8e-05,
-      "loss": 1.5396,
+      "loss": 1.5352,
       "step": 4
     },
     {
       "epoch": 0.0005037910274818005,
-      "grad_norm": 4.612551334078448e+18,
+      "grad_norm": 3.50965568439006e+18,
       "learning_rate": 0.0001,
-      "loss": 1.2117,
+      "loss": 1.2199,
       "step": 5
     },
     {
       "epoch": 0.0006045492329781607,
-      "grad_norm": 6.333141896013021e+18,
+      "grad_norm": 5.017360729099993e+18,
       "learning_rate": 0.00012,
-      "loss": 1.6426,
+      "loss": 1.6428,
       "step": 6
     },
     {
       "epoch": 0.0006045492329781607,
-      "eval_loss": 1.7828969955444336,
-      "eval_runtime": 1454.0873,
-      "eval_samples_per_second": 2.874,
+      "eval_loss": 1.799889326095581,
+      "eval_runtime": 1454.8745,
+      "eval_samples_per_second": 2.872,
       "eval_steps_per_second": 1.437,
       "step": 6
+    },
+    {
+      "epoch": 0.0007053074384745208,
+      "grad_norm": 3.866104434853413e+18,
+      "learning_rate": 0.00014,
+      "loss": 1.3893,
+      "step": 7
+    },
+    {
+      "epoch": 0.0008060656439708809,
+      "grad_norm": 6.592969687796023e+18,
+      "learning_rate": 0.00016,
+      "loss": 1.4081,
+      "step": 8
+    },
+    {
+      "epoch": 0.000906823849467241,
+      "grad_norm": 1.0697785243865186e+19,
+      "learning_rate": 0.00018,
+      "loss": 1.3395,
+      "step": 9
+    },
+    {
+      "epoch": 0.000906823849467241,
+      "eval_loss": 1.7862416505813599,
+      "eval_runtime": 1455.8794,
+      "eval_samples_per_second": 2.87,
+      "eval_steps_per_second": 1.436,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1235242526441472.0,
+  "total_flos": 1852863789662208.0,
   "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 sha256:58a3eb8d82e5fbac81f07720d857f56891a89c37b161f0eab5a75ef832506307
+oid sha256:b28660bfe89cc0538651f48cd70f7a481a8052384d78f5c68e3271d050811326
 size 6776