Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "up_proj",
-    "down_proj",
     "k_proj",
+    "v_proj",
+    "down_proj",
     "q_proj",
-    "o_proj",
-    "gate_proj",
-    "v_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 sha256:74b9d1479074eda5c6e938a92d87337e5c6e8670a0ddee5e7480e2cd29645c4e
+oid sha256:98a4a6013533b370515ea8a5910eaf0e999b88219095bba1ea648d832063869a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0717d0c0d8f0ff65af3e1c0017df830f0fb20a42bf3258a6ce6a824459b716c
+oid sha256:a3d26fcabff894a34104964cece3436174e2c75d96fb76cff0a070cf849a9772
 size 160172858

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0008097165991902834,
-      "grad_norm": 5.536149024963379,
+      "grad_norm": 5.243322849273682,
       "learning_rate": 2e-05,
       "loss": 14.12,
       "step": 1
@@ -18,14 +18,14 @@
     {
       "epoch": 0.0008097165991902834,
       "eval_loss": 16.039548873901367,
-      "eval_runtime": 46.298,
-      "eval_samples_per_second": 5.637,
-      "eval_steps_per_second": 5.637,
+      "eval_runtime": 48.3021,
+      "eval_samples_per_second": 5.403,
+      "eval_steps_per_second": 5.403,
       "step": 1
     },
     {
       "epoch": 0.0016194331983805667,
-      "grad_norm": 5.57291841506958,
+      "grad_norm": 5.311802387237549,
       "learning_rate": 4e-05,
       "loss": 14.9434,
       "step": 2
@@ -34,80 +34,80 @@
       "epoch": 0.0024291497975708503,
       "grad_norm": NaN,
       "learning_rate": 4e-05,
-      "loss": 17.5653,
+      "loss": 17.5635,
       "step": 3
     },
     {
       "epoch": 0.0024291497975708503,
-      "eval_loss": 16.010469436645508,
-      "eval_runtime": 48.2421,
-      "eval_samples_per_second": 5.41,
-      "eval_steps_per_second": 5.41,
+      "eval_loss": 16.010040283203125,
+      "eval_runtime": 47.6629,
+      "eval_samples_per_second": 5.476,
+      "eval_steps_per_second": 5.476,
       "step": 3
     },
     {
       "epoch": 0.0032388663967611335,
-      "grad_norm": 5.217444896697998,
+      "grad_norm": 4.934993267059326,
       "learning_rate": 6e-05,
-      "loss": 15.4635,
+      "loss": 15.4629,
       "step": 4
     },
     {
       "epoch": 0.004048582995951417,
-      "grad_norm": 6.765219688415527,
+      "grad_norm": 6.582982063293457,
       "learning_rate": 8e-05,
-      "loss": 14.5212,
+      "loss": 14.5189,
       "step": 5
     },
     {
       "epoch": 0.004858299595141701,
-      "grad_norm": 7.5979485511779785,
+      "grad_norm": 7.352993011474609,
       "learning_rate": 0.0001,
-      "loss": 14.5423,
+      "loss": 14.5364,
       "step": 6
     },
     {
       "epoch": 0.004858299595141701,
-      "eval_loss": 15.2241849899292,
-      "eval_runtime": 47.8959,
-      "eval_samples_per_second": 5.449,
-      "eval_steps_per_second": 5.449,
+      "eval_loss": 15.222670555114746,
+      "eval_runtime": 47.7487,
+      "eval_samples_per_second": 5.466,
+      "eval_steps_per_second": 5.466,
       "step": 6
     },
     {
       "epoch": 0.005668016194331984,
-      "grad_norm": 7.779355049133301,
+      "grad_norm": 7.531305313110352,
       "learning_rate": 0.00012,
-      "loss": 16.3143,
+      "loss": 16.2939,
       "step": 7
     },
     {
       "epoch": 0.006477732793522267,
-      "grad_norm": 8.685688972473145,
+      "grad_norm": 8.360276222229004,
       "learning_rate": 0.00014,
-      "loss": 13.914,
+      "loss": 13.913,
       "step": 8
     },
     {
       "epoch": 0.0072874493927125505,
-      "grad_norm": 11.748001098632812,
+      "grad_norm": 11.318435668945312,
       "learning_rate": 0.00016,
-      "loss": 13.1216,
+      "loss": 13.087,
       "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,
+      "eval_loss": 12.104350090026855,
+      "eval_runtime": 45.0844,
+      "eval_samples_per_second": 5.789,
+      "eval_steps_per_second": 5.789,
       "step": 9
     },
     {
       "epoch": 0.008097165991902834,
-      "grad_norm": 14.473112106323242,
+      "grad_norm": 14.088312149047852,
       "learning_rate": 0.00018,
-      "loss": 12.325,
+      "loss": 12.2794,
       "step": 10
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7eb56965fd55276c944caeebbd855891392f90553ede8609b47d5de737c680
+oid sha256:a6e1305fc8f281ddb72b2abbc2f99245c4a414545702847872a68fca4d715eef
 size 6776