Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
-    "up_proj",
+    "v_proj",
     "k_proj",
+    "gate_proj",
     "o_proj",
-    "v_proj",
-    "down_proj"
+    "down_proj",
+    "up_proj",
+    "q_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 sha256:60ff3a0a309f0ec4f8324cb3d79d2d2138937744820d1e192adbd2bea2a95a2e
+oid sha256:b78d966700171e907bd160b341c5bf7acbd51fc358a4f49eee24c16e2eef0885
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2adbcd6089dab4c84c1cb38baac8474d7cead3e2d1758fc5028637720750ced5
+oid sha256:3c3b73b1d4e694c6ca8816db5955229be047f3039ddf8fee76e61c3a662fd144
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3efe221c4a0adf497082884c488f9d91c42d1d873e72d47409fbf104eb83048
+oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0023949227637408694,
+  "epoch": 0.0007184768291222608,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00023949227637408692,
-      "grad_norm": 4.3014726638793945,
+      "grad_norm": 5.556643962860107,
       "learning_rate": 2e-05,
       "loss": 2.4864,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.00023949227637408692,
       "eval_loss": 3.196671962738037,
-      "eval_runtime": 56.3772,
-      "eval_samples_per_second": 15.609,
-      "eval_steps_per_second": 15.609,
+      "eval_runtime": 164.0333,
+      "eval_samples_per_second": 5.365,
+      "eval_steps_per_second": 5.365,
       "step": 1
     },
     {
       "epoch": 0.00047898455274817384,
-      "grad_norm": 3.2757163047790527,
+      "grad_norm": 4.200049877166748,
       "learning_rate": 4e-05,
       "loss": 3.3358,
       "step": 2
     },
     {
       "epoch": 0.0007184768291222608,
-      "grad_norm": 2.781923294067383,
+      "grad_norm": 3.4988012313842773,
       "learning_rate": 6e-05,
-      "loss": 3.3958,
+      "loss": 3.3931,
       "step": 3
     },
     {
       "epoch": 0.0007184768291222608,
-      "eval_loss": 3.0978620052337646,
-      "eval_runtime": 57.0247,
-      "eval_samples_per_second": 15.432,
-      "eval_steps_per_second": 15.432,
+      "eval_loss": 3.08847713470459,
+      "eval_runtime": 164.5024,
+      "eval_samples_per_second": 5.349,
+      "eval_steps_per_second": 5.349,
       "step": 3
-    },
-    {
-      "epoch": 0.0009579691054963477,
-      "grad_norm": 2.6946146488189697,
-      "learning_rate": 8e-05,
-      "loss": 2.7689,
-      "step": 4
-    },
-    {
-      "epoch": 0.0011974613818704347,
-      "grad_norm": 3.1957530975341797,
-      "learning_rate": 0.0001,
-      "loss": 2.8025,
-      "step": 5
-    },
-    {
-      "epoch": 0.0014369536582445215,
-      "grad_norm": 2.734419584274292,
-      "learning_rate": 0.00012,
-      "loss": 1.8246,
-      "step": 6
-    },
-    {
-      "epoch": 0.0014369536582445215,
-      "eval_loss": 2.6213483810424805,
-      "eval_runtime": 57.0839,
-      "eval_samples_per_second": 15.416,
-      "eval_steps_per_second": 15.416,
-      "step": 6
-    },
-    {
-      "epoch": 0.0016764459346186086,
-      "grad_norm": 2.242945909500122,
-      "learning_rate": 0.00014,
-      "loss": 2.6675,
-      "step": 7
-    },
-    {
-      "epoch": 0.0019159382109926954,
-      "grad_norm": 1.637675404548645,
-      "learning_rate": 0.00016,
-      "loss": 1.9593,
-      "step": 8
-    },
-    {
-      "epoch": 0.0021554304873667826,
-      "grad_norm": 1.1237943172454834,
-      "learning_rate": 0.00018,
-      "loss": 1.7248,
-      "step": 9
-    },
-    {
-      "epoch": 0.0021554304873667826,
-      "eval_loss": 2.173261880874634,
-      "eval_runtime": 57.6011,
-      "eval_samples_per_second": 15.277,
-      "eval_steps_per_second": 15.277,
-      "step": 9
-    },
-    {
-      "epoch": 0.0023949227637408694,
-      "grad_norm": 1.9361770153045654,
-      "learning_rate": 0.0002,
-      "loss": 1.5842,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1643164226027520.0,
+  "total_flos": 492949267808256.0,
   "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 sha256:682e4fd1b477dea9fb62e8a3f8adca3f3cce76d860e7468755e2a5e9c94008bf
+oid sha256:c8e3eaba4fc887116ba05575a8a64bfbe0629dae4f12cb37cac79d895993962b
 size 6776