Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
     "v_proj",
     "up_proj",
-    "o_proj",
-    "k_proj",
-    "down_proj",
-    "q_proj"
+    "down_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 sha256:2ac5d7560d1940307e5569258bc20f4a1ac776fb689e523fc4e1ab37f247dcea
+oid sha256:64affad19e866a2cd187c6382ace48ac7926b3f6bc4816e68b05c7be23d68ecf
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab88bce6dc19c21963aaca9961b7fb9c89644fdfd2d61bc8f083443d35d67f2d
+oid sha256:d9741f28eddc18a66b799dd7549d8ac8a61dca9abbbb150d1568ac27f7a3dde3
 size 15768084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c3490f66f3193c19d960a03b365425045c9218364a7eba1fbfdba254d9a4965
+oid sha256:2ccc19b6cc79f6792944bb183d23fb2ae518baee1ebed73538b3e3b120bc09b1
 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": 0.001453646836501072,
+  "epoch": 0.00043609405095032164,
   "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": 0.00014536468365010721,
-      "grad_norm": 11.293152809143066,
+      "grad_norm": 12.12260913848877,
       "learning_rate": 2e-05,
       "loss": 5.4024,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.00014536468365010721,
       "eval_loss": 4.953571796417236,
-      "eval_runtime": 1311.2116,
-      "eval_samples_per_second": 2.209,
-      "eval_steps_per_second": 1.105,
+      "eval_runtime": 572.8822,
+      "eval_samples_per_second": 5.057,
+      "eval_steps_per_second": 2.529,
       "step": 1
     },
     {
       "epoch": 0.00029072936730021443,
-      "grad_norm": 10.99425983428955,
+      "grad_norm": 11.454992294311523,
       "learning_rate": 4e-05,
       "loss": 4.8248,
       "step": 2
     },
     {
       "epoch": 0.00043609405095032164,
-      "grad_norm": 11.894266128540039,
+      "grad_norm": 12.662338256835938,
       "learning_rate": 6e-05,
-      "loss": 3.6072,
+      "loss": 3.6741,
       "step": 3
     },
     {
       "epoch": 0.00043609405095032164,
-      "eval_loss": 4.856856822967529,
-      "eval_runtime": 1306.8243,
-      "eval_samples_per_second": 2.217,
-      "eval_steps_per_second": 1.109,
+      "eval_loss": 4.851102828979492,
+      "eval_runtime": 557.8236,
+      "eval_samples_per_second": 5.193,
+      "eval_steps_per_second": 2.598,
       "step": 3
-    },
-    {
-      "epoch": 0.0005814587346004289,
-      "grad_norm": 9.180171012878418,
-      "learning_rate": 8e-05,
-      "loss": 3.6817,
-      "step": 4
-    },
-    {
-      "epoch": 0.000726823418250536,
-      "grad_norm": 12.513172149658203,
-      "learning_rate": 0.0001,
-      "loss": 5.2037,
-      "step": 5
-    },
-    {
-      "epoch": 0.0008721881019006433,
-      "grad_norm": 6.623383045196533,
-      "learning_rate": 0.00012,
-      "loss": 2.7651,
-      "step": 6
-    },
-    {
-      "epoch": 0.0008721881019006433,
-      "eval_loss": 3.960355758666992,
-      "eval_runtime": 1307.1519,
-      "eval_samples_per_second": 2.216,
-      "eval_steps_per_second": 1.109,
-      "step": 6
-    },
-    {
-      "epoch": 0.0010175527855507504,
-      "grad_norm": 6.6997294425964355,
-      "learning_rate": 0.00014,
-      "loss": 2.3049,
-      "step": 7
-    },
-    {
-      "epoch": 0.0011629174692008577,
-      "grad_norm": 16.76756477355957,
-      "learning_rate": 0.00016,
-      "loss": 4.7391,
-      "step": 8
-    },
-    {
-      "epoch": 0.0013082821528509648,
-      "grad_norm": 9.461111068725586,
-      "learning_rate": 0.00018,
-      "loss": 3.1305,
-      "step": 9
-    },
-    {
-      "epoch": 0.0013082821528509648,
-      "eval_loss": 2.8077025413513184,
-      "eval_runtime": 1305.1255,
-      "eval_samples_per_second": 2.22,
-      "eval_steps_per_second": 1.11,
-      "step": 9
-    },
-    {
-      "epoch": 0.001453646836501072,
-      "grad_norm": 7.420252799987793,
-      "learning_rate": 0.0002,
-      "loss": 2.4734,
-      "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": 621231451668480.0,
+  "total_flos": 186369435500544.0,
   "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:b5c4b58c9f31667588c413b2c887c7ce0fa2a81d404d99cd89b7e03043bfe723
+oid sha256:8b5f42d96646badd9458a75e8285b733e108982b902ffab71b1e7c9cfdc31d2d
 size 6776