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",
-    "v_proj",
-    "down_proj",
     "up_proj",
+    "down_proj",
+    "o_proj",
     "k_proj",
-    "o_proj"
+    "q_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 sha256:7065a8a7527601216ed9ba12aa9f758e0b31244fbf23be477758d02a912fc779
+oid sha256:347a0073c1aeed6922417e11b41217b5ca15082154d56f935f9777130fc8e554
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a368c6333529ed0cd850ea1b08ba7034b1dcc0f238b15aa7a4efdde292bef7b4
+oid sha256:35620aa52d5bb497ce8fb0fc1c246924976d482c41ce2a5120817656eb512e28
 size 39398

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccb4f4fa4dcfe5bc230fa2b68534e99c4447a88f31286dfb471650fb9f2ed51
+size 14512

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79f78716b356923e3a954e645268f3247781e92319c3c3c699c29edf2344335
+size 14512

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

@@ -1,114 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005608524957936063,
+  "epoch": 0.0033651149747616375,
   "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": 0.0005608524957936063,
-      "grad_norm": 0.01492331176996231,
+      "epoch": 0.0011217049915872126,
+      "grad_norm": 0.010464487597346306,
       "learning_rate": 2e-05,
-      "loss": 11.9315,
+      "loss": 11.9305,
       "step": 1
     },
     {
-      "epoch": 0.0005608524957936063,
-      "eval_loss": 11.931306838989258,
-      "eval_runtime": 3.0288,
-      "eval_samples_per_second": 247.95,
-      "eval_steps_per_second": 124.14,
+      "epoch": 0.0011217049915872126,
+      "eval_loss": 11.931302070617676,
+      "eval_runtime": 1.6109,
+      "eval_samples_per_second": 466.206,
+      "eval_steps_per_second": 116.707,
       "step": 1
     },
     {
-      "epoch": 0.0011217049915872126,
-      "grad_norm": 0.008967285975813866,
+      "epoch": 0.002243409983174425,
+      "grad_norm": 0.012750067748129368,
       "learning_rate": 4e-05,
-      "loss": 11.9304,
+      "loss": 11.9324,
       "step": 2
     },
     {
-      "epoch": 0.0016825574873808188,
-      "grad_norm": 0.016075991094112396,
+      "epoch": 0.0033651149747616375,
+      "grad_norm": 0.01111360639333725,
       "learning_rate": 6e-05,
-      "loss": 11.9319,
+      "loss": 11.9253,
       "step": 3
     },
-    {
-      "epoch": 0.0016825574873808188,
-      "eval_loss": 11.931303977966309,
-      "eval_runtime": 3.0838,
-      "eval_samples_per_second": 243.535,
-      "eval_steps_per_second": 121.929,
-      "step": 3
-    },
-    {
-      "epoch": 0.002243409983174425,
-      "grad_norm": 0.016678154468536377,
-      "learning_rate": 8e-05,
-      "loss": 11.9328,
-      "step": 4
-    },
-    {
-      "epoch": 0.0028042624789680315,
-      "grad_norm": 0.018861737102270126,
-      "learning_rate": 0.0001,
-      "loss": 11.9248,
-      "step": 5
-    },
     {
       "epoch": 0.0033651149747616375,
-      "grad_norm": 0.009495808742940426,
-      "learning_rate": 0.00012,
-      "loss": 11.926,
-      "step": 6
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "eval_loss": 11.93128776550293,
-      "eval_runtime": 3.1316,
-      "eval_samples_per_second": 239.81,
-      "eval_steps_per_second": 120.065,
-      "step": 6
-    },
-    {
-      "epoch": 0.003925967470555244,
-      "grad_norm": 0.012134317308664322,
-      "learning_rate": 0.00014,
-      "loss": 11.9324,
-      "step": 7
-    },
-    {
-      "epoch": 0.00448681996634885,
-      "grad_norm": 0.007003261707723141,
-      "learning_rate": 0.00016,
-      "loss": 11.9349,
-      "step": 8
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "grad_norm": 0.013818953186273575,
-      "learning_rate": 0.00018,
-      "loss": 11.9287,
-      "step": 9
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "eval_loss": 11.93126392364502,
-      "eval_runtime": 3.0619,
-      "eval_samples_per_second": 245.272,
-      "eval_steps_per_second": 122.799,
-      "step": 9
-    },
-    {
-      "epoch": 0.005608524957936063,
-      "grad_norm": 0.008010505698621273,
-      "learning_rate": 0.0002,
-      "loss": 11.9335,
-      "step": 10
+      "eval_loss": 11.931297302246094,
+      "eval_runtime": 1.6294,
+      "eval_samples_per_second": 460.916,
+      "eval_steps_per_second": 115.382,
+      "step": 3
     }
   ],
   "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": 1211154432.0,
+  "total_flos": 738508800.0,
   "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 sha256:9b3d69d552d88d6d7e3776d69f19b418168ac3147b1c0c877c9d865e8c645e99
+oid sha256:2daceafefb5eef61850777c2a560f7c86e0e58a4e9e3449351c10cc0e181f086
 size 6776