Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "down_proj",
     "o_proj",
     "up_proj",
+    "v_proj",
     "q_proj",
-    "k_proj",
-    "down_proj",
-    "gate_proj",
-    "v_proj"
+    "k_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 sha256:11e8c2cac5e40d8addc25d7a7b3345cfa2ebc4c29cd390d1c7063b114bf10188
+oid sha256:69402f6420b277547b6b4b2931d67cfebd33780cba203757e292a29b20c62730
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee971a1dc5c291f29f0ce193013311050ac2f600ec3046681cb02f8df07881f6
+oid sha256:d6db1852b4d877d84c6e2ed681603168bf1d357047027c3c5e4aa990988d00e7
 size 63910

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
+oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004253056884635832,
+  "epoch": 0.0002126528442317916,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 7.08842814105972e-05,
-      "grad_norm": 0.05384966731071472,
+      "grad_norm": 0.05572463199496269,
       "learning_rate": 2e-05,
       "loss": 10.3888,
       "step": 1
@@ -18,61 +18,32 @@
     {
       "epoch": 7.08842814105972e-05,
       "eval_loss": 10.386297225952148,
-      "eval_runtime": 14.7601,
-      "eval_samples_per_second": 201.219,
-      "eval_steps_per_second": 201.219,
+      "eval_runtime": 23.9211,
+      "eval_samples_per_second": 124.158,
+      "eval_steps_per_second": 124.158,
       "step": 1
     },
     {
       "epoch": 0.0001417685628211944,
-      "grad_norm": 0.07059969753026962,
+      "grad_norm": 0.07294921576976776,
       "learning_rate": 4e-05,
       "loss": 10.3973,
       "step": 2
     },
     {
       "epoch": 0.0002126528442317916,
-      "grad_norm": 0.08588440716266632,
+      "grad_norm": 0.09582077711820602,
       "learning_rate": 6e-05,
       "loss": 10.3902,
       "step": 3
     },
     {
       "epoch": 0.0002126528442317916,
-      "eval_loss": 10.386216163635254,
-      "eval_runtime": 14.8509,
-      "eval_samples_per_second": 199.988,
-      "eval_steps_per_second": 199.988,
+      "eval_loss": 10.38620662689209,
+      "eval_runtime": 25.6376,
+      "eval_samples_per_second": 115.845,
+      "eval_steps_per_second": 115.845,
       "step": 3
-    },
-    {
-      "epoch": 0.0002835371256423888,
-      "grad_norm": 0.06526752561330795,
-      "learning_rate": 8e-05,
-      "loss": 10.3829,
-      "step": 4
-    },
-    {
-      "epoch": 0.000354421407052986,
-      "grad_norm": 0.07151740044355392,
-      "learning_rate": 0.0001,
-      "loss": 10.3837,
-      "step": 5
-    },
-    {
-      "epoch": 0.0004253056884635832,
-      "grad_norm": 0.08352982252836227,
-      "learning_rate": 0.00012,
-      "loss": 10.3935,
-      "step": 6
-    },
-    {
-      "epoch": 0.0004253056884635832,
-      "eval_loss": 10.385886192321777,
-      "eval_runtime": 15.1198,
-      "eval_samples_per_second": 196.431,
-      "eval_steps_per_second": 196.431,
-      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -92,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 80818176000.0,
+  "total_flos": 38792724480.0,
   "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 sha256:78736215572f27c84ed8e421061f9fcbb9ad8dc5b3742a396ba6b43287746e1d
+oid sha256:b6b787cf00a0bf21dcecfa64e4ed3fd7c145cc55e1992c0ed725bf3c55bad515
 size 6776