Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "k_proj",
-    "q_proj",
-    "o_proj",
+    "gate_proj",
     "v_proj",
+    "q_proj",
     "up_proj",
-    "gate_proj",
-    "down_proj"
+    "o_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:d9d8a5a65032d30dc115d91ffc7c4090505cc09a6655b5634eec4a2a5f7d9857
+oid sha256:ca5e9fbb12778a358e05d3b59fb31e5a416f1c95252818e205a25abef4dca31d
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4259351cc023a3ae4df6f3d4bef17b937f1cc18564051abdd3bf5c8eef06d760
+oid sha256:77960643adc6b01367f94af5d36c37f4d7c825ce5ebe2e999b6e33d7df3574da
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9cabaafa64e3d215b753fb2306a6259b1c2a56fe7834f6169df4636d81ae5bc
+oid sha256:cd51db754346bf2b8266caa2103125228c5d971507a402b98cfcb6868ad9139a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020d33058b4dc1168ec2a4ababa6e1bf1ad35f3ff331b04ad76c13bb25bcaa8b
+oid sha256:796a96a6ded25f9c3f1c3d57bccc151a71727ac5763db79bb96300a5583f7dc0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf6f989b88dd01bc1b5bd0a9ef38e7ee5915de8d466ecc944c5849492c7689b1
+oid sha256:c755c49ceb06517fe07d63399788ab7f6a3688e3cb80d576e4be6dc9336829af
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd0a5f9761cc2ed373e6cf031fce757acc909105f7bcb52e8555b4d23d36c59
+oid sha256:309a5370cc86c5a9db16fe9673c9ed38a9791cfdcd2a57cbb688d99a809acfcf
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.028238616307800918,
+  "epoch": 0.014119308153900459,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0005647723261560184,
       "eval_loss": NaN,
-      "eval_runtime": 392.5762,
-      "eval_samples_per_second": 30.386,
-      "eval_steps_per_second": 3.801,
+      "eval_runtime": 822.1371,
+      "eval_samples_per_second": 14.51,
+      "eval_steps_per_second": 1.815,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 0.014119308153900459,
       "eval_loss": NaN,
-      "eval_runtime": 392.7311,
-      "eval_samples_per_second": 30.374,
-      "eval_steps_per_second": 3.799,
+      "eval_runtime": 821.1961,
+      "eval_samples_per_second": 14.526,
+      "eval_steps_per_second": 1.817,
       "step": 25
-    },
-    {
-      "epoch": 0.014684080480056478,
-      "grad_norm": 0.0,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 0.015248852806212496,
-      "grad_norm": 0.0,
-      "learning_rate": 4.6729843538492847e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.015813625132368513,
-      "grad_norm": 0.0,
-      "learning_rate": 4.347369038899744e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 0.016378397458524534,
-      "grad_norm": 0.0,
-      "learning_rate": 4.0245483899193595e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 0.01694316978468055,
-      "grad_norm": 0.0,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.017507942110836568,
-      "grad_norm": 0.0,
-      "learning_rate": 3.392802673484193e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 0.018072714436992588,
-      "grad_norm": 0.0,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 0.018637486763148605,
-      "grad_norm": 0.0,
-      "learning_rate": 2.7885565489049946e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 0.019202259089304625,
-      "grad_norm": 0.0,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 0.019767031415460642,
-      "grad_norm": 0.0,
-      "learning_rate": 2.2221488349019903e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.02033180374161666,
-      "grad_norm": 0.0,
-      "learning_rate": 1.9561928549563968e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 0.02089657606777268,
-      "grad_norm": 0.0,
-      "learning_rate": 1.703270924499656e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 0.021461348393928697,
-      "grad_norm": 0.0,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 0.022026120720084717,
-      "grad_norm": 0.0,
-      "learning_rate": 1.2408009626051137e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 0.022590893046240734,
-      "grad_norm": 0.0,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.02315566537239675,
-      "grad_norm": 0.0,
-      "learning_rate": 8.426519384872733e-06,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 0.02372043769855277,
-      "grad_norm": 0.0,
-      "learning_rate": 6.698729810778065e-06,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 0.02428521002470879,
-      "grad_norm": 0.0,
-      "learning_rate": 5.156362923365588e-06,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 0.02484998235086481,
-      "grad_norm": 0.0,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 0.025414754677020826,
-      "grad_norm": 0.0,
-      "learning_rate": 2.653493525244721e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.025979527003176843,
-      "grad_norm": 0.0,
-      "learning_rate": 1.70370868554659e-06,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 0.026544299329332863,
-      "grad_norm": 0.0,
-      "learning_rate": 9.607359798384785e-07,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 0.02710907165548888,
-      "grad_norm": 0.0,
-      "learning_rate": 4.277569313094809e-07,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 0.0276738439816449,
-      "grad_norm": 0.0,
-      "learning_rate": 1.0705383806982606e-07,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 0.028238616307800918,
-      "grad_norm": 0.0,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.028238616307800918,
-      "eval_loss": NaN,
-      "eval_runtime": 587.1147,
-      "eval_samples_per_second": 20.318,
-      "eval_steps_per_second": 2.541,
-      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -395,7 +212,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -404,12 +221,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.174479344467968e+17,
+  "total_flos": 3.087239672233984e+17,
   "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 sha256:4c8291eb414f62052e3d00af98f6c1108ce683800f7e2bcf4b57cbe8a1cfe099
+oid sha256:0268ef26ae0c8a14648824e25eb303d02b5d73a042a2b80319515c3c8917a0da
 size 6776