Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_proj",
+    "v_proj",
     "up_proj",
+    "k_proj",
     "q_proj",
-    "v_proj",
     "down_proj",
-    "k_proj"
+    "gate_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c090e3b2bcb5be844fa9c9fa0f3c5cc30d0f76c2aa402eba3abb57f16bcd95
+oid sha256:acf8868366c44e2804bb2c863a2051642730b14e735c76b02b230db95ca5385f
 size 78504446

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc2e4d38be32b2650fa204fe4333ae66c584b039f5d9fededad7d357b600dd4
+oid sha256:a9ace491c89a1e3fdd160dcbc3f876e1c4b7a0d365f5f7406d84a230daea929e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca38db28fe4855b1b7c21569d1b1c300b37829195b95977aafe1c6b54deda0e
+oid sha256:7874f044555b6fbb2537eb9a3d27f1a7d353d26968ed0d4cdda1c6d2518a3259
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ec0fdbf588254b02fbea8112b6f77d49e400f9bcc319f27614f6ceadaaeef5
+oid sha256:e94d5d90a989adf6c329db6fd7df10a9373f6f6cb86dacc62e0eb362375aecd7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39035050b14bcf13a4235485de7772faf67b2a7b053240f2a16f2d4afe364818
+oid sha256:34c5d626b5e45bd32e3870912b7cb8f61588b7958a7edb381204cdc9d0e70b55
 size 15024

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01299502940125402,
+  "epoch": 0.02599005880250804,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 0.0005198011760501609,
       "eval_loss": NaN,
-      "eval_runtime": 191.1407,
-      "eval_samples_per_second": 67.809,
-      "eval_steps_per_second": 8.481,
+      "eval_runtime": 74.2875,
+      "eval_samples_per_second": 174.471,
+      "eval_steps_per_second": 21.821,
       "step": 1
     },
     {
@@ -194,10 +194,193 @@
     {
       "epoch": 0.01299502940125402,
       "eval_loss": NaN,
-      "eval_runtime": 124.4962,
-      "eval_samples_per_second": 104.108,
-      "eval_steps_per_second": 13.02,
+      "eval_runtime": 131.8392,
+      "eval_samples_per_second": 98.309,
+      "eval_steps_per_second": 12.295,
       "step": 25
+    },
+    {
+      "epoch": 0.01351483057730418,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.014034631753354341,
+      "grad_norm": NaN,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.014554432929404502,
+      "grad_norm": NaN,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.015074234105454663,
+      "grad_norm": NaN,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.015594035281504824,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.016113836457554986,
+      "grad_norm": NaN,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.016633637633605147,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.017153438809655308,
+      "grad_norm": NaN,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.01767323998570547,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.01819304116175563,
+      "grad_norm": NaN,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.01871284233780579,
+      "grad_norm": NaN,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.01923264351385595,
+      "grad_norm": NaN,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.019752444689906112,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.020272245865956273,
+      "grad_norm": NaN,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.020792047042006434,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.021311848218056595,
+      "grad_norm": NaN,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.021831649394106756,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.022351450570156917,
+      "grad_norm": NaN,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.022871251746207077,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.02339105292225724,
+      "grad_norm": NaN,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.023910854098307396,
+      "grad_norm": NaN,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.024430655274357557,
+      "grad_norm": NaN,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.024950456450407717,
+      "grad_norm": NaN,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.025470257626457878,
+      "grad_norm": NaN,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.02599005880250804,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.02599005880250804,
+      "eval_loss": NaN,
+      "eval_runtime": 137.3254,
+      "eval_samples_per_second": 94.382,
+      "eval_steps_per_second": 11.804,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4608673301135360.0,
+  "total_flos": 9197395657097216.0,
   "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 sha256:6aa37725226041eb549cada138c82982136a64a4485aaea3339df266058c2f57
+oid sha256:2a7430ea693893e79130cc61c4e7dde4ca15e2565da26e1a2766595137d83546
 size 6776