Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
     "k_proj",
     "gate_proj",
-    "q_proj",
-    "o_proj",
     "down_proj",
-    "v_proj",
-    "up_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:f88b81b8749424823c69a67ced86b421018979622acbf2ba8078ca71b7a87b88
+oid sha256:e68b56c10ec86150d41c0273aee7902ccbf0179a81e0a827883202a82ffc400a
 size 859909312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f3e52a3921808d5243bd4d25361e27378db547355114798e0235ae3400ef7c6
+oid sha256:2a20e42f228d66e5e1ef7c3e904241d4700bc42d3030daabf20110d4831164cc
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:909549b7ea59196c105f2701a982144e3abd264ab05f953741a0326dbe35d165
+oid sha256:32d546015f0a7f279f2378cd6f584a1c90fc583677e8f4f17cd03657d8be9de6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3a978250de09192e12ec024037c9a18575857a4a7cee048eceae8c58f0114e
+oid sha256:9b63ac94520b82337d9daf989e3d60b437c741ae29e1e7c049b870aae080e7cf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d142b8878a2b7b5fddb25ee475538d2c5f3f7a12b6c850c8dd6ee522056921
+oid sha256:7885afd6435f8f95677973ce89c6fcff7025b412fb3aa33950e0be6f7140c566
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9dc711c6452ab4be3793721a44f0a1d25ca26b4b5194aa04f189a0ff79d6c81
+oid sha256:23316f53377a59f805f3dbdf28c9cb9dc9c8710b1d6bef6d0b82ecfbf8b648cd
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
+oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.62402496099844,
+  "epoch": 0.31201248049922,
   "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": 0.0124804992199688,
       "eval_loss": NaN,
-      "eval_runtime": 3.1747,
-      "eval_samples_per_second": 15.749,
-      "eval_steps_per_second": 4.095,
+      "eval_runtime": 3.1778,
+      "eval_samples_per_second": 15.734,
+      "eval_steps_per_second": 4.091,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 0.31201248049922,
       "eval_loss": NaN,
-      "eval_runtime": 3.1868,
-      "eval_samples_per_second": 15.69,
-      "eval_steps_per_second": 4.079,
+      "eval_runtime": 3.1834,
+      "eval_samples_per_second": 15.707,
+      "eval_steps_per_second": 4.084,
       "step": 25
-    },
-    {
-      "epoch": 0.3244929797191888,
-      "grad_norm": NaN,
-      "learning_rate": 8.681980515339464e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 0.3369734789391576,
-      "grad_norm": NaN,
-      "learning_rate": 8.571489144483944e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.3494539781591264,
-      "grad_norm": NaN,
-      "learning_rate": 8.457416554680877e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 0.3619344773790952,
-      "grad_norm": NaN,
-      "learning_rate": 8.339895749467238e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 0.374414976599064,
-      "grad_norm": NaN,
-      "learning_rate": 8.219063752844926e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.3868954758190328,
-      "grad_norm": NaN,
-      "learning_rate": 8.095061449516903e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 0.3993759750390016,
-      "grad_norm": NaN,
-      "learning_rate": 7.968033420621935e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 0.4118564742589704,
-      "grad_norm": NaN,
-      "learning_rate": 7.838127775159452e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 0.4243369734789392,
-      "grad_norm": NaN,
-      "learning_rate": 7.705495977301078e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 0.43681747269890797,
-      "grad_norm": NaN,
-      "learning_rate": 7.570292669790186e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.44929797191887677,
-      "grad_norm": NaN,
-      "learning_rate": 7.43267549363537e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 0.46177847113884557,
-      "grad_norm": NaN,
-      "learning_rate": 7.292804904308087e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 0.47425897035881437,
-      "grad_norm": NaN,
-      "learning_rate": 7.150843984658754e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 0.48673946957878317,
-      "grad_norm": NaN,
-      "learning_rate": 7.006958254769438e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 0.49921996879875197,
-      "grad_norm": NaN,
-      "learning_rate": 6.861315478964841e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.5117004680187207,
-      "grad_norm": NaN,
-      "learning_rate": 6.714085470206609e-05,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 0.5241809672386896,
-      "grad_norm": NaN,
-      "learning_rate": 6.56543989209901e-05,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 0.5366614664586583,
-      "grad_norm": NaN,
-      "learning_rate": 6.415552058736854e-05,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 0.5491419656786272,
-      "grad_norm": NaN,
-      "learning_rate": 6.264596732629e-05,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 0.5616224648985959,
-      "grad_norm": NaN,
-      "learning_rate": 6.112749920933111e-05,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.5741029641185648,
-      "grad_norm": NaN,
-      "learning_rate": 5.960188670239154e-05,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 0.5865834633385335,
-      "grad_norm": NaN,
-      "learning_rate": 5.80709086014102e-05,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 0.5990639625585024,
-      "grad_norm": NaN,
-      "learning_rate": 5.653634995836856e-05,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 0.6115444617784711,
-      "grad_norm": NaN,
-      "learning_rate": 5.500000000000001e-05,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 0.62402496099844,
-      "grad_norm": NaN,
-      "learning_rate": 5.346365004163145e-05,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.62402496099844,
-      "eval_loss": NaN,
-      "eval_runtime": 3.1961,
-      "eval_samples_per_second": 15.644,
-      "eval_steps_per_second": 4.067,
-      "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": 5.658024559509504e+17,
+  "total_flos": 2.829012279754752e+17,
   "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 sha256:8f0dd78bcb7bdc141ef5a6182d39d2e5a9c3e45a72eeef304fe7f74994340043
+oid sha256:b26aef1ddd64839b4afc9406b588180ab9d1cb1040935f92c2fa63f73ed885fa
 size 6840