Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "up_proj",
-    "v_proj",
     "gate_proj",
+    "k_proj",
+    "v_proj",
     "q_proj",
-    "down_proj",
-    "k_proj"
+    "up_proj",
+    "down_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 sha256:3c6c3b49517918f71b5a8df86ce64802524c101812f6310fcee02fef5d317af6
+oid sha256:ecacf0120c3313aa6d110d54cdb0747ee47b71b2cd60beeadeed0c4feac79962
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6fd6c7b9a2377bba4e59fb04dbc6e3d8d1162b96d84676ab6da2ca765504105
-size 14960
+oid sha256:3b280ff098b61e98834efe14302b9ca0b65bd223dd58755a430ec4288255caec
+size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39bbeaeb98e95ec8854afee5d4fa6bbe14ff3d204e269b001bd1cf561904a32
+oid sha256:51582a8d3f1dafd55ece10db7b3d2fae7e2ffbf3b0b5933bbc13c68d6149080d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673c24c0b2a7bcf15fd580f818cf21b6e200925e9ac5ba6f09b5d6f40ba421a1
+oid sha256:b3d98f59769b5af3b8f0691acb88919899b687d62b2cc547e53b9f26fc13ad6e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0665238a16735e393f2dd5fe2d64d1515fe31f4483ac4d424cd8d62713f52c
+oid sha256:2da2634dd00f183ae9c1b73bbd78fe76858020a924d44af6f45d61a6e8544499
 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": 0.28870443883074703,
+  "epoch": 0.14435221941537352,
   "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": 0.00577408877661494,
       "eval_loss": NaN,
-      "eval_runtime": 32.8937,
-      "eval_samples_per_second": 35.478,
-      "eval_steps_per_second": 4.439,
+      "eval_runtime": 32.871,
+      "eval_samples_per_second": 35.502,
+      "eval_steps_per_second": 4.442,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 0.14435221941537352,
       "eval_loss": NaN,
-      "eval_runtime": 32.9674,
-      "eval_samples_per_second": 35.399,
-      "eval_steps_per_second": 4.429,
+      "eval_runtime": 32.81,
+      "eval_samples_per_second": 35.568,
+      "eval_steps_per_second": 4.45,
       "step": 25
-    },
-    {
-      "epoch": 0.15012630819198844,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 0.1559003969686034,
-      "grad_norm": NaN,
-      "learning_rate": 4.6729843538492847e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.16167448574521834,
-      "grad_norm": NaN,
-      "learning_rate": 4.347369038899744e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 0.16744857452183326,
-      "grad_norm": NaN,
-      "learning_rate": 4.0245483899193595e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 0.1732226632984482,
-      "grad_norm": NaN,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.17899675207506316,
-      "grad_norm": NaN,
-      "learning_rate": 3.392802673484193e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 0.18477084085167808,
-      "grad_norm": NaN,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 0.19054492962829303,
-      "grad_norm": NaN,
-      "learning_rate": 2.7885565489049946e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 0.19631901840490798,
-      "grad_norm": NaN,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 0.20209310718152293,
-      "grad_norm": NaN,
-      "learning_rate": 2.2221488349019903e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.20786719595813785,
-      "grad_norm": NaN,
-      "learning_rate": 1.9561928549563968e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 0.2136412847347528,
-      "grad_norm": NaN,
-      "learning_rate": 1.703270924499656e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 0.21941537351136775,
-      "grad_norm": NaN,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 0.22518946228798267,
-      "grad_norm": NaN,
-      "learning_rate": 1.2408009626051137e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 0.23096355106459762,
-      "grad_norm": NaN,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.23673763984121257,
-      "grad_norm": NaN,
-      "learning_rate": 8.426519384872733e-06,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 0.2425117286178275,
-      "grad_norm": NaN,
-      "learning_rate": 6.698729810778065e-06,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 0.24828581739444244,
-      "grad_norm": NaN,
-      "learning_rate": 5.156362923365588e-06,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 0.2540599061710574,
-      "grad_norm": NaN,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 0.25983399494767234,
-      "grad_norm": NaN,
-      "learning_rate": 2.653493525244721e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.26560808372428724,
-      "grad_norm": NaN,
-      "learning_rate": 1.70370868554659e-06,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 0.2713821725009022,
-      "grad_norm": NaN,
-      "learning_rate": 9.607359798384785e-07,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 0.27715626127751714,
-      "grad_norm": NaN,
-      "learning_rate": 4.277569313094809e-07,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 0.2829303500541321,
-      "grad_norm": NaN,
-      "learning_rate": 1.0705383806982606e-07,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 0.28870443883074703,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.28870443883074703,
-      "eval_loss": NaN,
-      "eval_runtime": 32.9078,
-      "eval_samples_per_second": 35.463,
-      "eval_steps_per_second": 4.437,
-      "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": 5.971813667564421e+17,
+  "total_flos": 2.9859068337822106e+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 sha256:065dd46411693725591d2f0663c9166384e353689ef074a92dea5efe121d8812
+oid sha256:d72672300f9cf14e7960187500f88d47ee3190e2e02e2f783be1cfb3ab494e3d
 size 6776