Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "gate_proj",
-    "up_proj",
+    "v_proj",
     "down_proj",
+    "up_proj",
     "k_proj",
-    "q_proj",
-    "v_proj"
+    "gate_proj",
+    "q_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 sha256:55d9b1f7342b3650d2017aff7fe84f2577a2ffe70cd37c648a32a7129bf17405
+oid sha256:6fd1768f059e3228ad6876e3eeff39181f582f5c6b2c94486a72f4604b51e1da
 size 912734242

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40bf22e05df913a65002b0cc31a0f7b805ed52a1f04e1868f1d9c6471aa807f5
+oid sha256:b3828d741e639c538791bbae428b031ba32639942f15575ab3462d6f8160c2e5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0980c1d7cf5a211aaa94c8e1395637f341126bc80a863048db8d3a3a2ef12788
+oid sha256:f6761d8a6b9de011b6948d12791f7a748ab1e8f55500c554c48a352990390ad5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff450a7301f9b09a9211cd69d2dbe58ac477077d0cf2a6be54667deed4a91393
+oid sha256:9aad6197ed62e19c7ed0857795140428626902d01c45a8216dbd0755e4412693
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a6dc071785dc671c54bb5df420e46c4638420b581d1485bd1004e9021083529
+oid sha256:434234dc2b26d63fa68df1a1aa78bbf1cf17af177cce7cf3119b772e447e6dd7
 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": 0.866738894907909,
+  "epoch": 0.4333694474539545,
   "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": 0.01733477789815818,
       "eval_loss": NaN,
-      "eval_runtime": 15.364,
-      "eval_samples_per_second": 25.319,
-      "eval_steps_per_second": 3.189,
+      "eval_runtime": 32.0899,
+      "eval_samples_per_second": 12.122,
+      "eval_steps_per_second": 1.527,
       "step": 1
     },
     {
@@ -194,193 +194,10 @@
     {
       "epoch": 0.4333694474539545,
       "eval_loss": NaN,
-      "eval_runtime": 15.3009,
-      "eval_samples_per_second": 25.423,
-      "eval_steps_per_second": 3.202,
+      "eval_runtime": 31.9589,
+      "eval_samples_per_second": 12.172,
+      "eval_steps_per_second": 1.533,
       "step": 25
-    },
-    {
-      "epoch": 0.4507042253521127,
-      "grad_norm": NaN,
-      "learning_rate": 5e-05,
-      "loss": 0.0,
-      "step": 26
-    },
-    {
-      "epoch": 0.46803900325027087,
-      "grad_norm": NaN,
-      "learning_rate": 4.6729843538492847e-05,
-      "loss": 0.0,
-      "step": 27
-    },
-    {
-      "epoch": 0.48537378114842905,
-      "grad_norm": NaN,
-      "learning_rate": 4.347369038899744e-05,
-      "loss": 0.0,
-      "step": 28
-    },
-    {
-      "epoch": 0.5027085590465872,
-      "grad_norm": NaN,
-      "learning_rate": 4.0245483899193595e-05,
-      "loss": 0.0,
-      "step": 29
-    },
-    {
-      "epoch": 0.5200433369447454,
-      "grad_norm": NaN,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.0,
-      "step": 30
-    },
-    {
-      "epoch": 0.5373781148429035,
-      "grad_norm": NaN,
-      "learning_rate": 3.392802673484193e-05,
-      "loss": 0.0,
-      "step": 31
-    },
-    {
-      "epoch": 0.5547128927410617,
-      "grad_norm": NaN,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0,
-      "step": 32
-    },
-    {
-      "epoch": 0.5720476706392199,
-      "grad_norm": NaN,
-      "learning_rate": 2.7885565489049946e-05,
-      "loss": 0.0,
-      "step": 33
-    },
-    {
-      "epoch": 0.5893824485373781,
-      "grad_norm": NaN,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 0.0,
-      "step": 34
-    },
-    {
-      "epoch": 0.6067172264355363,
-      "grad_norm": NaN,
-      "learning_rate": 2.2221488349019903e-05,
-      "loss": 0.0,
-      "step": 35
-    },
-    {
-      "epoch": 0.6240520043336945,
-      "grad_norm": NaN,
-      "learning_rate": 1.9561928549563968e-05,
-      "loss": 0.0,
-      "step": 36
-    },
-    {
-      "epoch": 0.6413867822318526,
-      "grad_norm": NaN,
-      "learning_rate": 1.703270924499656e-05,
-      "loss": 0.0,
-      "step": 37
-    },
-    {
-      "epoch": 0.6587215601300108,
-      "grad_norm": NaN,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0,
-      "step": 38
-    },
-    {
-      "epoch": 0.676056338028169,
-      "grad_norm": NaN,
-      "learning_rate": 1.2408009626051137e-05,
-      "loss": 0.0,
-      "step": 39
-    },
-    {
-      "epoch": 0.6933911159263272,
-      "grad_norm": NaN,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.0,
-      "step": 40
-    },
-    {
-      "epoch": 0.7107258938244854,
-      "grad_norm": NaN,
-      "learning_rate": 8.426519384872733e-06,
-      "loss": 0.0,
-      "step": 41
-    },
-    {
-      "epoch": 0.7280606717226435,
-      "grad_norm": NaN,
-      "learning_rate": 6.698729810778065e-06,
-      "loss": 0.0,
-      "step": 42
-    },
-    {
-      "epoch": 0.7453954496208017,
-      "grad_norm": NaN,
-      "learning_rate": 5.156362923365588e-06,
-      "loss": 0.0,
-      "step": 43
-    },
-    {
-      "epoch": 0.7627302275189599,
-      "grad_norm": NaN,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.0,
-      "step": 44
-    },
-    {
-      "epoch": 0.7800650054171181,
-      "grad_norm": NaN,
-      "learning_rate": 2.653493525244721e-06,
-      "loss": 0.0,
-      "step": 45
-    },
-    {
-      "epoch": 0.7973997833152763,
-      "grad_norm": NaN,
-      "learning_rate": 1.70370868554659e-06,
-      "loss": 0.0,
-      "step": 46
-    },
-    {
-      "epoch": 0.8147345612134345,
-      "grad_norm": NaN,
-      "learning_rate": 9.607359798384785e-07,
-      "loss": 0.0,
-      "step": 47
-    },
-    {
-      "epoch": 0.8320693391115926,
-      "grad_norm": NaN,
-      "learning_rate": 4.277569313094809e-07,
-      "loss": 0.0,
-      "step": 48
-    },
-    {
-      "epoch": 0.8494041170097508,
-      "grad_norm": NaN,
-      "learning_rate": 1.0705383806982606e-07,
-      "loss": 0.0,
-      "step": 49
-    },
-    {
-      "epoch": 0.866738894907909,
-      "grad_norm": NaN,
-      "learning_rate": 0.0,
-      "loss": 0.0,
-      "step": 50
-    },
-    {
-      "epoch": 0.866738894907909,
-      "eval_loss": NaN,
-      "eval_runtime": 15.301,
-      "eval_samples_per_second": 25.423,
-      "eval_steps_per_second": 3.202,
-      "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": 9.193961612640256e+17,
+  "total_flos": 4.596980806320128e+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 sha256:3ad3d0fc1484cb1788a781453748bbf25613f4bc71b8d8bccc46ef1ccff2bf1c
+oid sha256:c8fa9cce12db97aa6dedced98f9ee2a3bc2bd263f137af9bfb9a7ad687b0f737
 size 6776