Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a94339e063a24bd4bfb3046399c8f0bc56947ebdc31ae4399c9045cc22ed3e9a
+oid sha256:972b9089b779acefe59011736b1b4591a557f8e476a17cce01cd7dc2e32081da
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86414ecd3c4fe9a5b48a333fe8b1e290367aab276ed07d37b5375962a656b087
+oid sha256:846d06e48e97876d76e7d0fcd47862b747b8cb4803a0ca7f112de19bf0a9096c
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe431361997aa55993e0009e1d25076a1d1a3c60d00600830ab0d4d19be7e26
+oid sha256:70f92bdc49c6502cd67d6b2451332cd8be3a12fde09f18abd604176d37172258
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae60a041773ae8a0b302594a9f6fd1a01473c9c9edfd37b841a6a9063eb4835
+oid sha256:7209cbdb720f3f6d770356d8f8841ac8b032453ae3002668366d1c4453b8e099
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d65676a1c19c127e41a2494bca40b73ff40dcb5377488d403417c3ddac12639f
+oid sha256:d8bb5a46b3cf8c02184c50d54ca551040973d034761525a2b620aac82bbf80d8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e41c0e5262c9f3f81dc0b9bfa0d65360b31a9f34bd650a3a76ded07a2f438c
+oid sha256:86dd8516e1cc3189d5952a9a68f0581f812aade11e1c42aa508d2ff3f0c32e54
 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": 0.9523809523809523,
+  "epoch": 1.9047619047619047,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 14.228,
       "eval_steps_per_second": 1.849,
       "step": 25
+    },
+    {
+      "epoch": 0.9904761904761905,
+      "grad_norm": 1.7644603252410889,
+      "learning_rate": 5e-05,
+      "loss": 1.3783,
+      "step": 26
+    },
+    {
+      "epoch": 1.0285714285714285,
+      "grad_norm": 1.728111982345581,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.1437,
+      "step": 27
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 1.1753063201904297,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.9938,
+      "step": 28
+    },
+    {
+      "epoch": 1.1047619047619048,
+      "grad_norm": 1.6626451015472412,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4311,
+      "step": 29
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.8298120498657227,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8651,
+      "step": 30
+    },
+    {
+      "epoch": 1.180952380952381,
+      "grad_norm": 1.8219621181488037,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4195,
+      "step": 31
+    },
+    {
+      "epoch": 1.2190476190476192,
+      "grad_norm": 2.4925100803375244,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4548,
+      "step": 32
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 1.085057020187378,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1806,
+      "step": 33
+    },
+    {
+      "epoch": 1.2952380952380953,
+      "grad_norm": 1.118369698524475,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3083,
+      "step": 34
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.8153469562530518,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4447,
+      "step": 35
+    },
+    {
+      "epoch": 1.3714285714285714,
+      "grad_norm": 2.3695998191833496,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.3817,
+      "step": 36
+    },
+    {
+      "epoch": 1.4095238095238094,
+      "grad_norm": 1.7949069738388062,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.7265,
+      "step": 37
+    },
+    {
+      "epoch": 1.4476190476190476,
+      "grad_norm": 1.624284267425537,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2413,
+      "step": 38
+    },
+    {
+      "epoch": 1.4857142857142858,
+      "grad_norm": 1.9687860012054443,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0754,
+      "step": 39
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 1.0471829175949097,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5677,
+      "step": 40
+    },
+    {
+      "epoch": 1.561904761904762,
+      "grad_norm": 1.2650785446166992,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5782,
+      "step": 41
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.6667383909225464,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3541,
+      "step": 42
+    },
+    {
+      "epoch": 1.638095238095238,
+      "grad_norm": 1.6385276317596436,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.7588,
+      "step": 43
+    },
+    {
+      "epoch": 1.6761904761904762,
+      "grad_norm": 1.7854325771331787,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3247,
+      "step": 44
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 2.053854465484619,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.07,
+      "step": 45
+    },
+    {
+      "epoch": 1.7523809523809524,
+      "grad_norm": 0.8745402693748474,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0016,
+      "step": 46
+    },
+    {
+      "epoch": 1.7904761904761903,
+      "grad_norm": 1.2501132488250732,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.2583,
+      "step": 47
+    },
+    {
+      "epoch": 1.8285714285714287,
+      "grad_norm": 1.4963077306747437,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4846,
+      "step": 48
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.8609797954559326,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.594,
+      "step": 49
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 1.9615119695663452,
+      "learning_rate": 0.0,
+      "loss": 1.8321,
+      "step": 50
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "eval_loss": NaN,
+      "eval_runtime": 12.43,
+      "eval_samples_per_second": 14.24,
+      "eval_steps_per_second": 1.85,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null