Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d64dec8d2e7c4f847ff276121bd3bca655e4144659ccbee441ff74379905910
+oid sha256:e6f75b5559acf15794e47ac67f5494d5fdfa0f776229ea1ca588ce5dd9670fd7
 size 188794608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74ea20d64d456b81bee35a040864fd9b2405c6bf9884471e15327c2a2dbaf66
+oid sha256:817afd45d6382dc14b388c2ccd587fdb7b6fa6ac54d718825cf466f3d04d7476
 size 377811346

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4d8278f5edb0806b8a960e05ca0ca9aa10114e72cb13204138c89277706ad7
+oid sha256:7f3b395c1d9b05da12894987a2586b62da50ac816d6b5c6b3741f9418ca9dcc6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3dff32055046cb7372e0f341bf8e8458e58ac33be876d1d999faf5318335d6a
+oid sha256:e22193cf137961f31ddb6f70e50dd717e8a56b985153e5930a6dae5940612de1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b48ce5c841d3a69b780abee8be3811abce579434c70f1772f1534dc97e648b1
+oid sha256:3069a6113165c3379dfef1814096c1e9148dcda2c70c7118291887909668c6d4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f9b9162905d52449dcb0ca51e22db8de549b0ae2436d402551f5d931609cf0
+oid sha256:c77936decac686f807b37214b9a17c49c058960a4fd478bb07a06bf2ac5aef3f
 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": 1.273535966873169,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009168423947923351,
+  "best_metric": 1.2655391693115234,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.018336847895846702,
   "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": 18.488,
       "eval_steps_per_second": 2.312,
       "step": 25
+    },
+    {
+      "epoch": 0.009535160905840286,
+      "grad_norm": 0.47894275188446045,
+      "learning_rate": 5e-05,
+      "loss": 1.2658,
+      "step": 26
+    },
+    {
+      "epoch": 0.00990189786375722,
+      "grad_norm": 0.4528166353702545,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1375,
+      "step": 27
+    },
+    {
+      "epoch": 0.010268634821674155,
+      "grad_norm": 0.4974655508995056,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1421,
+      "step": 28
+    },
+    {
+      "epoch": 0.010635371779591089,
+      "grad_norm": 0.5114527940750122,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1505,
+      "step": 29
+    },
+    {
+      "epoch": 0.011002108737508022,
+      "grad_norm": 0.5961247682571411,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.188,
+      "step": 30
+    },
+    {
+      "epoch": 0.011368845695424956,
+      "grad_norm": 0.6712135076522827,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2264,
+      "step": 31
+    },
+    {
+      "epoch": 0.01173558265334189,
+      "grad_norm": 0.551060676574707,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2452,
+      "step": 32
+    },
+    {
+      "epoch": 0.012102319611258825,
+      "grad_norm": 0.5791922211647034,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3737,
+      "step": 33
+    },
+    {
+      "epoch": 0.01246905656917576,
+      "grad_norm": 0.7123498320579529,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4179,
+      "step": 34
+    },
+    {
+      "epoch": 0.012835793527092692,
+      "grad_norm": 0.660800039768219,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4359,
+      "step": 35
+    },
+    {
+      "epoch": 0.013202530485009627,
+      "grad_norm": 0.7791957259178162,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5145,
+      "step": 36
+    },
+    {
+      "epoch": 0.013569267442926561,
+      "grad_norm": 1.006568193435669,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.6791,
+      "step": 37
+    },
+    {
+      "epoch": 0.013936004400843496,
+      "grad_norm": 0.6788609027862549,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2752,
+      "step": 38
+    },
+    {
+      "epoch": 0.014302741358760428,
+      "grad_norm": 0.4459913969039917,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1875,
+      "step": 39
+    },
+    {
+      "epoch": 0.014669478316677363,
+      "grad_norm": 0.45657065510749817,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1233,
+      "step": 40
+    },
+    {
+      "epoch": 0.015036215274594297,
+      "grad_norm": 0.46388086676597595,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.135,
+      "step": 41
+    },
+    {
+      "epoch": 0.015402952232511232,
+      "grad_norm": 0.5328096747398376,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1675,
+      "step": 42
+    },
+    {
+      "epoch": 0.015769689190428166,
+      "grad_norm": 0.5747068524360657,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1903,
+      "step": 43
+    },
+    {
+      "epoch": 0.0161364261483451,
+      "grad_norm": 0.5286138653755188,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2724,
+      "step": 44
+    },
+    {
+      "epoch": 0.016503163106262035,
+      "grad_norm": 0.6160573959350586,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.3105,
+      "step": 45
+    },
+    {
+      "epoch": 0.016869900064178968,
+      "grad_norm": 0.6273021697998047,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.3675,
+      "step": 46
+    },
+    {
+      "epoch": 0.0172366370220959,
+      "grad_norm": 0.6863045692443848,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3798,
+      "step": 47
+    },
+    {
+      "epoch": 0.017603373980012837,
+      "grad_norm": 0.6844849586486816,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4587,
+      "step": 48
+    },
+    {
+      "epoch": 0.01797011093792977,
+      "grad_norm": 0.8137116432189941,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.6066,
+      "step": 49
+    },
+    {
+      "epoch": 0.018336847895846702,
+      "grad_norm": 1.1856001615524292,
+      "learning_rate": 0.0,
+      "loss": 1.6489,
+      "step": 50
+    },
+    {
+      "epoch": 0.018336847895846702,
+      "eval_loss": 1.2655391693115234,
+      "eval_runtime": 992.6039,
+      "eval_samples_per_second": 18.507,
+      "eval_steps_per_second": 2.314,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1534460285616128e+17,
+  "total_flos": 2.3062295476803994e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null