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:dfa5f54e6fe556141a997468a7989711e5d33e5b20ca1e987be9c9f9b61c4483
+oid sha256:b99238d3b1d852fc1e48b829e65d6bd716805c576c47430cb9f0bceaa7d74832
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f0123b918d7201b8b82fdbb40b7629fb5375c63df7676e07afd810479fe9fa
+oid sha256:d845630006496e37ce87e057632f96451ae55b66f96c1bb76da6fb3d456c9124
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5f3172311d15d0e1cb4da025824df8bf42ed4443301dad5f01cb66c912beac
+oid sha256:721cd46fb6411a716ecb56ce7ac50a1dd69ad45cb063cf192352e7d462e55e76
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0f36980c13d686affaf56b31bd8e52ec9e9ab591fb1a81e7f9dfea2b8d0ae3
+oid sha256:c9cfcff8280b0c6be01b1d68f5a970d80f0aaf1a5066abe8052a815994e775cd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e561ae497bd1255bc962b1325340da28706397fac8314e600e870032195bea65
+oid sha256:7054da42c15b3f62f673df0be173b89f2094f79abf97f648ef60c8cdd7b30096
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47e6fdd9e5b12fc04bf339bd90d43b071640dd698636ed4e968e180844a8bf3
+oid sha256:fed30b3b09296f14865909296b58a88b1422617ddaa48761017a3d5b8a149bdc
 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": 1.9103429317474365,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09732360097323602,
+  "best_metric": 1.885321855545044,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.19464720194647203,
   "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": 47.091,
       "eval_steps_per_second": 5.903,
       "step": 25
+    },
+    {
+      "epoch": 0.10121654501216545,
+      "grad_norm": 0.8730716109275818,
+      "learning_rate": 5e-05,
+      "loss": 2.1233,
+      "step": 26
+    },
+    {
+      "epoch": 0.10510948905109489,
+      "grad_norm": 0.9246626496315002,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.2101,
+      "step": 27
+    },
+    {
+      "epoch": 0.10900243309002433,
+      "grad_norm": 0.8004997372627258,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.0681,
+      "step": 28
+    },
+    {
+      "epoch": 0.11289537712895377,
+      "grad_norm": 0.7172746658325195,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.0711,
+      "step": 29
+    },
+    {
+      "epoch": 0.11678832116788321,
+      "grad_norm": 0.7176663279533386,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8255,
+      "step": 30
+    },
+    {
+      "epoch": 0.12068126520681265,
+      "grad_norm": 0.7020939588546753,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.8726,
+      "step": 31
+    },
+    {
+      "epoch": 0.1245742092457421,
+      "grad_norm": 0.7199696898460388,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.0506,
+      "step": 32
+    },
+    {
+      "epoch": 0.12846715328467154,
+      "grad_norm": 0.7078929543495178,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9991,
+      "step": 33
+    },
+    {
+      "epoch": 0.13236009732360096,
+      "grad_norm": 0.7883986234664917,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.9867,
+      "step": 34
+    },
+    {
+      "epoch": 0.1362530413625304,
+      "grad_norm": 1.1987528800964355,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8544,
+      "step": 35
+    },
+    {
+      "epoch": 0.14014598540145987,
+      "grad_norm": 0.9711931347846985,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8425,
+      "step": 36
+    },
+    {
+      "epoch": 0.1440389294403893,
+      "grad_norm": 0.9126873016357422,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8503,
+      "step": 37
+    },
+    {
+      "epoch": 0.14793187347931874,
+      "grad_norm": 0.7694374322891235,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0683,
+      "step": 38
+    },
+    {
+      "epoch": 0.15182481751824817,
+      "grad_norm": 0.6620789170265198,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.9371,
+      "step": 39
+    },
+    {
+      "epoch": 0.15571776155717762,
+      "grad_norm": 0.7303202152252197,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0504,
+      "step": 40
+    },
+    {
+      "epoch": 0.15961070559610704,
+      "grad_norm": 0.6710600256919861,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.8286,
+      "step": 41
+    },
+    {
+      "epoch": 0.1635036496350365,
+      "grad_norm": 0.7300748825073242,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1142,
+      "step": 42
+    },
+    {
+      "epoch": 0.16739659367396595,
+      "grad_norm": 0.7144145369529724,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.1115,
+      "step": 43
+    },
+    {
+      "epoch": 0.17128953771289537,
+      "grad_norm": 0.6737845540046692,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0772,
+      "step": 44
+    },
+    {
+      "epoch": 0.17518248175182483,
+      "grad_norm": 0.7557979822158813,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.8919,
+      "step": 45
+    },
+    {
+      "epoch": 0.17907542579075425,
+      "grad_norm": 0.7306810617446899,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9798,
+      "step": 46
+    },
+    {
+      "epoch": 0.1829683698296837,
+      "grad_norm": 0.7133315205574036,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.7939,
+      "step": 47
+    },
+    {
+      "epoch": 0.18686131386861313,
+      "grad_norm": 0.721962571144104,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8628,
+      "step": 48
+    },
+    {
+      "epoch": 0.19075425790754258,
+      "grad_norm": 0.7585230469703674,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.9218,
+      "step": 49
+    },
+    {
+      "epoch": 0.19464720194647203,
+      "grad_norm": 0.9087316393852234,
+      "learning_rate": 0.0,
+      "loss": 1.6011,
+      "step": 50
+    },
+    {
+      "epoch": 0.19464720194647203,
+      "eval_loss": 1.885321855545044,
+      "eval_runtime": 18.8729,
+      "eval_samples_per_second": 91.719,
+      "eval_steps_per_second": 11.498,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null