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:dc90759924009111a350ab3652d810019255452229375672558e31c5db6d21d2
+oid sha256:08bae529c81cd9d02f6c2652a23689f82485d37ed18f1ab7e02d1f153dd6859b
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88be791e8b98f0f8d5f194bd67c7187c2e81245cf7f6cfa70ee0658f48fc6f44
+oid sha256:2ee460eb38de3f778105bea854e450edd87b2416d94387200305643a9a1be1ec
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48095226a6e232eefa717dcb6539a9e2502b2adc6669fae4f321453cba7fc057
+oid sha256:c1999a68120cf27dfd8721161ff7ed3b48e0968b5c5249d7a0928273c54401da
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ec8b7a3e6afc171abcf0e29ff382e39d3863fc1aa63d2e8f8a9efef0366cc2
+oid sha256:69a937f7641048eac0d694655ca7f4f4015d6bb49fac492b1cf3223a8ecc7982
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9c29178ecc5bc8df67295dc46b942cab77b4fe717697821d8be665f3f1ede4
+oid sha256:ee2762200d310fc7a16f2080744ad5b8abafc01414e50e65a138757bb191301f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5396be8858b8451a1782d001f7219a90a2ccbb3e591a320d288b8729c0546c1
+oid sha256:8ba943c44fb1bf7c2e279da6255c782b9467f4cb8fb364567b9fce9f8b86a841
 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": 1.9761757850646973,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.35587188612099646,
+  "best_metric": 1.9367903470993042,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7117437722419929,
   "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": 21.008,
       "eval_steps_per_second": 2.665,
       "step": 25
+    },
+    {
+      "epoch": 0.3701067615658363,
+      "grad_norm": 0.9723377227783203,
+      "learning_rate": 5e-05,
+      "loss": 1.843,
+      "step": 26
+    },
+    {
+      "epoch": 0.38434163701067614,
+      "grad_norm": 0.883572518825531,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.7424,
+      "step": 27
+    },
+    {
+      "epoch": 0.398576512455516,
+      "grad_norm": 0.7840570211410522,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.8546,
+      "step": 28
+    },
+    {
+      "epoch": 0.4128113879003559,
+      "grad_norm": 0.8222391605377197,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.8556,
+      "step": 29
+    },
+    {
+      "epoch": 0.42704626334519574,
+      "grad_norm": 0.7635681629180908,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8463,
+      "step": 30
+    },
+    {
+      "epoch": 0.4412811387900356,
+      "grad_norm": 0.863717794418335,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.8744,
+      "step": 31
+    },
+    {
+      "epoch": 0.4555160142348754,
+      "grad_norm": 0.8257912397384644,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9853,
+      "step": 32
+    },
+    {
+      "epoch": 0.4697508896797153,
+      "grad_norm": 0.7964351177215576,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9543,
+      "step": 33
+    },
+    {
+      "epoch": 0.48398576512455516,
+      "grad_norm": 0.8466922044754028,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.9271,
+      "step": 34
+    },
+    {
+      "epoch": 0.498220640569395,
+      "grad_norm": 0.7582820057868958,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.0414,
+      "step": 35
+    },
+    {
+      "epoch": 0.5124555160142349,
+      "grad_norm": 0.7933133244514465,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.1764,
+      "step": 36
+    },
+    {
+      "epoch": 0.5266903914590747,
+      "grad_norm": 1.0502933263778687,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.2742,
+      "step": 37
+    },
+    {
+      "epoch": 0.5409252669039146,
+      "grad_norm": 0.7502277493476868,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0152,
+      "step": 38
+    },
+    {
+      "epoch": 0.5551601423487544,
+      "grad_norm": 0.6980727314949036,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.8224,
+      "step": 39
+    },
+    {
+      "epoch": 0.5693950177935944,
+      "grad_norm": 0.6420523524284363,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.7978,
+      "step": 40
+    },
+    {
+      "epoch": 0.5836298932384342,
+      "grad_norm": 0.6218376755714417,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.8147,
+      "step": 41
+    },
+    {
+      "epoch": 0.597864768683274,
+      "grad_norm": 0.666327714920044,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.953,
+      "step": 42
+    },
+    {
+      "epoch": 0.6120996441281139,
+      "grad_norm": 0.6272517442703247,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.7463,
+      "step": 43
+    },
+    {
+      "epoch": 0.6263345195729537,
+      "grad_norm": 0.6795321106910706,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7496,
+      "step": 44
+    },
+    {
+      "epoch": 0.6405693950177936,
+      "grad_norm": 0.6798703670501709,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.884,
+      "step": 45
+    },
+    {
+      "epoch": 0.6548042704626335,
+      "grad_norm": 0.7086116075515747,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9659,
+      "step": 46
+    },
+    {
+      "epoch": 0.6690391459074733,
+      "grad_norm": 0.7290291786193848,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.049,
+      "step": 47
+    },
+    {
+      "epoch": 0.6832740213523132,
+      "grad_norm": 0.7203341126441956,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.976,
+      "step": 48
+    },
+    {
+      "epoch": 0.697508896797153,
+      "grad_norm": 0.7907271981239319,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.172,
+      "step": 49
+    },
+    {
+      "epoch": 0.7117437722419929,
+      "grad_norm": 0.8677495718002319,
+      "learning_rate": 0.0,
+      "loss": 2.2552,
+      "step": 50
+    },
+    {
+      "epoch": 0.7117437722419929,
+      "eval_loss": 1.9367903470993042,
+      "eval_runtime": 22.4882,
+      "eval_samples_per_second": 21.033,
+      "eval_steps_per_second": 2.668,
+      "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": 5.114180768104448e+17,
+  "total_flos": 1.0228361536208896e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null