Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9d15ad6b956ed7556492b119624ac8cbab5fe7025fad86059e26b4aa107a0c
+oid sha256:d94b0e61ca62333c8edceaca9061be8b33191d2dd03c0f7004e3d35e6b540140
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37308e15fd8d36c3b900ddf899d5ba78bfe555e1bb9cc19870a2c2e54d721255
+oid sha256:f79ca6da8f60adbc0310cbfd09164f9c654b0935cf02a14fcdf5f54b4f70064a
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:264e3cca76acb7d6526d50525764a7d4846a597083f717e5883939b1ca109674
+oid sha256:ceffdaae13eedb884e9296ba957ab0ae09810cd43fe18f1e2c2f24d777ddd96d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0453726053237915,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0013667270304438446,
+  "best_metric": 0.8442187905311584,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.002733454060887689,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 5.719,
       "eval_steps_per_second": 2.86,
       "step": 10
+    },
+    {
+      "epoch": 0.001503399733488229,
+      "grad_norm": 0.8284047245979309,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.9237,
+      "step": 11
+    },
+    {
+      "epoch": 0.0016400724365326135,
+      "grad_norm": 0.6000273823738098,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.0106,
+      "step": 12
+    },
+    {
+      "epoch": 0.001776745139576998,
+      "grad_norm": 1.1275712251663208,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.8098,
+      "step": 13
+    },
+    {
+      "epoch": 0.0019134178426213825,
+      "grad_norm": 0.4717814326286316,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.6462,
+      "step": 14
+    },
+    {
+      "epoch": 0.002050090545665767,
+      "grad_norm": 0.7204762697219849,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.9598,
+      "step": 15
+    },
+    {
+      "epoch": 0.002050090545665767,
+      "eval_loss": 0.904741108417511,
+      "eval_runtime": 541.6221,
+      "eval_samples_per_second": 5.688,
+      "eval_steps_per_second": 2.845,
+      "step": 15
+    },
+    {
+      "epoch": 0.0021867632487101514,
+      "grad_norm": 0.5360210537910461,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.8431,
+      "step": 16
+    },
+    {
+      "epoch": 0.002323435951754536,
+      "grad_norm": 0.6423148512840271,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.7532,
+      "step": 17
+    },
+    {
+      "epoch": 0.0024601086547989203,
+      "grad_norm": 0.49850893020629883,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.6763,
+      "step": 18
+    },
+    {
+      "epoch": 0.0025967813578433047,
+      "grad_norm": 0.6532036662101746,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6426,
+      "step": 19
+    },
+    {
+      "epoch": 0.002733454060887689,
+      "grad_norm": 0.4738406240940094,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.9267,
+      "step": 20
+    },
+    {
+      "epoch": 0.002733454060887689,
+      "eval_loss": 0.8442187905311584,
+      "eval_runtime": 541.123,
+      "eval_samples_per_second": 5.694,
+      "eval_steps_per_second": 2.848,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3007276835143680.0,
+  "total_flos": 6138140389539840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null