Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3246b51949dec19faed5fccac7f5c28fe68ceaed2864c60513ae53bb0538734
+oid sha256:19984b0d8590785bfdac6e2aa6e6bf8c63fbb109b1a021b8dd66241e71b9e8b1
 size 997533656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4476dd3e37cf7ae54cf744d2492fe1eb9e9919e3afd21db73cdc671695ce3a66
+oid sha256:4335d3decd77bea658cb976fbb4bdd6da73a916d99568e5bb13fcc19ddcaef7b
 size 507180180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a09ee82dfe4a094c4732fa5e6a3738362c84407410605d5358b112edd61fc60
+oid sha256:872dc95d9082ae8a82e28062da54d94aea6f32709064c360096e535472369f9e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697eb5c311706d748c20f07b0521bb9d1f71aee638eb745112aecf80a82e51da
+oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5630460977554321,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.03678499172337686,
+  "best_metric": 1.5262999534606934,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.05517748758506529,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 10.681,
       "eval_steps_per_second": 2.677,
       "step": 100
+    },
+    {
+      "epoch": 0.04046349089571455,
+      "grad_norm": 0.6026347875595093,
+      "learning_rate": 0.0002085764548830435,
+      "loss": 1.6232,
+      "step": 110
+    },
+    {
+      "epoch": 0.044141990068052236,
+      "grad_norm": 0.7379695773124695,
+      "learning_rate": 0.00020524128762162305,
+      "loss": 1.4991,
+      "step": 120
+    },
+    {
+      "epoch": 0.047820489240389924,
+      "grad_norm": 0.6722536683082581,
+      "learning_rate": 0.00020143724248105043,
+      "loss": 1.5017,
+      "step": 130
+    },
+    {
+      "epoch": 0.051498988412727605,
+      "grad_norm": 0.6395397186279297,
+      "learning_rate": 0.0001971828523868693,
+      "loss": 1.4441,
+      "step": 140
+    },
+    {
+      "epoch": 0.05517748758506529,
+      "grad_norm": 0.8695403933525085,
+      "learning_rate": 0.0001924988442999686,
+      "loss": 1.3411,
+      "step": 150
+    },
+    {
+      "epoch": 0.05517748758506529,
+      "eval_loss": 1.5262999534606934,
+      "eval_runtime": 107.2361,
+      "eval_samples_per_second": 10.677,
+      "eval_steps_per_second": 2.676,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3516964282368e+16,
+  "total_flos": 5.0275446423552e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null