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:f851d7fbec79522799fcb5d074b1d9b2aadcc40d113e0309ef98cafbd7068e70
+oid sha256:9b404017d938064912f2c57b4643037046329ebcc23f7201243e78ea8a76eaa3
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed80cf13e1007e6ff620bd6e550136585832d9d7ae34ef9964c2ce784269129b
+oid sha256:884d56a38687330289cc19c423dd01a3bcc501b1eeca20f94d5d4a7471413f20
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0551e97453d9ae10819166b91ebf1cddf27d5fcb315c65549de5aa2ad4d60cfa
+oid sha256:ae341615e23f78ea0d9ec53f366f85dd01668aeaa6fa0024d702041da2ad7e77
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1533548831939697,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.038204393505253106,
+  "best_metric": 2.0634360313415527,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.07640878701050621,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 2.54,
       "eval_steps_per_second": 0.644,
       "step": 10
+    },
+    {
+      "epoch": 0.045845272206303724,
+      "grad_norm": 0.16003547608852386,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.1493,
+      "step": 12
+    },
+    {
+      "epoch": 0.05730659025787966,
+      "grad_norm": 0.17825794219970703,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.1093,
+      "step": 15
+    },
+    {
+      "epoch": 0.05730659025787966,
+      "eval_loss": 2.093752861022949,
+      "eval_runtime": 86.9783,
+      "eval_samples_per_second": 2.541,
+      "eval_steps_per_second": 0.644,
+      "step": 15
+    },
+    {
+      "epoch": 0.06876790830945559,
+      "grad_norm": 0.15024003386497498,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.1147,
+      "step": 18
+    },
+    {
+      "epoch": 0.07640878701050621,
+      "eval_loss": 2.0634360313415527,
+      "eval_runtime": 86.9622,
+      "eval_samples_per_second": 2.541,
+      "eval_steps_per_second": 0.644,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5391158788096e+16,
+  "total_flos": 5.0782317576192e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null