Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:521acc0180e6d1e67c06de5204482e8348e97be9d2c13e72e3173ddd5605ee71
+oid sha256:d0f84b04a2eeb38966d2568328a5f593d47120546b5da65834b39943e338bf5a
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5387bbc8f0058dd15552a7d6be29e4d8a2ab697a7fc05146d789e2bcf7d83c13
+oid sha256:eadbf4aa7bba76fbb78467943f0a75b696861b0d1e360998af6a6e98a501ea42
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af74accd7327d72d5059e691ff96af46a9e13ec1aeec2087c6705ce6332b519
+oid sha256:d6ed9ebb7297ee2e0f818b649d564c25c55944ce776d4f6fb15d80ba0ede6b9d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1425969cd8e5d9456eff9b286f7f5cbcd4119e2e34178d957af8f58c73bf1eea
+oid sha256:70f9eefb79e5a651e4979588997923d1fc997984394f03e9fb61aca38c6bee05
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.639662504196167,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0429553264604811,
+  "best_metric": 1.587920069694519,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.0859106529209622,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 20.399,
       "eval_steps_per_second": 5.121,
       "step": 50
+    },
+    {
+      "epoch": 0.05154639175257732,
+      "grad_norm": 0.652748167514801,
+      "learning_rate": 7.855555555555556e-06,
+      "loss": 1.5711,
+      "step": 60
+    },
+    {
+      "epoch": 0.06013745704467354,
+      "grad_norm": 0.6387035846710205,
+      "learning_rate": 7.294444444444444e-06,
+      "loss": 1.6766,
+      "step": 70
+    },
+    {
+      "epoch": 0.06872852233676977,
+      "grad_norm": 0.6020448803901672,
+      "learning_rate": 6.733333333333333e-06,
+      "loss": 1.5793,
+      "step": 80
+    },
+    {
+      "epoch": 0.07731958762886598,
+      "grad_norm": 0.7771233320236206,
+      "learning_rate": 6.172222222222223e-06,
+      "loss": 1.5681,
+      "step": 90
+    },
+    {
+      "epoch": 0.0859106529209622,
+      "grad_norm": 1.099347472190857,
+      "learning_rate": 5.611111111111111e-06,
+      "loss": 1.6476,
+      "step": 100
+    },
+    {
+      "epoch": 0.0859106529209622,
+      "eval_loss": 1.587920069694519,
+      "eval_runtime": 24.0797,
+      "eval_samples_per_second": 20.349,
+      "eval_steps_per_second": 5.108,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.513988554752e+16,
+  "total_flos": 2.9943329193984e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null