Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1370ad3c1883db511fc40229d954e39ca02b8b229b1dff560c59cf0d6c31af66
+oid sha256:1fa695feddce03c21355299741548ef01414a73e84113e5eeaf6585af14973b4
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcce895a3b46441ed88cdaf97a45b7ec7f29582b7b9c73927cff4c96de37b23
+oid sha256:60ebdd50680977b4a41233c3a9447e96277631cd19f43cc43d573d351750c516
 size 51418196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064ca9091358d66e2ab03aefa648106f992aba53d671e16240504e9a408be35c
+oid sha256:518e3d3c2c08ef3f14d6f9dca0c125a6a693fcc7f4de3079ce531745772767d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b49f2fa3a406bdd61a3e48a2439867e734b5cd9ac3b08f0221d2c0369ea6d2
+oid sha256:0051c53bcb92b7c913136d782f625b409707ede35cdcc9bbc83a63d788098e04
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9343328475952148,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.05884083553986467,
+  "best_metric": 0.8446639180183411,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.11768167107972934,
   "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": 22.043,
       "eval_steps_per_second": 5.511,
       "step": 50
+    },
+    {
+      "epoch": 0.0706090026478376,
+      "grad_norm": 0.8677065968513489,
+      "learning_rate": 0.0001964767868814516,
+      "loss": 6.2807,
+      "step": 60
+    },
+    {
+      "epoch": 0.08237716975581054,
+      "grad_norm": 0.7287414073944092,
+      "learning_rate": 0.00019493976084683813,
+      "loss": 4.9082,
+      "step": 70
+    },
+    {
+      "epoch": 0.09414533686378347,
+      "grad_norm": 1.209147572517395,
+      "learning_rate": 0.00019313361774523385,
+      "loss": 3.0766,
+      "step": 80
+    },
+    {
+      "epoch": 0.1059135039717564,
+      "grad_norm": 0.9230589866638184,
+      "learning_rate": 0.00019106347728549135,
+      "loss": 1.5117,
+      "step": 90
+    },
+    {
+      "epoch": 0.11768167107972934,
+      "grad_norm": 2.2932982444763184,
+      "learning_rate": 0.00018873520750565718,
+      "loss": 1.5895,
+      "step": 100
+    },
+    {
+      "epoch": 0.11768167107972934,
+      "eval_loss": 0.8446639180183411,
+      "eval_runtime": 64.7346,
+      "eval_samples_per_second": 22.121,
+      "eval_steps_per_second": 5.53,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.361817002770432e+16,
+  "total_flos": 6.723634005540864e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null