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:a65fc62b17e98ee2f48d32e0705c5e847c50c3922777f08de7718629851ecfe0
+oid sha256:604ac09c8d411abafe73a615271bae685081aeb9d9aa109219c52777c6138759
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ebe1c15e377333c79dd7d85f6a77c313b30318ae2cb95c999490f68cda43e9
+oid sha256:c8b64c5da8513d93d3af9c9c4dcca4356a69d930833cb4bb048dd3ceb343174d
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6069c262ae1c977de720efbc7041ae7a796e99c03ebef59ad16e731210e11a8c
+oid sha256:f49cc70e43698962a43ee5f1e5ea93c76dbe4ce826f81dfbb789efeb8adbd88f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff293d6444222bd1d89236cd1763caa87bb59d6363a546a504877debc45066aa
+oid sha256:aa1bfb19ac7a71e5a662427e7488d4a4d957109537750c19fd28e94a30346c50
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2990323305130005,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.034916201117318434,
+  "best_metric": 1.2746367454528809,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.06983240223463687,
   "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": 11.523,
       "eval_steps_per_second": 2.886,
       "step": 50
+    },
+    {
+      "epoch": 0.04189944134078212,
+      "grad_norm": 0.47972574830055237,
+      "learning_rate": 0.00021074300730241147,
+      "loss": 0.9318,
+      "step": 60
+    },
+    {
+      "epoch": 0.04888268156424581,
+      "grad_norm": 0.447611004114151,
+      "learning_rate": 0.00020997328125223568,
+      "loss": 0.8635,
+      "step": 70
+    },
+    {
+      "epoch": 0.055865921787709494,
+      "grad_norm": 0.48597830533981323,
+      "learning_rate": 0.0002086945718774165,
+      "loss": 0.9055,
+      "step": 80
+    },
+    {
+      "epoch": 0.06284916201117319,
+      "grad_norm": 0.6027791500091553,
+      "learning_rate": 0.00020691310892149265,
+      "loss": 0.9913,
+      "step": 90
+    },
+    {
+      "epoch": 0.06983240223463687,
+      "grad_norm": 1.350448489189148,
+      "learning_rate": 0.00020463757149291335,
+      "loss": 2.3175,
+      "step": 100
+    },
+    {
+      "epoch": 0.06983240223463687,
+      "eval_loss": 1.2746367454528809,
+      "eval_runtime": 52.113,
+      "eval_samples_per_second": 11.571,
+      "eval_steps_per_second": 2.898,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.395228272492544e+16,
+  "total_flos": 2.817116957835264e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null