Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0699ca4de27e58db97cc6b27be37d58c6acc867741a887955dc90e3adc4255df
+oid sha256:69f65c76ed793a44d9c23d6fe986af55ebca2dd204c46cdf098a1187012e2fc2
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024ba709d7ce8919beb9e6a3e1ae8de7e25cdbecf726711c297333fa79294c3e
+oid sha256:f43e6f511e273676e1ddb8e13214b2c24f66873be15eca00043a2f53da349253
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bbd8ff7e32216810ea7bd520f178cf2bfc5faa8502982101e50fd1bbcdbdbbd
+oid sha256:2b2fee558c9495cb623a884636f71596218024aa791ce615245d2e3ab584219d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0ae195d31357f5defc54b09ff712d3e8a645441befdccfede53a6dd1acdeebf
+oid sha256:bf46b31db7a35a4f33a788122727c08a6ae915948d136962f20a8e597d273f2e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.864169597625732,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.011763321962122103,
+  "best_metric": 6.832787036895752,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.023526643924244205,
   "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": 561.335,
       "eval_steps_per_second": 140.491,
       "step": 50
+    },
+    {
+      "epoch": 0.014115986354546525,
+      "grad_norm": 0.49429962038993835,
+      "learning_rate": 0.00021373935337780118,
+      "loss": 6.8976,
+      "step": 60
+    },
+    {
+      "epoch": 0.016468650746970945,
+      "grad_norm": 0.4391353726387024,
+      "learning_rate": 0.00021295868335534802,
+      "loss": 6.8643,
+      "step": 70
+    },
+    {
+      "epoch": 0.018821315139395365,
+      "grad_norm": 0.4785984754562378,
+      "learning_rate": 0.0002116617932785172,
+      "loss": 6.8459,
+      "step": 80
+    },
+    {
+      "epoch": 0.021173979531819785,
+      "grad_norm": 0.5224839448928833,
+      "learning_rate": 0.00020985500146540012,
+      "loss": 6.8126,
+      "step": 90
+    },
+    {
+      "epoch": 0.023526643924244205,
+      "grad_norm": 0.7273280024528503,
+      "learning_rate": 0.0002075471104240922,
+      "loss": 6.8084,
+      "step": 100
+    },
+    {
+      "epoch": 0.023526643924244205,
+      "eval_loss": 6.832787036895752,
+      "eval_runtime": 3.2348,
+      "eval_samples_per_second": 553.365,
+      "eval_steps_per_second": 138.496,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 120141004800.0,
+  "total_flos": 240282009600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null