Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55b5b1384ef1a4182ef84080850e0338c09c123bc4ca3a6e4d8d803a21cf5b0
+oid sha256:7c6deca04e11a19b82831c5ccd8242f355be4f9b37d8796e5507a5b500c473be
 size 864368280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6670c71979f0d37a7dbe952f2dd0534c2691704150e622cfdec2d6e097ba11c6
+oid sha256:77a23ed555cc893f2f994a2ceeef2b152056030d58e492d3b041c3886e331445
 size 439588164

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42b5fdee32026592763edc587fdf4b992199bc66c75b9451b2fd84ed4b2bff3
+oid sha256:5d63a134cc3f1399baeb171edc0216a7efb43b91023df4e86760ba5a0fb3c447
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7708307d1b959a393541df6c657dca87476d08205aaca5feb82f751cfc227436
+oid sha256:93a4031351d40494c6fa2a2ab0690336e71553ec331e91c1b2ab832fe81468d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9161679148674011,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.048355899419729204,
+  "best_metric": 0.8664661645889282,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.09671179883945841,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 6.587,
       "eval_steps_per_second": 3.297,
       "step": 100
+    },
+    {
+      "epoch": 0.05319148936170213,
+      "grad_norm": 5.653870582580566,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 1.0653,
+      "step": 110
+    },
+    {
+      "epoch": 0.058027079303675046,
+      "grad_norm": 5.368271350860596,
+      "learning_rate": 3e-05,
+      "loss": 0.7673,
+      "step": 120
+    },
+    {
+      "epoch": 0.06286266924564797,
+      "grad_norm": 5.161637306213379,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 0.7348,
+      "step": 130
+    },
+    {
+      "epoch": 0.06769825918762089,
+      "grad_norm": 4.92420768737793,
+      "learning_rate": 3.5e-05,
+      "loss": 0.9869,
+      "step": 140
+    },
+    {
+      "epoch": 0.0725338491295938,
+      "grad_norm": 4.13116979598999,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.9724,
+      "step": 150
+    },
+    {
+      "epoch": 0.07736943907156674,
+      "grad_norm": 3.968526601791382,
+      "learning_rate": 4e-05,
+      "loss": 0.8784,
+      "step": 160
+    },
+    {
+      "epoch": 0.08220502901353965,
+      "grad_norm": 3.1204934120178223,
+      "learning_rate": 4.25e-05,
+      "loss": 0.7255,
+      "step": 170
+    },
+    {
+      "epoch": 0.08704061895551257,
+      "grad_norm": 3.6519956588745117,
+      "learning_rate": 4.5e-05,
+      "loss": 0.9508,
+      "step": 180
+    },
+    {
+      "epoch": 0.09187620889748549,
+      "grad_norm": 8.2903413772583,
+      "learning_rate": 4.75e-05,
+      "loss": 0.7325,
+      "step": 190
+    },
+    {
+      "epoch": 0.09671179883945841,
+      "grad_norm": 4.074306488037109,
+      "learning_rate": 5e-05,
+      "loss": 0.8663,
+      "step": 200
+    },
+    {
+      "epoch": 0.09671179883945841,
+      "eval_loss": 0.8664661645889282,
+      "eval_runtime": 132.3019,
+      "eval_samples_per_second": 6.583,
+      "eval_steps_per_second": 3.295,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -116,12 +194,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.067065616053043e+16,
+  "total_flos": 1.8050176920846336e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null