Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632bcfb77e63319dedf96d3e14b621b8f4b48645e894175bb767a8d5ba826f35
+oid sha256:783f430e39c1a0a3580af314870f5a1fb5370147d2f31754c13f9b35e0af4fa6
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38e1358b3e276ca6e542758c57c2771979420c2e84d93a6912570311ef45f626
+oid sha256:086bb265e820ab945d1978839d90771e2c6752bae98469f227ac389f91deb03a
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a74fac83fdb4a5a1908cbd90e4b073a5a5313993b97f78970d46912c8fc87947
+oid sha256:e045276e0937c8c5281651aa9ed8e933d9b3aa852e701288b0ef181f067313b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e3c543dd881d7b92b58f753c91bcd488f8269b3e4ffd67623431c55e782209
+oid sha256:8e4a64d71eed58bad723d1496b310be4dbd45cd96d8ef2f7cd1e195fe59bff7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.9041831493377686,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.008920606601248885,
+  "best_metric": 2.8749983310699463,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.011894142134998514,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 47.257,
       "eval_steps_per_second": 11.814,
       "step": 150
+    },
+    {
+      "epoch": 0.00951531370799881,
+      "grad_norm": 0.7546591758728027,
+      "learning_rate": 0.0001779516693350504,
+      "loss": 2.8554,
+      "step": 160
+    },
+    {
+      "epoch": 0.010110020814748736,
+      "grad_norm": 0.7574900388717651,
+      "learning_rate": 0.00017275501775814182,
+      "loss": 2.7957,
+      "step": 170
+    },
+    {
+      "epoch": 0.010704727921498661,
+      "grad_norm": 0.8689918518066406,
+      "learning_rate": 0.00016722096269620562,
+      "loss": 2.8529,
+      "step": 180
+    },
+    {
+      "epoch": 0.011299435028248588,
+      "grad_norm": 1.0633153915405273,
+      "learning_rate": 0.00016137646550922228,
+      "loss": 2.8309,
+      "step": 190
+    },
+    {
+      "epoch": 0.011894142134998514,
+      "grad_norm": 2.1989660263061523,
+      "learning_rate": 0.00015525,
+      "loss": 2.9186,
+      "step": 200
+    },
+    {
+      "epoch": 0.011894142134998514,
+      "eval_loss": 2.8749983310699463,
+      "eval_runtime": 149.067,
+      "eval_samples_per_second": 47.495,
+      "eval_steps_per_second": 11.874,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1563569639915520.0,
+  "total_flos": 2090767472394240.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null