Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3dcf08a07630b5d8fc12ef87471f9719a4330767db2f392e7e778819cc19793
+oid sha256:4b336e8073b3a2fd13e0b0c7c2350a546f4ead5d10a9b415d60b63dd48fca689
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f634f46c5652f6927cadf4b686224a762c5aab8d5eeea6c0483118e382980539
+oid sha256:f21c75ebd30d8c38e76f59f8cf907a2137ff4f272476fbe3fb4fae86bad3447d
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:116799cfcafee8097de641f682eb6f4469057abad98c74c9f9734a95406a096b
+oid sha256:6d22c5e4d98a66829548cb600325d63aaa8739d17a7aecf0100846f2afe72e70
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d848dabb6bc38ff43473c21d7be2b08bb8548094e836702054933aaacbbfba
+oid sha256:767a2fd667ddadd1421c73fc4302b452a37b1de4baa59f021c867ede8f954df9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7539ac9f02350f27a3e6b73b4f7464ed1d850a06448ed4b703d06302d3eb098b
+oid sha256:49a812e938b03f1fdbad64f9936ab0790ba8fcbc329d29a159207d72cdc68f26
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb75b64ab4ee313717cb111207c37bf02c69745d8fb056d01bab9109e6ae055a
+oid sha256:b79cfb5239c137907672a844adb26ffb5c8d84a40da24ce2be6abd4a077036d8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c220d2fbe9a2870f9ac93749b3d4b3852ce94b5983d948fa8de3d35e453f98ce
+oid sha256:7312f49c1e1b01f68cdaee175129535fda49cd22ed1f251a2745d2c8c42996be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8160011172294617,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2598870056497176,
+  "epoch": 3.073446327683616,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,69 @@
       "eval_samples_per_second": 21.497,
       "eval_steps_per_second": 5.589,
       "step": 25
+    },
+    {
+      "epoch": 2.3502824858757063,
+      "grad_norm": 2.9992833137512207,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7953,
+      "step": 26
+    },
+    {
+      "epoch": 2.440677966101695,
+      "grad_norm": 3.01076602935791,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 0.7956,
+      "step": 27
+    },
+    {
+      "epoch": 2.5310734463276834,
+      "grad_norm": 3.3934991359710693,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.8145,
+      "step": 28
+    },
+    {
+      "epoch": 2.621468926553672,
+      "grad_norm": 2.1873085498809814,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 0.7734,
+      "step": 29
+    },
+    {
+      "epoch": 2.711864406779661,
+      "grad_norm": 1.753711462020874,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.7645,
+      "step": 30
+    },
+    {
+      "epoch": 2.8022598870056497,
+      "grad_norm": 3.903904914855957,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 0.8525,
+      "step": 31
+    },
+    {
+      "epoch": 2.8926553672316384,
+      "grad_norm": 1.5703907012939453,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7837,
+      "step": 32
+    },
+    {
+      "epoch": 2.983050847457627,
+      "grad_norm": 1.638397216796875,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 0.8452,
+      "step": 33
+    },
+    {
+      "epoch": 3.073446327683616,
+      "grad_norm": 1.8110815286636353,
+      "learning_rate": 1e-05,
+      "loss": 1.5157,
+      "step": 34
     }
   ],
   "logging_steps": 1,
@@ -221,12 +284,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.087239672233984e+17,
+  "total_flos": 4.198645954238218e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null