Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c1f34cdc6065ed72f4de2dda23172c19424e387e6908fe94a03030d40c7af6f
+oid sha256:8240f519392129a19102ff04c9add810864f445ee1f8dac2ff3faf28b901893c
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af0a5133080268fec9bec0208b89cc06ac9998581a2557b10035628c35ca95c5
+oid sha256:9a53e70c0226d912e793c6d94377401d17b136c90cb79e805e5fe0316b3f444e
 size 445835066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020ca376f4228a2ef9ca385cd5daed6527ca20102bc7adba3cc1f49052ea0a24
+oid sha256:98e31a45a8095a57ba97d7f9515c49fa268d5f648d3f99241bdc55f4bf0e98b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3284010887145996,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0017139429257005741,
+  "best_metric": 1.2484335899353027,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0034278858514011482,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 4.183,
       "eval_steps_per_second": 2.092,
       "step": 10
+    },
+    {
+      "epoch": 0.002056731510840689,
+      "grad_norm": 10.381022453308105,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 5.3987,
+      "step": 12
+    },
+    {
+      "epoch": 0.0025709143885508613,
+      "grad_norm": 1.8296691179275513,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 4.907,
+      "step": 15
+    },
+    {
+      "epoch": 0.0025709143885508613,
+      "eval_loss": 1.2899432182312012,
+      "eval_runtime": 587.3318,
+      "eval_samples_per_second": 4.183,
+      "eval_steps_per_second": 2.093,
+      "step": 15
+    },
+    {
+      "epoch": 0.0030850972662610334,
+      "grad_norm": 1.917513132095337,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 5.0149,
+      "step": 18
+    },
+    {
+      "epoch": 0.0034278858514011482,
+      "eval_loss": 1.2484335899353027,
+      "eval_runtime": 587.2531,
+      "eval_samples_per_second": 4.184,
+      "eval_steps_per_second": 2.093,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6808424939520000.0,
+  "total_flos": 1.361684987904e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null