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:eea82364e647b5c4d401b91aae9fc7ef63c49892aee8818f7c706500599b5d5d
+oid sha256:953be3a656373376c66a6830714687bf84fd7d7d7cb55019b7aba47fc9665150
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e23861933bff149e357536f01120af092bcb96de9aaa3a8825a150fa7f84e16
+oid sha256:8426979b814d0ed0bfb1e9b46084cb08c2086115d8bcd50f4855198958ddb7ff
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f534c3b16831353fa4b63569bc9a89294f70d374a11b77300960914fa249ce2
+oid sha256:7997d407d530053dc265970b89da31e783b48e60cf7d581555906a0d35844b5e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.598532795906067,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.024524831391784182,
+  "best_metric": 1.3281397819519043,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.049049662783568364,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 4.772,
       "eval_steps_per_second": 2.386,
       "step": 10
+    },
+    {
+      "epoch": 0.0269773145309626,
+      "grad_norm": 1.1657987833023071,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.6275,
+      "step": 11
+    },
+    {
+      "epoch": 0.029429797670141016,
+      "grad_norm": 1.2491055727005005,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.4108,
+      "step": 12
+    },
+    {
+      "epoch": 0.03188228080931944,
+      "grad_norm": 1.3122302293777466,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.5438,
+      "step": 13
+    },
+    {
+      "epoch": 0.034334763948497854,
+      "grad_norm": 1.375346064567566,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.3879,
+      "step": 14
+    },
+    {
+      "epoch": 0.03678724708767627,
+      "grad_norm": 1.3388978242874146,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.319,
+      "step": 15
+    },
+    {
+      "epoch": 0.03678724708767627,
+      "eval_loss": 1.3976945877075195,
+      "eval_runtime": 36.051,
+      "eval_samples_per_second": 4.771,
+      "eval_steps_per_second": 2.386,
+      "step": 15
+    },
+    {
+      "epoch": 0.03923973022685469,
+      "grad_norm": 1.8990790843963623,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.4382,
+      "step": 16
+    },
+    {
+      "epoch": 0.041692213366033105,
+      "grad_norm": 1.6522033214569092,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.351,
+      "step": 17
+    },
+    {
+      "epoch": 0.04414469650521153,
+      "grad_norm": 1.8031131029129028,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.4272,
+      "step": 18
+    },
+    {
+      "epoch": 0.04659717964438995,
+      "grad_norm": 1.5843220949172974,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.0583,
+      "step": 19
+    },
+    {
+      "epoch": 0.049049662783568364,
+      "grad_norm": 1.3835418224334717,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.099,
+      "step": 20
+    },
+    {
+      "epoch": 0.049049662783568364,
+      "eval_loss": 1.3281397819519043,
+      "eval_runtime": 36.7286,
+      "eval_samples_per_second": 4.683,
+      "eval_steps_per_second": 2.341,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3135311286632448.0,
+  "total_flos": 6352059230060544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null