Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da3bba99c397ef4b7f125242f280bcf16e36defe7d46d1e0a9df90286f0ec136
+oid sha256:c71ad4338f06f674e2d0c21a29e277181ed00d95784e10f4dfe16d81e49fbee1
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebeed5cc9e4e186a8b785aef1ac80eec9a72a05ad6df5e40b54231301af1ff36
+oid sha256:64b3d86bccaae2b8c19671d36d103ecafb5682a4758ae0d6e351e6bcec075915
 size 121430

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:958a16ea4d01c4d32ad17077b47780afd42e4c2cba1107ac2de6a76659960a45
+oid sha256:1587bfa9125c3473f421ab7fc0730693aa315162f7c8523bf68c63d742a00fcf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.848521709442139,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0017466638720044715,
+  "best_metric": 6.83262300491333,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.003493327744008943,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 294.8,
       "eval_steps_per_second": 147.424,
       "step": 25
+    },
+    {
+      "epoch": 0.0018165304268846503,
+      "grad_norm": 0.4626302123069763,
+      "learning_rate": 0.0001,
+      "loss": 6.8368,
+      "step": 26
+    },
+    {
+      "epoch": 0.0018863969817648292,
+      "grad_norm": 0.46538764238357544,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 6.8595,
+      "step": 27
+    },
+    {
+      "epoch": 0.001956263536645008,
+      "grad_norm": 0.5668134093284607,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 6.8305,
+      "step": 28
+    },
+    {
+      "epoch": 0.002026130091525187,
+      "grad_norm": 0.4846513867378235,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 6.8458,
+      "step": 29
+    },
+    {
+      "epoch": 0.0020959966464053656,
+      "grad_norm": 0.5467333197593689,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 6.8318,
+      "step": 30
+    },
+    {
+      "epoch": 0.0021658632012855447,
+      "grad_norm": 0.540037214756012,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 6.8427,
+      "step": 31
+    },
+    {
+      "epoch": 0.0022357297561657235,
+      "grad_norm": 0.49980029463768005,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 6.8372,
+      "step": 32
+    },
+    {
+      "epoch": 0.002305596311045902,
+      "grad_norm": 0.467425674200058,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 6.8629,
+      "step": 33
+    },
+    {
+      "epoch": 0.0023754628659260813,
+      "grad_norm": 0.48374143242836,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.8463,
+      "step": 34
+    },
+    {
+      "epoch": 0.00244532942080626,
+      "grad_norm": 0.4555916488170624,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 6.8526,
+      "step": 35
+    },
+    {
+      "epoch": 0.0025151959756864388,
+      "grad_norm": 0.5127541422843933,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 6.8357,
+      "step": 36
+    },
+    {
+      "epoch": 0.002585062530566618,
+      "grad_norm": 0.44566676020622253,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 6.8396,
+      "step": 37
+    },
+    {
+      "epoch": 0.0026549290854467967,
+      "grad_norm": 0.4989950358867645,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 6.8291,
+      "step": 38
+    },
+    {
+      "epoch": 0.0027247956403269754,
+      "grad_norm": 0.4991087019443512,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 6.8387,
+      "step": 39
+    },
+    {
+      "epoch": 0.0027946621952071545,
+      "grad_norm": 0.5077288150787354,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.8349,
+      "step": 40
+    },
+    {
+      "epoch": 0.0028645287500873333,
+      "grad_norm": 0.4772498905658722,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 6.8435,
+      "step": 41
+    },
+    {
+      "epoch": 0.002934395304967512,
+      "grad_norm": 0.4704778492450714,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.8389,
+      "step": 42
+    },
+    {
+      "epoch": 0.0030042618598476907,
+      "grad_norm": 0.47462359070777893,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 6.8362,
+      "step": 43
+    },
+    {
+      "epoch": 0.00307412841472787,
+      "grad_norm": 0.42201927304267883,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.8744,
+      "step": 44
+    },
+    {
+      "epoch": 0.0031439949696080486,
+      "grad_norm": 0.4583438038825989,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 6.8459,
+      "step": 45
+    },
+    {
+      "epoch": 0.0032138615244882273,
+      "grad_norm": 0.40070590376853943,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 6.8537,
+      "step": 46
+    },
+    {
+      "epoch": 0.0032837280793684065,
+      "grad_norm": 0.4594520628452301,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 6.8449,
+      "step": 47
+    },
+    {
+      "epoch": 0.003353594634248585,
+      "grad_norm": 0.5334432125091553,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 6.8251,
+      "step": 48
+    },
+    {
+      "epoch": 0.003423461189128764,
+      "grad_norm": 0.5096091628074646,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 6.8198,
+      "step": 49
+    },
+    {
+      "epoch": 0.003493327744008943,
+      "grad_norm": 0.566801130771637,
+      "learning_rate": 0.0,
+      "loss": 6.8349,
+      "step": 50
+    },
+    {
+      "epoch": 0.003493327744008943,
+      "eval_loss": 6.83262300491333,
+      "eval_runtime": 20.4848,
+      "eval_samples_per_second": 294.218,
+      "eval_steps_per_second": 147.134,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 294651494400.0,
+  "total_flos": 589302988800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null