Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c97802d7ccb75584203fac5928cf25115abcb2ea1b271164c00f2f175efe0e
+oid sha256:e2aa905d76b930692980c1e162c05981a643c94b37cb86d4b684edf6627eb5f8
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a0ea04e04a4ed62960479a522a73907e7c4ec5720198719272757cf11d82cc
+oid sha256:49cd8fda8f7a281f85d5d09c3e8424ac52d3919438cb726e0fce44bda3f867be
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36dab2fa0c5af06020db6b40cb2995fbc7676b0e56f8d703215aa07fb7e3eba5
+oid sha256:29b0e515fcc536506ad81be9b9fa7ea1daa4caf638cb33310c7e9127ad9b6486
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a49108293edbb6877a3e9ba0d52e802c533bf4a33edff9df48f4e84b4fa057
+oid sha256:ca2ad0660f4430a149f84300447ae0a59e68e8b51799a2e3848afe158aff8281
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.806708812713623,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010225994477962982,
+  "best_metric": 2.531360149383545,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.020451988955925964,
   "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": 6.104,
       "eval_steps_per_second": 1.526,
       "step": 25
+    },
+    {
+      "epoch": 0.010635034257081502,
+      "grad_norm": 1.088171124458313,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 2.5672,
+      "step": 26
+    },
+    {
+      "epoch": 0.01104407403620002,
+      "grad_norm": 1.2368388175964355,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 2.8143,
+      "step": 27
+    },
+    {
+      "epoch": 0.01145311381531854,
+      "grad_norm": 1.1344971656799316,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 2.7588,
+      "step": 28
+    },
+    {
+      "epoch": 0.011862153594437059,
+      "grad_norm": 1.1049875020980835,
+      "learning_rate": 1.45e-05,
+      "loss": 2.5798,
+      "step": 29
+    },
+    {
+      "epoch": 0.012271193373555579,
+      "grad_norm": 1.0875412225723267,
+      "learning_rate": 1.5e-05,
+      "loss": 2.7744,
+      "step": 30
+    },
+    {
+      "epoch": 0.012680233152674098,
+      "grad_norm": 0.8803157806396484,
+      "learning_rate": 1.55e-05,
+      "loss": 2.5996,
+      "step": 31
+    },
+    {
+      "epoch": 0.013089272931792616,
+      "grad_norm": 0.9814906716346741,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.7021,
+      "step": 32
+    },
+    {
+      "epoch": 0.013498312710911136,
+      "grad_norm": 0.8770394325256348,
+      "learning_rate": 1.65e-05,
+      "loss": 2.5973,
+      "step": 33
+    },
+    {
+      "epoch": 0.013907352490029655,
+      "grad_norm": 0.8788903951644897,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 2.6578,
+      "step": 34
+    },
+    {
+      "epoch": 0.014316392269148175,
+      "grad_norm": 0.9856432676315308,
+      "learning_rate": 1.75e-05,
+      "loss": 2.7158,
+      "step": 35
+    },
+    {
+      "epoch": 0.014725432048266695,
+      "grad_norm": 0.9377185106277466,
+      "learning_rate": 1.8e-05,
+      "loss": 2.5759,
+      "step": 36
+    },
+    {
+      "epoch": 0.015134471827385212,
+      "grad_norm": 0.8886085748672485,
+      "learning_rate": 1.85e-05,
+      "loss": 2.4104,
+      "step": 37
+    },
+    {
+      "epoch": 0.015543511606503732,
+      "grad_norm": 0.953931450843811,
+      "learning_rate": 1.9e-05,
+      "loss": 2.6482,
+      "step": 38
+    },
+    {
+      "epoch": 0.01595255138562225,
+      "grad_norm": 0.8806855082511902,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 2.6219,
+      "step": 39
+    },
+    {
+      "epoch": 0.01636159116474077,
+      "grad_norm": 0.9649810194969177,
+      "learning_rate": 2e-05,
+      "loss": 2.7425,
+      "step": 40
+    },
+    {
+      "epoch": 0.01677063094385929,
+      "grad_norm": 0.9306110143661499,
+      "learning_rate": 2.05e-05,
+      "loss": 2.563,
+      "step": 41
+    },
+    {
+      "epoch": 0.01717967072297781,
+      "grad_norm": 0.8921884298324585,
+      "learning_rate": 2.1e-05,
+      "loss": 2.3917,
+      "step": 42
+    },
+    {
+      "epoch": 0.01758871050209633,
+      "grad_norm": 0.9402901530265808,
+      "learning_rate": 2.15e-05,
+      "loss": 2.614,
+      "step": 43
+    },
+    {
+      "epoch": 0.01799775028121485,
+      "grad_norm": 1.015141487121582,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 2.6101,
+      "step": 44
+    },
+    {
+      "epoch": 0.018406790060333366,
+      "grad_norm": 0.9544494152069092,
+      "learning_rate": 2.25e-05,
+      "loss": 2.4646,
+      "step": 45
+    },
+    {
+      "epoch": 0.018815829839451886,
+      "grad_norm": 0.959822416305542,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 2.606,
+      "step": 46
+    },
+    {
+      "epoch": 0.019224869618570405,
+      "grad_norm": 0.8654732704162598,
+      "learning_rate": 2.35e-05,
+      "loss": 2.5762,
+      "step": 47
+    },
+    {
+      "epoch": 0.019633909397688925,
+      "grad_norm": 0.8668029308319092,
+      "learning_rate": 2.4e-05,
+      "loss": 2.3706,
+      "step": 48
+    },
+    {
+      "epoch": 0.020042949176807445,
+      "grad_norm": 0.8058049082756042,
+      "learning_rate": 2.45e-05,
+      "loss": 2.5585,
+      "step": 49
+    },
+    {
+      "epoch": 0.020451988955925964,
+      "grad_norm": 0.6671596765518188,
+      "learning_rate": 2.5e-05,
+      "loss": 2.4116,
+      "step": 50
+    },
+    {
+      "epoch": 0.020451988955925964,
+      "eval_loss": 2.531360149383545,
+      "eval_runtime": 1349.1339,
+      "eval_samples_per_second": 6.104,
+      "eval_steps_per_second": 1.526,
+      "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": 1.5273699984801792e+17,
+  "total_flos": 3.0547399969603584e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null