Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a64ebfa8894739079f7c63b2f8cf8d67d7be766fe621192d76685cf65ad7c2
+oid sha256:39130af13222a6991f6ec78afa2a53e4d5b39afee482e0c4d525fe3193b72b0a
 size 113284112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b835efa726f5bf461fd79842c9fb84ff1c50425cfb3d9075338e938c78fbe5fb
+oid sha256:56729d388c04c3a6dbf7db10548aae245eca427afc79f930a371c0d19fbd1ad5
 size 57846868

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81db36b0a25f22f0d1ac7a8c735b36ac1ce658c78a8615ddf68bdeb80312c7b9
+oid sha256:5371d0acb92050c8272e5f0dc5fb9a10d68c668296aaec43a303834e7454349a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802645150f3e2b6e2077b6a42609ed4e92e9d829b58b6711b4a505ffe83a56a5
+oid sha256:04123ec3dabfb5da3b42d11f8fadb887467f7e5f5fb71eca92df453137021786
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51614e00633f8bc18d2c3666a48049bc79b89bc5dcf9ccb96d97694fd9b01587
+oid sha256:a8605bb5e6614be39e5d7a49ad92de20b617a78ff3372ecddc3cef5e7278fad7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d01fbea0b690e0adbd4b8f94bc8598acd3adce0ba73d5d8c8f90447fa89d7008
+oid sha256:9559f3cdf59cf14c07c9c442d8890c498b1cf9d9371646c1cb80b268565be33c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.616195797920227,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9090909090909091,
+  "best_metric": 0.7014458775520325,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.8181818181818183,
   "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": 83.29,
       "eval_steps_per_second": 10.805,
       "step": 25
+    },
+    {
+      "epoch": 0.9454545454545454,
+      "grad_norm": 1.3311731815338135,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.5433,
+      "step": 26
+    },
+    {
+      "epoch": 0.9818181818181818,
+      "grad_norm": 1.3132495880126953,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 1.5142,
+      "step": 27
+    },
+    {
+      "epoch": 1.018181818181818,
+      "grad_norm": 1.8900108337402344,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 2.1575,
+      "step": 28
+    },
+    {
+      "epoch": 1.0545454545454545,
+      "grad_norm": 1.3511183261871338,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 1.4059,
+      "step": 29
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 1.3030800819396973,
+      "learning_rate": 5e-05,
+      "loss": 1.2821,
+      "step": 30
+    },
+    {
+      "epoch": 1.1272727272727272,
+      "grad_norm": 1.3078441619873047,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 1.2639,
+      "step": 31
+    },
+    {
+      "epoch": 1.1636363636363636,
+      "grad_norm": 1.2813204526901245,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.1609,
+      "step": 32
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.2373963594436646,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.9931,
+      "step": 33
+    },
+    {
+      "epoch": 1.2363636363636363,
+      "grad_norm": 1.1406350135803223,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.0044,
+      "step": 34
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 1.2524733543395996,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0676,
+      "step": 35
+    },
+    {
+      "epoch": 1.309090909090909,
+      "grad_norm": 1.296142816543579,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.9606,
+      "step": 36
+    },
+    {
+      "epoch": 1.3454545454545455,
+      "grad_norm": 1.1478257179260254,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.7671,
+      "step": 37
+    },
+    {
+      "epoch": 1.3818181818181818,
+      "grad_norm": 1.094861388206482,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.8396,
+      "step": 38
+    },
+    {
+      "epoch": 1.4181818181818182,
+      "grad_norm": 1.2488963603973389,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.796,
+      "step": 39
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 1.0716795921325684,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7188,
+      "step": 40
+    },
+    {
+      "epoch": 1.490909090909091,
+      "grad_norm": 0.9967021346092224,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.6436,
+      "step": 41
+    },
+    {
+      "epoch": 1.5272727272727273,
+      "grad_norm": 1.1100887060165405,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7328,
+      "step": 42
+    },
+    {
+      "epoch": 1.5636363636363635,
+      "grad_norm": 1.1688659191131592,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.7326,
+      "step": 43
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.1410752534866333,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.7059,
+      "step": 44
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 1.242427110671997,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7424,
+      "step": 45
+    },
+    {
+      "epoch": 1.6727272727272728,
+      "grad_norm": 1.0488547086715698,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.6415,
+      "step": 46
+    },
+    {
+      "epoch": 1.709090909090909,
+      "grad_norm": 1.1210660934448242,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.6584,
+      "step": 47
+    },
+    {
+      "epoch": 1.7454545454545456,
+      "grad_norm": 1.1600866317749023,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.6407,
+      "step": 48
+    },
+    {
+      "epoch": 1.7818181818181817,
+      "grad_norm": 1.138494610786438,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.6473,
+      "step": 49
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 1.110583782196045,
+      "learning_rate": 0.0,
+      "loss": 0.6157,
+      "step": 50
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "eval_loss": 0.7014458775520325,
+      "eval_runtime": 2.2203,
+      "eval_samples_per_second": 83.324,
+      "eval_steps_per_second": 10.81,
+      "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": 5.27587608625152e+16,
+  "total_flos": 1.055175217250304e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null