Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e2cf5e691a93faf4cc82944904d5afd56e843e5aafdcab8766089c7bcb8802
+oid sha256:c436b41dd5ec24c01d2e51532f241b7bc0fe70896d3184d31a89d7533676e64c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be39beba465b279fcddc5e5867309467d7cd3292767111cfe4abe2704b7e1c86
+oid sha256:be661d80dbe1d1c2be0effc899ec5ae3c15b7564316cba41d9da03792b4aa469
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf3237885fe379174253442cfddde58af957477ddc024acd1f23db7cac1fb76
+oid sha256:78254aecc1cb474272df6e2df8e5a87da025e1f5fc32d59beb42c38e8e646537
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31244a54444acfa2cb79b2989fa1eadd9300faf09fd29e2cce4db5ef2bbd5ba9
+oid sha256:8b375ee3bf798dadc585d676cb519f0380a4fc94483dd5cecb34d79746675b20
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6678efb1d91d4b5f962c86ca8fd2ba7bd648984bcd68a68653eaf1e47e6e7fd0
+oid sha256:27caa134403786386ec27f9441953387d2d46573059bd24bd4239a4cd5e9b2fd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df056a32208e475ca72659f2d557a28eca2d4a7c9de32a5bdeefeb39ab01ecd6
+oid sha256:ca3d01a6bf3606d93f8e97980f2797167672ff81e1803b1ce18ceb9bc1e8124e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.18756365776062,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.34904013961605584,
+  "best_metric": 2.1088995933532715,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6980802792321117,
   "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": 33.14,
       "eval_steps_per_second": 4.185,
       "step": 25
+    },
+    {
+      "epoch": 0.36300174520069806,
+      "grad_norm": 1.2121622562408447,
+      "learning_rate": 5e-05,
+      "loss": 2.3337,
+      "step": 26
+    },
+    {
+      "epoch": 0.3769633507853403,
+      "grad_norm": 1.252693772315979,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.3411,
+      "step": 27
+    },
+    {
+      "epoch": 0.39092495636998253,
+      "grad_norm": 1.2453138828277588,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.1837,
+      "step": 28
+    },
+    {
+      "epoch": 0.4048865619546248,
+      "grad_norm": 1.2619675397872925,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.4556,
+      "step": 29
+    },
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 1.2121081352233887,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.2601,
+      "step": 30
+    },
+    {
+      "epoch": 0.4328097731239092,
+      "grad_norm": 1.2065447568893433,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1049,
+      "step": 31
+    },
+    {
+      "epoch": 0.4467713787085515,
+      "grad_norm": 1.3605051040649414,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.3307,
+      "step": 32
+    },
+    {
+      "epoch": 0.4607329842931937,
+      "grad_norm": 1.3275235891342163,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9696,
+      "step": 33
+    },
+    {
+      "epoch": 0.47469458987783597,
+      "grad_norm": 1.4929739236831665,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1102,
+      "step": 34
+    },
+    {
+      "epoch": 0.4886561954624782,
+      "grad_norm": 1.5965300798416138,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.9822,
+      "step": 35
+    },
+    {
+      "epoch": 0.5026178010471204,
+      "grad_norm": 1.6006946563720703,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.0504,
+      "step": 36
+    },
+    {
+      "epoch": 0.5165794066317626,
+      "grad_norm": 1.8246269226074219,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.9678,
+      "step": 37
+    },
+    {
+      "epoch": 0.5305410122164049,
+      "grad_norm": 1.0196877717971802,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3278,
+      "step": 38
+    },
+    {
+      "epoch": 0.5445026178010471,
+      "grad_norm": 0.9331263303756714,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2347,
+      "step": 39
+    },
+    {
+      "epoch": 0.5584642233856894,
+      "grad_norm": 1.1264294385910034,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.1915,
+      "step": 40
+    },
+    {
+      "epoch": 0.5724258289703316,
+      "grad_norm": 1.0697758197784424,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.1187,
+      "step": 41
+    },
+    {
+      "epoch": 0.5863874345549738,
+      "grad_norm": 1.1378289461135864,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1259,
+      "step": 42
+    },
+    {
+      "epoch": 0.6003490401396161,
+      "grad_norm": 1.2001599073410034,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.1106,
+      "step": 43
+    },
+    {
+      "epoch": 0.6143106457242583,
+      "grad_norm": 1.2745617628097534,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0472,
+      "step": 44
+    },
+    {
+      "epoch": 0.6282722513089005,
+      "grad_norm": 1.2752476930618286,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.8658,
+      "step": 45
+    },
+    {
+      "epoch": 0.6422338568935427,
+      "grad_norm": 1.4296314716339111,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.0441,
+      "step": 46
+    },
+    {
+      "epoch": 0.6561954624781849,
+      "grad_norm": 1.4413177967071533,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.946,
+      "step": 47
+    },
+    {
+      "epoch": 0.6701570680628273,
+      "grad_norm": 1.5997071266174316,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.982,
+      "step": 48
+    },
+    {
+      "epoch": 0.6841186736474695,
+      "grad_norm": 1.6253526210784912,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.965,
+      "step": 49
+    },
+    {
+      "epoch": 0.6980802792321117,
+      "grad_norm": 2.0481815338134766,
+      "learning_rate": 0.0,
+      "loss": 1.9041,
+      "step": 50
+    },
+    {
+      "epoch": 0.6980802792321117,
+      "eval_loss": 2.1088995933532715,
+      "eval_runtime": 14.5721,
+      "eval_samples_per_second": 33.146,
+      "eval_steps_per_second": 4.186,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null