Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b15b326cb78892d61af8d9764498cb6866adcf111c8486ffd349e74a946efb
+oid sha256:bdf8524b5374c7eec8c83ac38caa6b1b597a75fced18c9010a6342b0f2a8914b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a6b5d604e20c10bf5221c1ebc0e77f9a713b5e9492ce9c6a6d008a76e15b01
+oid sha256:7450b1b261e1462102989d6f8ddbacd47ff74d4867892c4c94e42c4e5e36fb4d
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a8fc064198f1c14cdf4fa22ca1658a00547ed6843a3445f83c4e43b404fe9e
+oid sha256:5bd3be1f09897dd6d566802505b3ab021e7e037994ae8c69c90fac9f71e27d86
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5709c7fc026e80f7be63670cd83f6d9c9c52203ebc2cc554bb378ad0eeb1046d
+oid sha256:41a8c9204a09a1732ed5766e6a5ed99c079809b9a951ac9497b7f6a0a2e6034e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565f0a8d1cc0e644d4d15e406a6b126b01a03973c958914305384bbf91c02efa
+oid sha256:6eb8c6590ddb6adfd2ab2b4ebaff3de42be8c16f185e319b25a25925b273f2fd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eca008db5cff221007cac7cdc48cbe40d0cfa229b281b90afa8eec08756c53d
+oid sha256:e4f6aef10de5491f53c3fa124cb90ba2683537847b2ff7a4e5161d6c8f51f7c4
 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": 1.4920990467071533,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6191950464396285,
+  "best_metric": 1.14642333984375,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.238390092879257,
   "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": 16.642,
       "eval_steps_per_second": 2.08,
       "step": 25
+    },
+    {
+      "epoch": 0.6439628482972136,
+      "grad_norm": 1.4375908374786377,
+      "learning_rate": 5e-05,
+      "loss": 1.3052,
+      "step": 26
+    },
+    {
+      "epoch": 0.6687306501547987,
+      "grad_norm": 1.6213889122009277,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5831,
+      "step": 27
+    },
+    {
+      "epoch": 0.6934984520123839,
+      "grad_norm": 1.6705217361450195,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3199,
+      "step": 28
+    },
+    {
+      "epoch": 0.718266253869969,
+      "grad_norm": 1.8949580192565918,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.3975,
+      "step": 29
+    },
+    {
+      "epoch": 0.7430340557275542,
+      "grad_norm": 2.545088291168213,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6941,
+      "step": 30
+    },
+    {
+      "epoch": 0.7678018575851393,
+      "grad_norm": 1.6592068672180176,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2374,
+      "step": 31
+    },
+    {
+      "epoch": 0.7925696594427245,
+      "grad_norm": 1.3235689401626587,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2425,
+      "step": 32
+    },
+    {
+      "epoch": 0.8173374613003096,
+      "grad_norm": 1.3531960248947144,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0226,
+      "step": 33
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 1.3992116451263428,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.009,
+      "step": 34
+    },
+    {
+      "epoch": 0.8668730650154799,
+      "grad_norm": 1.4692587852478027,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.2067,
+      "step": 35
+    },
+    {
+      "epoch": 0.891640866873065,
+      "grad_norm": 1.4496288299560547,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.065,
+      "step": 36
+    },
+    {
+      "epoch": 0.9164086687306502,
+      "grad_norm": 1.6986883878707886,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.3435,
+      "step": 37
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 1.7336461544036865,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0844,
+      "step": 38
+    },
+    {
+      "epoch": 0.9659442724458205,
+      "grad_norm": 2.353813886642456,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.4309,
+      "step": 39
+    },
+    {
+      "epoch": 0.9907120743034056,
+      "grad_norm": 2.4746670722961426,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4469,
+      "step": 40
+    },
+    {
+      "epoch": 1.0154798761609907,
+      "grad_norm": 2.405529499053955,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.8413,
+      "step": 41
+    },
+    {
+      "epoch": 1.0402476780185759,
+      "grad_norm": 1.1980689764022827,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9997,
+      "step": 42
+    },
+    {
+      "epoch": 1.065015479876161,
+      "grad_norm": 1.176184058189392,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9265,
+      "step": 43
+    },
+    {
+      "epoch": 1.089783281733746,
+      "grad_norm": 1.2744024991989136,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8837,
+      "step": 44
+    },
+    {
+      "epoch": 1.1145510835913313,
+      "grad_norm": 1.2227189540863037,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8724,
+      "step": 45
+    },
+    {
+      "epoch": 1.1393188854489165,
+      "grad_norm": 1.2973285913467407,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8306,
+      "step": 46
+    },
+    {
+      "epoch": 1.1640866873065017,
+      "grad_norm": 1.4821503162384033,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0709,
+      "step": 47
+    },
+    {
+      "epoch": 1.1888544891640866,
+      "grad_norm": 1.5012022256851196,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9295,
+      "step": 48
+    },
+    {
+      "epoch": 1.2136222910216719,
+      "grad_norm": 1.8078975677490234,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0632,
+      "step": 49
+    },
+    {
+      "epoch": 1.238390092879257,
+      "grad_norm": 2.235991954803467,
+      "learning_rate": 0.0,
+      "loss": 1.1633,
+      "step": 50
+    },
+    {
+      "epoch": 1.238390092879257,
+      "eval_loss": 1.14642333984375,
+      "eval_runtime": 15.6309,
+      "eval_samples_per_second": 17.401,
+      "eval_steps_per_second": 2.175,
+      "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