Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fdfea562ed117b0f0a6aa09a8e712053815dada64078fbd832a37bdb47c560b
+oid sha256:291214b969435121a62e3461d03aabd1cfd41b84bc7c9fb5141db351d94407bf
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01df707eee622d10af731286a4dc57b587f417970d63ab91d76b1fdd0f53b328
+oid sha256:a156e3b116157a78505e886ddea532f3a57f0f79d5b01551f3aa2e1537f62384
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92cc19839144006d0b1bea40e4e77ad8c6ab443719d7516df07ef9aa91c64a5
+oid sha256:ea5dd64b4d8616ac34fb3a581d5e92a9ed7987aff3fecf823c4114c082bcfe43
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1938d50f46120f39e5abdfc90d7f40330c614d9ef81d9a3ae8c31100a60a599f
+oid sha256:d44d378579853882a0105739b82bd123631a7e5020a7d39951af6675c75532d1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6431e099fdfb276beb8ad5dd3a41c09c98fd42633a3d7e82fbdc46bced3c4b1f
+oid sha256:39a1793c5dff9996e3ac3e64dc6e3a51255a4a7301045b7ad42ea83a5deb9b88
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c2b71659a629d3021beb22a82451fe5e5a28771130d28ebf768b27f962daabc
+oid sha256:c15a460c925470a7de090742206e2b41d8d4fea6bce460cbbc049627c6365104
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
+oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3130438327789307,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.1541218637992832,
+  "best_metric": 1.3074243068695068,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 1.7275985663082438,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 10.471,
       "eval_steps_per_second": 2.723,
       "step": 50
+    },
+    {
+      "epoch": 1.1770609318996417,
+      "grad_norm": 46.695682525634766,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 30.7516,
+      "step": 51
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 51.038291931152344,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 29.5743,
+      "step": 52
+    },
+    {
+      "epoch": 1.2229390681003585,
+      "grad_norm": 56.04834747314453,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 28.3398,
+      "step": 53
+    },
+    {
+      "epoch": 1.2458781362007167,
+      "grad_norm": 58.13565444946289,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 25.4231,
+      "step": 54
+    },
+    {
+      "epoch": 1.2688172043010753,
+      "grad_norm": 57.815208435058594,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 38.2288,
+      "step": 55
+    },
+    {
+      "epoch": 1.2917562724014338,
+      "grad_norm": 60.06364440917969,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 37.1063,
+      "step": 56
+    },
+    {
+      "epoch": 1.314695340501792,
+      "grad_norm": 54.02146530151367,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 35.0785,
+      "step": 57
+    },
+    {
+      "epoch": 1.3376344086021505,
+      "grad_norm": 50.7199592590332,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 32.4164,
+      "step": 58
+    },
+    {
+      "epoch": 1.360573476702509,
+      "grad_norm": 49.94532012939453,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 31.3014,
+      "step": 59
+    },
+    {
+      "epoch": 1.3835125448028673,
+      "grad_norm": 53.36236572265625,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 32.4417,
+      "step": 60
+    },
+    {
+      "epoch": 1.4064516129032258,
+      "grad_norm": 52.96565246582031,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 31.0806,
+      "step": 61
+    },
+    {
+      "epoch": 1.4293906810035844,
+      "grad_norm": 52.68083572387695,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 30.1467,
+      "step": 62
+    },
+    {
+      "epoch": 1.4523297491039426,
+      "grad_norm": 55.56118392944336,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 29.6131,
+      "step": 63
+    },
+    {
+      "epoch": 1.4752688172043011,
+      "grad_norm": 60.30636215209961,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 30.151,
+      "step": 64
+    },
+    {
+      "epoch": 1.4982078853046594,
+      "grad_norm": 54.61465835571289,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 26.281,
+      "step": 65
+    },
+    {
+      "epoch": 1.521146953405018,
+      "grad_norm": 48.4765510559082,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 36.4622,
+      "step": 66
+    },
+    {
+      "epoch": 1.5440860215053762,
+      "grad_norm": 54.45204162597656,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 36.89,
+      "step": 67
+    },
+    {
+      "epoch": 1.5670250896057347,
+      "grad_norm": 52.27381134033203,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 32.998,
+      "step": 68
+    },
+    {
+      "epoch": 1.5899641577060932,
+      "grad_norm": 54.354190826416016,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 31.7506,
+      "step": 69
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 55.66099548339844,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 33.7973,
+      "step": 70
+    },
+    {
+      "epoch": 1.63584229390681,
+      "grad_norm": 57.908321380615234,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 32.1609,
+      "step": 71
+    },
+    {
+      "epoch": 1.6587813620071685,
+      "grad_norm": 54.846675872802734,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 30.6282,
+      "step": 72
+    },
+    {
+      "epoch": 1.6817204301075268,
+      "grad_norm": 56.08439636230469,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 29.2229,
+      "step": 73
+    },
+    {
+      "epoch": 1.7046594982078853,
+      "grad_norm": 61.20675277709961,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 29.949,
+      "step": 74
+    },
+    {
+      "epoch": 1.7275985663082438,
+      "grad_norm": 59.61654281616211,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 25.5925,
+      "step": 75
+    },
+    {
+      "epoch": 1.7275985663082438,
+      "eval_loss": 1.3074243068695068,
+      "eval_runtime": 4.7759,
+      "eval_samples_per_second": 10.469,
+      "eval_steps_per_second": 2.722,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.658021338284032e+17,
+  "total_flos": 8.487032007426048e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null