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:c636be3299000ca6e3d7f6f3090e0f187a3175ff6e41c1d03c0dd4a6c75901eb
+oid sha256:87786da68bfd89a9c51ca144e2dbe8720d884cc153aa4af97a688dc7a5ec5f43
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3de956a8eae8ffd641b07396e6862adfb2566620c360c61a744a837def30eaab
+oid sha256:e63c6a2b6fb71565e2a88e78ab5427068150f85fdd018673c516aaacdc0d1f09
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c94b61ccdb23baa6d72baf6e87d741fed7d6973708ab15badbea487510d215
+oid sha256:cc0069e110610e59528c04803fe0f8f18029279562d95bd0b55b5697d7ca97dd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf04cc54e4ed9348165301bf9324784db23491502412c8597c066c796a7ae12
+oid sha256:7ef83491accae5e9c5c3447eee76089e5ec99e1b1aefde6e4c2bf51aac0c1c2e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1608e3e51f6b0ef5a97a99f62b93246f27c931fb5d28ee9357293eca0e2a695d
+oid sha256:bffbc0955e9a48b707189d482ed198f2ae16da4ea84743c50bdbe5ddf46e2a82
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15020c03d63b6bc19821c95d06af9abd62b1d94874457f7ac8bc37753238d2b9
+oid sha256:63abb24e7d50c1663315e87847a4330d52b93a2978a52252516beb869fbc0847
 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": 0.8090626001358032,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.24879489970455607,
+  "best_metric": 0.7902164459228516,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.37319234955683406,
   "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": 48.761,
       "eval_steps_per_second": 12.678,
       "step": 50
+    },
+    {
+      "epoch": 0.2537707976986472,
+      "grad_norm": 0.12577220797538757,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 1.0566,
+      "step": 51
+    },
+    {
+      "epoch": 0.2587466956927383,
+      "grad_norm": 0.16750161349773407,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 0.8238,
+      "step": 52
+    },
+    {
+      "epoch": 0.26372259368682943,
+      "grad_norm": 0.17324009537696838,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 0.8423,
+      "step": 53
+    },
+    {
+      "epoch": 0.2686984916809205,
+      "grad_norm": 0.17715862393379211,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 0.8862,
+      "step": 54
+    },
+    {
+      "epoch": 0.2736743896750117,
+      "grad_norm": 0.17103923857212067,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 0.8712,
+      "step": 55
+    },
+    {
+      "epoch": 0.27865028766910277,
+      "grad_norm": 0.16644009947776794,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 0.8458,
+      "step": 56
+    },
+    {
+      "epoch": 0.2836261856631939,
+      "grad_norm": 0.17309409379959106,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 0.8803,
+      "step": 57
+    },
+    {
+      "epoch": 0.288602083657285,
+      "grad_norm": 0.1786348819732666,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 0.8838,
+      "step": 58
+    },
+    {
+      "epoch": 0.29357798165137616,
+      "grad_norm": 0.19110921025276184,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 0.9268,
+      "step": 59
+    },
+    {
+      "epoch": 0.29855387964546726,
+      "grad_norm": 0.198200523853302,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 0.9084,
+      "step": 60
+    },
+    {
+      "epoch": 0.3035297776395584,
+      "grad_norm": 0.22449031472206116,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 0.8733,
+      "step": 61
+    },
+    {
+      "epoch": 0.3085056756336495,
+      "grad_norm": 0.26478344202041626,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 0.8939,
+      "step": 62
+    },
+    {
+      "epoch": 0.31348157362774065,
+      "grad_norm": 0.13545911014080048,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 1.0545,
+      "step": 63
+    },
+    {
+      "epoch": 0.31845747162183174,
+      "grad_norm": 0.1377517431974411,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 0.8699,
+      "step": 64
+    },
+    {
+      "epoch": 0.3234333696159229,
+      "grad_norm": 0.1665552407503128,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 0.8334,
+      "step": 65
+    },
+    {
+      "epoch": 0.328409267610014,
+      "grad_norm": 0.15971739590168,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 0.8595,
+      "step": 66
+    },
+    {
+      "epoch": 0.33338516560410514,
+      "grad_norm": 0.1528182327747345,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 0.8277,
+      "step": 67
+    },
+    {
+      "epoch": 0.33836106359819623,
+      "grad_norm": 0.1469763070344925,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 0.8526,
+      "step": 68
+    },
+    {
+      "epoch": 0.3433369615922874,
+      "grad_norm": 0.14643485844135284,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 0.8201,
+      "step": 69
+    },
+    {
+      "epoch": 0.3483128595863785,
+      "grad_norm": 0.1613270789384842,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 0.8523,
+      "step": 70
+    },
+    {
+      "epoch": 0.3532887575804696,
+      "grad_norm": 0.17931152880191803,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 0.8531,
+      "step": 71
+    },
+    {
+      "epoch": 0.3582646555745607,
+      "grad_norm": 0.1984926164150238,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8898,
+      "step": 72
+    },
+    {
+      "epoch": 0.36324055356865187,
+      "grad_norm": 0.20060153305530548,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 0.8438,
+      "step": 73
+    },
+    {
+      "epoch": 0.36821645156274296,
+      "grad_norm": 0.24903373420238495,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 0.8631,
+      "step": 74
+    },
+    {
+      "epoch": 0.37319234955683406,
+      "grad_norm": 0.31300994753837585,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 0.8392,
+      "step": 75
+    },
+    {
+      "epoch": 0.37319234955683406,
+      "eval_loss": 0.7902164459228516,
+      "eval_runtime": 1.0566,
+      "eval_samples_per_second": 47.321,
+      "eval_steps_per_second": 12.304,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.33416392081408e+16,
+  "total_flos": 1.250124588122112e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null