Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b5a839717e632b98a5deea209c7f05ac50be1faa8678d07fa15be0080f38be
+oid sha256:61dceeb9ad0bf8554c33194f89a946e397171d104329660baaf9ca09e94d7f9c
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bda194d33c8b026979c899e3051ceef683b1aa7dff3323952c31b0c9b30c5b6
+oid sha256:2d562bbffd8890f1265516a7b6b1b5e545fca254f2a4aaa638cc76cce659e7f0
 size 1049049122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2724d67dcfbf17f12eb686e9f79e15c2fb9fe55f5dfd739ca16b8779f72fa479
+oid sha256:87b892a8040c088a85e7d863814550adc99c84464e5669cb331549ebb8c161d6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb3884d8c80b0758d3ee8f07c2322e773532d369eee4d6dc78249634fd59f99
+oid sha256:44945f02fa73533cb50937afdc02028f18d3c32f216b401c9b7327e931deae58
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:376451bfa7941856503f8e49ae514625e93096b95f7999406dfa32045a8c2ebc
+oid sha256:16bb4e7459d64be9aa10e66d82be1148a1b993c6c3e2166609b9a6a5fe0ec63c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7ccfc5adfca83316ccf632cdb605a72669e7255d81543f480bf7ec283b87ee6
+oid sha256:b65fee72b101786899fa145beda8405a33b25e3819e3ffce8f217de876620e73
 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": 1.9849716424942017,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.2282282282282282,
+  "best_metric": 1.975742220878601,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.4564564564564564,
   "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": 16.112,
       "eval_steps_per_second": 2.071,
       "step": 25
+    },
+    {
+      "epoch": 1.2762762762762763,
+      "grad_norm": 1.8273707628250122,
+      "learning_rate": 5e-05,
+      "loss": 31.9574,
+      "step": 26
+    },
+    {
+      "epoch": 1.3243243243243243,
+      "grad_norm": 0.3835039436817169,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 30.7649,
+      "step": 27
+    },
+    {
+      "epoch": 1.3723723723723724,
+      "grad_norm": 0.4291238486766815,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 30.7455,
+      "step": 28
+    },
+    {
+      "epoch": 1.4204204204204205,
+      "grad_norm": 0.8780869841575623,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 32.1305,
+      "step": 29
+    },
+    {
+      "epoch": 1.4684684684684686,
+      "grad_norm": 0.8173553347587585,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 32.4201,
+      "step": 30
+    },
+    {
+      "epoch": 1.5165165165165164,
+      "grad_norm": 1.8756839036941528,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 31.9964,
+      "step": 31
+    },
+    {
+      "epoch": 1.5645645645645647,
+      "grad_norm": 0.5796070694923401,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 31.4211,
+      "step": 32
+    },
+    {
+      "epoch": 1.6126126126126126,
+      "grad_norm": 0.5456942319869995,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 30.4474,
+      "step": 33
+    },
+    {
+      "epoch": 1.6606606606606606,
+      "grad_norm": 0.5846412777900696,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 32.8379,
+      "step": 34
+    },
+    {
+      "epoch": 1.7087087087087087,
+      "grad_norm": 0.9131438136100769,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 33.014,
+      "step": 35
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 1.9769388437271118,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 31.248,
+      "step": 36
+    },
+    {
+      "epoch": 1.8048048048048049,
+      "grad_norm": 1.053635835647583,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 31.7611,
+      "step": 37
+    },
+    {
+      "epoch": 1.8528528528528527,
+      "grad_norm": 0.49638527631759644,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 32.2847,
+      "step": 38
+    },
+    {
+      "epoch": 1.900900900900901,
+      "grad_norm": 0.571926474571228,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 32.4141,
+      "step": 39
+    },
+    {
+      "epoch": 1.9489489489489489,
+      "grad_norm": 0.9473947286605835,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 32.4951,
+      "step": 40
+    },
+    {
+      "epoch": 2.024024024024024,
+      "grad_norm": 2.7117865085601807,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 31.7703,
+      "step": 41
+    },
+    {
+      "epoch": 2.0720720720720722,
+      "grad_norm": 0.4527989625930786,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 30.8804,
+      "step": 42
+    },
+    {
+      "epoch": 2.12012012012012,
+      "grad_norm": 0.4707128405570984,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 30.7912,
+      "step": 43
+    },
+    {
+      "epoch": 2.1681681681681684,
+      "grad_norm": 0.5620436668395996,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 31.8568,
+      "step": 44
+    },
+    {
+      "epoch": 2.2162162162162162,
+      "grad_norm": 0.8135024905204773,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 32.5255,
+      "step": 45
+    },
+    {
+      "epoch": 2.264264264264264,
+      "grad_norm": 2.222813606262207,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 31.1272,
+      "step": 46
+    },
+    {
+      "epoch": 2.3123123123123124,
+      "grad_norm": 0.4300619661808014,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 30.4856,
+      "step": 47
+    },
+    {
+      "epoch": 2.3603603603603602,
+      "grad_norm": 0.4539353549480438,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 30.6673,
+      "step": 48
+    },
+    {
+      "epoch": 2.4084084084084085,
+      "grad_norm": 0.5699998140335083,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 32.4255,
+      "step": 49
+    },
+    {
+      "epoch": 2.4564564564564564,
+      "grad_norm": 0.7823691368103027,
+      "learning_rate": 0.0,
+      "loss": 32.8661,
+      "step": 50
+    },
+    {
+      "epoch": 2.4564564564564564,
+      "eval_loss": 1.975742220878601,
+      "eval_runtime": 8.705,
+      "eval_samples_per_second": 16.083,
+      "eval_steps_per_second": 2.068,
+      "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": 6.479236587270963e+17,
+  "total_flos": 1.291397765695275e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null