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:d6fe10c6bd14034f5ebec263f33d589c6fa919a77fa68a9259ee0b25cb4c8630
+oid sha256:e751efb06c8c38c7793472cef07e79e5269aa52b4f79d1863c1e8bd4abb94dca
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e36938a94dec7f4671c4b375056c4358403c7a00d45238a22b503d9146cae315
+oid sha256:ecfb02fc8b9d719bf485049c3731642d6a1dfe50ef74d79a85630efed5da059e
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80562815ddbf0236b590a0189474398ea3a4844d550008805c983686f8dc16fb
+oid sha256:dd79fb15a38b03644bfb87e9d7b2d05e78481bacf9dd7a268922e5206d130bc6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b753b8be015162e79009c5f2582bef10045bc9f63349168e06e741ec0ff13201
+oid sha256:0c34739530a0da6ba93b26c9ac75660ef37ca9ebf485a4ba52c47ddd8dd85bc3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:573f75b9b62124f2eb4991afb1da833afb51870f75a42fc25104ad07929f63c0
+oid sha256:8efd7e9d7bb2e06615d28d4ff7c917a6fb4911616cd2e820b335dd81789637a7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4593f0a3d1c65aa90acfb710bc989fb0f6980300b588fbe7c70347f6da36ee92
+oid sha256:3b50e4afef25f422f10ddbcef4a6a486a95dc4bf7be5cc573319ad59ba9486ae
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0199352105656616,
+  "epoch": 0.0398704211313232,
   "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": 145.912,
       "eval_steps_per_second": 18.254,
       "step": 25
+    },
+    {
+      "epoch": 0.020732618988288064,
+      "grad_norm": 1.758143424987793,
+      "learning_rate": 5e-05,
+      "loss": 2.3564,
+      "step": 26
+    },
+    {
+      "epoch": 0.02153002741091453,
+      "grad_norm": 1.8171120882034302,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.3386,
+      "step": 27
+    },
+    {
+      "epoch": 0.022327435833540993,
+      "grad_norm": 2.4620540142059326,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.2566,
+      "step": 28
+    },
+    {
+      "epoch": 0.023124844256167457,
+      "grad_norm": 2.1204512119293213,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.3241,
+      "step": 29
+    },
+    {
+      "epoch": 0.02392225267879392,
+      "grad_norm": 3.1958048343658447,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.2001,
+      "step": 30
+    },
+    {
+      "epoch": 0.024719661101420383,
+      "grad_norm": 3.4434661865234375,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1418,
+      "step": 31
+    },
+    {
+      "epoch": 0.025517069524046847,
+      "grad_norm": 3.5963659286499023,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.5206,
+      "step": 32
+    },
+    {
+      "epoch": 0.026314477946673312,
+      "grad_norm": 3.911703586578369,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9435,
+      "step": 33
+    },
+    {
+      "epoch": 0.027111886369299776,
+      "grad_norm": 4.419018745422363,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.6252,
+      "step": 34
+    },
+    {
+      "epoch": 0.02790929479192624,
+      "grad_norm": 3.8828225135803223,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6891,
+      "step": 35
+    },
+    {
+      "epoch": 0.028706703214552702,
+      "grad_norm": 5.121977806091309,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4323,
+      "step": 36
+    },
+    {
+      "epoch": 0.029504111637179167,
+      "grad_norm": 3.6891393661499023,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.7424,
+      "step": 37
+    },
+    {
+      "epoch": 0.03030152005980563,
+      "grad_norm": 1.6718828678131104,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2177,
+      "step": 38
+    },
+    {
+      "epoch": 0.031098928482432096,
+      "grad_norm": 1.5160930156707764,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2251,
+      "step": 39
+    },
+    {
+      "epoch": 0.03189633690505856,
+      "grad_norm": 1.7978293895721436,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.2484,
+      "step": 40
+    },
+    {
+      "epoch": 0.03269374532768502,
+      "grad_norm": 2.5029444694519043,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.3805,
+      "step": 41
+    },
+    {
+      "epoch": 0.03349115375031149,
+      "grad_norm": 3.7533793449401855,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1574,
+      "step": 42
+    },
+    {
+      "epoch": 0.03428856217293795,
+      "grad_norm": 5.509903907775879,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.4423,
+      "step": 43
+    },
+    {
+      "epoch": 0.03508597059556442,
+      "grad_norm": 3.371899127960205,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.3273,
+      "step": 44
+    },
+    {
+      "epoch": 0.03588337901819088,
+      "grad_norm": 4.512765884399414,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0492,
+      "step": 45
+    },
+    {
+      "epoch": 0.03668078744081734,
+      "grad_norm": 6.9926981925964355,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.8342,
+      "step": 46
+    },
+    {
+      "epoch": 0.03747819586344381,
+      "grad_norm": 5.881093978881836,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.3712,
+      "step": 47
+    },
+    {
+      "epoch": 0.03827560428607027,
+      "grad_norm": 3.9496421813964844,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.7801,
+      "step": 48
+    },
+    {
+      "epoch": 0.03907301270869674,
+      "grad_norm": 6.15703010559082,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.0498,
+      "step": 49
+    },
+    {
+      "epoch": 0.0398704211313232,
+      "grad_norm": 5.4105987548828125,
+      "learning_rate": 0.0,
+      "loss": 1.9125,
+      "step": 50
+    },
+    {
+      "epoch": 0.0398704211313232,
+      "eval_loss": NaN,
+      "eval_runtime": 57.9087,
+      "eval_samples_per_second": 145.902,
+      "eval_steps_per_second": 18.253,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null