Training in progress, step 1000, checkpoint

last-checkpoint/config.json

@@ -3,12 +3,12 @@
   "architectures": [
     "EsmForMaskedLM"
   ],
-  "attention_probs_dropout_prob": 0.0,
+  "attention_probs_dropout_prob": 0.01,
   "classifier_dropout": null,
   "emb_layer_norm_before": false,
   "esmfold_config": null,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
+  "hidden_dropout_prob": 0.01,
   "hidden_size": 480,
   "initializer_range": 0.02,
   "intermediate_size": 1920,

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83ce41a972129fb0b1551fb265aaeb45dcb8ef48ed776e2a9693ee89609dc74c
+oid sha256:54523ee02a2389771e25d39b96df920a04fddbc3f888f4e4a1dc10c14a900999
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd3a95f8d68a6d3fb84e9ede2ee7c143d1c5afcd1d769a243d8ca98d8f33aa79
+oid sha256:f9c915286f9878c2b1a2926e419498689b5e3e4a19b9adea6de4edafe20fa82d
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef9e4df5ee72c5c3f44486d5dca78bea54cda14da3592af33eedfde3caef4154
-size 15006
+oid sha256:61a36eda00bdae5afbc5bdeebfcbdace8a0365966fa57c020bed29406600ec49
+size 14942

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ca222bf68a3564a804857106a49feb87b18dba9a0be2082fc90028354b2ec2
+oid sha256:a1c11d4e32c92ddc1610815e78968750931b353aa09e9bb0384d11e35312cefd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,138 +1,19 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.335782247380465,
+  "epoch": 0.24087679152113695,
   "eval_steps": 500,
-  "global_step": 18000,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.24087679152113695,
-      "grad_norm": 0.5820891857147217,
+      "grad_norm": 0.5082331299781799,
       "learning_rate": 0.000991969806472336,
-      "loss": 1.5141,
+      "loss": 1.4852,
       "step": 1000
-    },
-    {
-      "epoch": 0.4817535830422739,
-      "grad_norm": 0.4833473861217499,
-      "learning_rate": 0.0009839396129446719,
-      "loss": 1.3712,
-      "step": 2000
-    },
-    {
-      "epoch": 0.7226303745634108,
-      "grad_norm": 0.49527350068092346,
-      "learning_rate": 0.0009759094194170079,
-      "loss": 1.3169,
-      "step": 3000
-    },
-    {
-      "epoch": 0.9635071660845478,
-      "grad_norm": 0.5308498740196228,
-      "learning_rate": 0.000967879225889344,
-      "loss": 1.2857,
-      "step": 4000
-    },
-    {
-      "epoch": 1.2043839576056847,
-      "grad_norm": 0.46151238679885864,
-      "learning_rate": 0.00095984903236168,
-      "loss": 1.2532,
-      "step": 5000
-    },
-    {
-      "epoch": 1.4452607491268217,
-      "grad_norm": 0.4826602339744568,
-      "learning_rate": 0.0009518188388340159,
-      "loss": 1.2336,
-      "step": 6000
-    },
-    {
-      "epoch": 1.6861375406479586,
-      "grad_norm": 0.5108029246330261,
-      "learning_rate": 0.0009437886453063518,
-      "loss": 1.2128,
-      "step": 7000
-    },
-    {
-      "epoch": 1.9270143321690956,
-      "grad_norm": 0.4216555655002594,
-      "learning_rate": 0.0009357584517786879,
-      "loss": 1.1934,
-      "step": 8000
-    },
-    {
-      "epoch": 2.1678911236902323,
-      "grad_norm": 0.5326149463653564,
-      "learning_rate": 0.0009277282582510239,
-      "loss": 1.176,
-      "step": 9000
-    },
-    {
-      "epoch": 2.4087679152113695,
-      "grad_norm": 0.4811168313026428,
-      "learning_rate": 0.0009196980647233599,
-      "loss": 1.1599,
-      "step": 10000
-    },
-    {
-      "epoch": 2.649644706732506,
-      "grad_norm": 0.5096309781074524,
-      "learning_rate": 0.0009116678711956958,
-      "loss": 1.1506,
-      "step": 11000
-    },
-    {
-      "epoch": 2.8905214982536434,
-      "grad_norm": 0.479825496673584,
-      "learning_rate": 0.0009036376776680318,
-      "loss": 1.1389,
-      "step": 12000
-    },
-    {
-      "epoch": 3.13139828977478,
-      "grad_norm": 0.4735005795955658,
-      "learning_rate": 0.0008956074841403679,
-      "loss": 1.1269,
-      "step": 13000
-    },
-    {
-      "epoch": 3.3722750812959172,
-      "grad_norm": 0.5051562190055847,
-      "learning_rate": 0.0008875772906127038,
-      "loss": 1.116,
-      "step": 14000
-    },
-    {
-      "epoch": 3.613151872817054,
-      "grad_norm": 0.48939937353134155,
-      "learning_rate": 0.0008795470970850398,
-      "loss": 1.11,
-      "step": 15000
-    },
-    {
-      "epoch": 3.854028664338191,
-      "grad_norm": 0.43153703212738037,
-      "learning_rate": 0.0008715169035573758,
-      "loss": 1.0959,
-      "step": 16000
-    },
-    {
-      "epoch": 4.094905455859328,
-      "grad_norm": 0.4543096125125885,
-      "learning_rate": 0.0008634867100297117,
-      "loss": 1.0903,
-      "step": 17000
-    },
-    {
-      "epoch": 4.335782247380465,
-      "grad_norm": 0.4869837164878845,
-      "learning_rate": 0.0008554565165020477,
-      "loss": 1.0827,
-      "step": 18000
     }
   ],
   "logging_steps": 1000,
@@ -152,7 +33,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8006571361081754e+17,
+  "total_flos": 1.0003876480548864e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:774cac0098b0da6548d23bcab6e1119da0b3be368b10412f62ce5bbf50ef0802
+oid sha256:0e18ec5730a38ec86822609eef175321578f30afb709c8cd04e2b0522a0e28c7
 size 5112