Training in progress, step 1000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.1",
+  "unk_token_id": 0,
+  "use_cache": false,
+  "vocab_size": 250880
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1155008f4624e7db0acb97980ee4edce3ddeba7204024679161570fc7a502762
+size 2236955191

runs/Sep27_11-50-57_163646036bff/1664279476.271967/events.out.tfevents.1664279476.163646036bff.68.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554331629e38a2c37d75d002710d137c6966f0cd7adc37f5f047dc99970bb5d7
+size 5548

runs/Sep27_11-50-57_163646036bff/events.out.tfevents.1664279476.163646036bff.68.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e6cd6d2f532f7148049ecd92606dc60c973aefc3eccd68386e27310444609b
+size 8146

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ec16c1d2f7cd3fbadcb6fd0f7701b4449c87e76e12b26e1b50a29ab9847d61
+size 3375